arXane › Statistics › Statistics
Wednesday, 4 November 2026: 9 new papers, 24 cross-lists and 27 replacements in Machine Learning (stat.ML), in arXiv's order, with full abstracts. The same papers as arXiv's own listing, set as a newspaper; every title links to arXiv.
We study nonparametric estimation and forecasting for GARCH-type processes and propose an iterated neural estimator that alternates between estimating the recursion map and updating the unobserved conditional variances. Under mild conditions, we establish finite-sample bounds for the time-averaged in-sample variance-path error and show that the estimator is minimax rate-optimal up to logarithmic factors. Under stationarity and mixing conditions, we establish the same rate for recursion-map estimation and derive finite-sample bounds for out-of-sample variance forecasts and expected excess Gaussian quasi-likelihood (QLIKE) loss. The convergence rates depend on the true lag orders and remain unchanged when the fitted orders are overspecified. Simulation studies illustrate the effectiveness of our estimators under nonlinear and time-varying volatility dynamics. Real-data applications suggest that our neural methods perform competitively and can incorporate option-price and high-frequency information.
Motivated by the expressive power of neural ordinary differential equations in flow-based generative modeling, we study the approximation of probability measures by pushforwards generated by parameterized families of Lipschitz vector fields. For Wasserstein distances, we establish a quantitative relationship between finite-sample point interpolation and distributional approximation, and derive universality criteria based on $L^p$-approximation of transport maps. In particular, affine-invariant families containing a non-affine vector field are universal from compactly supported absolutely continuous base measures. For total variation, we show that coordinate-wise dynamics are insufficient in dimensions $d\geq 2$ and establish sufficient conditions based on one-dimensional Sobolev approximation and shear-type mixing. We further examine the role of point interpolation, establishing when different regimes relate to one another and when approximate interpolation can be made exact.
Set separation by continuous linear functionals is fundamental in functional analysis and convex optimization and underlies binary classification in machine learning. Support vector machines provide maximum-margin affine separators for linearly separable data, while kernel methods represent nonlinear decision rules through linear separation in a reproducing-kernel Hilbert space. We study when two classes, not necessarily convex or linearly separable in the input space, can be separated with positive margin by finite ReLU networks and by random ReLU features. At the deterministic level, we prove that positive-margin separation by a finite ReLU network is equivalent to the existence of finite closed convex covers whose opposite-label members have positive pairwise distances, and exactly two hidden layers suffice. For random separation, suppose each class is represented as a finite union of nonempty closed convex cells, possibly unbounded. If every opposite-label cell pair has positive distance and its closed difference cone is pointed, then two independent random ReLU layers yield a common positive-margin affine separator with high probability. The first layer separates the feature image of each negative cell from the feature image of the positive class by a hyperplane through the origin. It also controls all cross-class distances uniformly. The second layer combines cellwise scores through Chebyshev polynomials and realizes the resulting polynomial using Gaussian Hermite features, followed by a uniform finite-width approximation. With the remaining geometric, bias, and confidence parameters fixed, each sufficient width is quadratic in the largest Gaussian width of a spherical difference-cone section, hence at most linear in its span dimension. An example shows that this squared Gaussian-width dependence is sharp for both layers.
Data-driven algorithms are ubiquitous across industries, and there is an extensive literature on analyzing their \emph{average} performance. The risk profile of such algorithms, while critical, is much less understood. This paper quantifies the risk of data-driven policies and isolates its sources. We evaluate a policy through the conditional value-at-risk (CVaR) of its loss over the training sample, any policy randomization, and the future outcome, at a fixed unknown distribution. Regret against an oracle that knows the distribution decomposes into expected post-sample regret (PS), the average outcome-only CVaR gap of the selected action, and a sample-risk premium (SR), the additional tail risk omitted by averaging those evaluations. The analogous premium vanishes under expected loss. We characterize when the premium vanishes and how large it is relative to post-sample regret. For losses with a continuous density near the tail cutoff, we identify conditions under which both components decay at the same rate, yet the limiting ratio of the premium to post-sample regret can reach the thousands. When a probability mass at the cutoff moves with the action, the premium can decay more slowly and dominate post-sample regret. We establish conditions under which sample average approximation learns the oracle action at rate $n^{-1/2}$ in both settings, but its combined-risk regret is of order $n^{-1}$ in the first and $n^{-1/2}$ in the second. In finite-sample numerical examples of SAA in both settings, the premium accounts for approximately $74\%$--$97\%$ of regret.
We study online learning with directed weakly observable feedback graphs and propose a Follow-the-Perturbed-Leader (FTPL) policy that achieves best-of-both-worlds guarantee with nearly linear expected time complexity. To preserve the simple structure of FTPL, we develop a novel graph-based loss estimator that combines forced exploration, conditional geometric resampling and adaptive learning rates with surrogate probabilities. Our policy achieves $\tilde{\mathcal{O}}(\delta_*^{1/3} T^{2/3})$ regret for adversarial regimes as well as $\tilde{\mathcal{O}}(\delta_* \log T / \Delta_{\min}^2)$ regret for stochastic regimes, where $\delta_*$ and $\Delta$, respectively, denote the fractional weak domination number and the suboptimality gap. These results show that refined guarantees for problems with minimax regret of $\Theta(T^{2/3})$ can be obtained through appropriately designed adaptive learning rates and loss estimators without sacrificing the simplicity of FTPL.
Ranking models define probability distributions over rankings and are fundamental in applications such as preference learning and decision-making. Without structural assumptions, these models are intractable due to their factorial complexity. Although independence assumptions are key to reducing complexity and enabling interpretability, standard notions of conditional independence must account for the mutual exclusivity constraints inherent to rankings. We introduce relative rank models, a probabilistic framework based on structured coarsenings of the ranking space that relax these constraints while preserving relative order information. This representation enables a well-defined notion of conditional independence for rankings and allows rankings to be modeled using Bayesian networks. As a result, standard methods for learning and probabilistic inference can be applied to rankings, with interpretable representations based on conditional independence. We further show that two prominent ranking models based on independence assumptions tailored to rankings arise as special cases, providing a unifying framework for independence in ranking models.
Distributed learning has drawn considerable attention due to its capability of learning from distributed data without aggregating raw observations. However, frequent exchange of model updates can become the main bottleneck of communication. Therefore, one-shot approaches where each worker fits a local model and sends it to the server to aggregate emerge. It is known that averaging can achieve the so-called pooled-data mean squared error (MSE) order of a hypothetical node that has access to data from the server and all the workers, and performs empirical risk minimization (ERM) on it. However, when the number of workers increases too fast compared to the local sample size, nonzero local estimation bias prevents averaging from achieving this order. In this paper, we study whether independent server data can overcome this limitation. We consider $m$ workers with $n$ observations each and a server with $p$ observations, all i.i.d., giving $N=mn+p$ observations in total. Under certain regularity conditions, a pooled-data ERM achieves MSE of order $\mathcal O(N^{-1})$. We analyze deterministic nonnegative averaging of convex-loss M-estimators, with equal worker weights and the server's own estimator included. Under our assumptions, including nonzero local bias of order $n^{-\alpha}$, $\alpha\geq1$, sample-size weighted averaging achieves the pooled-data MSE order whenever $m=\mathcal O(n^{2\alpha-1})$. Above this worker scale, it does so if and only if $p=\Omega(nm\cdot m/n^{2\alpha-1})$. Hence, server-only estimation, whose MSE is of order $\mathcal{O}(p^{-1})$, can achieve pooled-data order while sample-size weighting fails. Analytical examples and synthetic experiments illustrate when averaging matches the pooled-data MSE order, complemented by CIFAR-10 experiments comparing aggregation strategies with linear and nonlinear classifiers.
Real-world time series exhibit complex dynamics across multiple temporal resolutions, yet effectively incorporating multi-scale information into generative modeling remains challenging without increasing generative complexity. We propose UniFlow, a unified framework that integrates multi-scale representation learning with efficient non-autoregressive generation through a shared-semantic discrete interface. Specifically, a multi-scale tokenizer employs shared-index voting to consolidate complementary temporal information into a single public-ID sequence, while scale-specific codebooks preserve the information required for reconstruction. Building on this unified representation, we develop geometry-aware categorical flow matching, which initializes transport from learned low-rank anchors and generates public identities non-autoregressively. This design captures multi-scale temporal structure without requiring multiple generative token streams or sequential token decoding. Experiments across four benchmarks and both short- and long-term settings demonstrate improved generative fidelity, strong cross-scale consistency, and substantial inference speedups over representative autoregressive and diffusion-based baselines. Code is available at https://github.com/William-Liwei/uniflow
We study a fundamental problem in machine learning: partial recovery of a planted signal $\boldsymbol{v} \in \mathbb{S}^{n-1}$ from a spiked tensor $\boldsymbol{\mathsf{X}} = \lambda \, \boldsymbol{v}^{\otimes p} + \boldsymbol{\mathsf{Z}}$, where $\boldsymbol{\mathsf{Z}}$ has symmetric Gaussian entries of variance $\asymp n^{-1}$. While previous works replace $\boldsymbol{\mathsf{Z}}$ by an i.i.d. standard Gaussian tensor to circumvent technical difficulties caused by dependencies, this paper directly analyzes the symmetric model via random matrix theory. We show that the square unfolding algorithm is subject to a sharp phase transition for partial recovery at $\lambda \asymp n^{(p-2) / 4}$, validating an open conjecture from Montanari and Richard (2014). We get precise expressions for the limiting spectral distribution, deterministic equivalent, phase transition threshold and overlap. The main message is that unfolded symmetric tensors spectrally behave like standard Wigner matrices, up to simple transformations accounting for high-order symmetries. We consider extensions to multiple orthogonal spikes, recursive unfolding and non-square unfolding via disproportionate random matrix theory, leading to an interesting conjectured statistical-computational tradeoff regarding the choice of unfolding: square versus long.
We introduce the Axiomatic Learning Structures (ALS) and Axiomatic Probabilistic Structure (APS) in order to study the interactions of Machine Learning, Optimization, with research frameworks- which, we take the view, can be characterized at the core by the corresponding axioms. The ALS explores the interplays between structures that one is interested in Learning Theory such as Loss functions and the axioms of the objects and transformations involved in these functions. The APS studies the interaction between structures of interest in Probability Theory such as Gibbs distributions, equations with noise, etc. and the axioms of the corresponding objects and transformations. We also introduce in Section 6 Transformations-Axiomatic Based Learning (TABLe) on Mathematical data-sets. One feature of this approach is the ranking of transformations from a table for a certain task based on scores which reflect which transformations work better than others, similarly to when human investigators try various methods on a task. We also study structure recovery from noisy data. In particular, to exemplify the ideas, we consider loss functions which contain derivations and derivations-like transformations. As a first application we study recovery in the context of polynomials with integer coefficients using standard derivatives along with other types of derivations which appear in Arithmetic: the p-derivations which satisfy \textit{different axioms} from the usual derivatives. As a first application of the APS we study a class of noisy (partial/mixed) derivations equations. In the last sections, to provide further potential applications of this framework, we give an overview of an initial simplified Opinion Dynamics model and its (simultaneous) study of rules of updates.
Bubeck and Sellke's universal law of robustness says that fitting $n$ noisy samples below the noise level with a class of $p$ real parameters forces a Lipschitz constant of order $\sqrt{nd/p}$, when the covariate distribution on $\mathbb{R}^d$ is isoperimetric: smooth interpolation costs a factor $d$ of overparametrization. Its hypotheses are Gaussian-type concentration, a homogeneous covariate law, scalar outputs, and independent samples; we relax each one. Exponential concentration suffices, at the unchanged rate and absolute constant and at the price of a capacity burn-in, some form of which we show is necessary; this gives the law for normalized log-concave covariates, with a $\log d$ loss from the current KLS bound. For heterogeneous mixtures the worst component constant is replaced by the weighted average of the component constants, under a typicality condition on the mixture composition. For vector-valued predictors the bound at the Frobenius Lipschitz scale is free of the output dimension $K$, and the Euclidean bound loses only $K^{-1/2}$, a loss that covariate-independent noise removes. Stationary Markov covariates retain the i.i.d. rate, the pseudo-spectral gap entering only the sample-size conditions. One master theorem carries the shared argument, and constants are explicit throughout.
Groundwater inversion is commonly built on Gaussian assumptions for both network weights and output errors. The assumptions are convenient, but it is unclear which one should be relaxed when hydraulic conductivity is heavy tailed. Here, Gaussian and q-Gaussian distributions were assigned independently to variational weights and the conditional output likelihood in a $2\times2$ Bayesian neural design. Hydraulic conductivity, porosity, and dispersion were inferred jointly from sparse head and transport observations. Four q regimes ($q=1.0$, 1.2, 1.5, and 1.8) were evaluated with five independently generated data sets and matched training seeds, giving 130 held-out cases per regime and 500 posterior draws per case. At $q=1.5$, q-Gaussian weights with a Gaussian likelihood reduced log-conductivity CRPS by 2.85\% (95\% paired CI 0.82--4.88) and calibration error by 3.72 percentage points. Conductivity RMSE was unchanged, while 95\% interval width increased by 9.86\%. At $q=1.8$, assigning q-Gaussian tails to both components produced no stable accuracy gain and increased interval width by 138.46\%. The Gaussian-generated porosity and dispersion controls showed negligible accuracy changes. Moderate weight-side tails can thus improve distributional prediction, whereas an overly heavy output likelihood trades sharpness for coverage. Separating these two roles provides a clearer basis for uncertainty modeling in groundwater inversion.
Training a classifier means letting a validation metric decide which model is kept and when training stops. A natural requirement on that metric is superiority: every correctly classified forecast should score better than every incorrectly classified one, however close the underlying probabilities are. Neither the Brier score nor the logarithmic score satisfies this on its own. We show that superiority is governed by the separation between two endpoints -- the supremum of the score on correct predictions and the infimum on incorrect predictions -- and derive both in closed form for each score. Their difference is the infimal penalty, the greatest lower bound on the penalty needed to restore superiority. Prior work restores superiority with a penalty calibrated from the first endpoint alone; for the Brier base, our infimal penalty is smaller than that published penalty by a factor ranging from 4.00 at three classes to 2.11 at twenty. We further embed the published and infimal penalties in a one-parameter family and show that, under a single-valued tie convention, every member of the family is strictly proper. In a pre-specified two-dataset case study, mean selected-model macro-F1 rises with the penalty in the reported ten-class regimes, though not distinguishably from noise once seed/selection-mode nesting is accounted for; a fifth regime at forty-seven classes does not reproduce even this descriptive pattern. The intended no-superiority baseline is algebraically a rescaling of the family under test, so the experiment cannot attribute the observed pattern specifically to superiority. When superiority itself is the objective, any penalty strictly above the infimal value suffices; choosing a larger penalty is a separate calibration trade-off rather than a requirement for the guarantee.
Accurate forecasting and temporal downscaling of solar irradiance is critical for reliable renewable energy integration and grid management. Traditional methods often struggle to capture rapid irradiance variability. In this work, we develop a Transformer-based architecture for simultaneous forecasting and temporal downscaling. The model takes input data at arbitrary resolutions and generates outputs at any resolutions represented within the training data, leveraging both global and local contextual information. To improve training efficiency, a genetic algorithm-based optimization framework is implemented to identify suitable model hyperparameters, while reducing the computational cost of exhaustive grid search. The effectiveness of the proposed model is shown by analyzing real data in Dallas, Texas. The proposed model achieved root mean square error (RMSE) values of 28.785, 29.544, 30.157, 32.132~W/m\(^2\) for 15-, 30-, 60-minute, and irregularly spaced global input and producing forecast at 5-minutes resolution, respectively. Furthermore, this model produced reliable uncertainty estimates, exhibiting wider prediction intervals for high-resolution inputs during volatile solar conditions, whereas coarser-resolution inputs result in narrower intervals and significantly lower training time and computational cost. Our approach provides a scalable and efficient framework for multi-resolution solar irradiance forecasting and temporal downscaling, suitable for practical energy forecasting and grid management applications.
We develop PanelGP, a conditional factor model for large panels of stock returns in which firm characteristics determine the factor loadings and economic conditions determine the expected factors. Both relations are estimated nonparametrically with Gaussian-process priors. The kernel choice nests instrumented principal component analysis (IPCA) as well as smooth nonlinear maps. Asset-specific loading innovations and common factor innovations separate idiosyncratic from systematic risk, so one estimated model forecasts both expected returns and their covariance matrix. Estimation uses sparse variational inference with a joint posterior over loadings and factors. Because each predicted return is bilinear in a Gaussian state, the predictive covariance matrix and the cumulants of any portfolio have closed forms. In simulations, the estimator recovers the nonlinear maps and the variance parameters. For S&P 500 constituents over 1995-2024, nonlinear loadings rank stocks better than affine loadings and improve the Gaussian log score. Relative to IPCA, the resulting portfolios have higher Sharpe ratios, also net of trading costs, and the minimum-variance portfolio has lower volatility. The predicted variances rank stocks and months by risk but are too compressed.
We study score learning from denoising pairs when the data contain a hidden non-Gaussian component. If covariance reveals the component, its subspace can be recovered directly. If covariance is isotropic, the first distinguishing moment has order $k^\ast$, and the learner must extract that moment from clean points and their noisy views. Correlations in the denoising loss are Stein discrepancies against a baseline; for polynomial fields they determine exactly the corresponding moment differences. Averaging fresh noisy views conditional on a clean point gives an exact moment query on the clean distribution. In the covariance-matched regime, orientation-independent dictionaries satisfying an $L^4/L^2$ condition need order $d^{k^\ast-1}$ features, and the stated dot-product kernel ridge models need the same power in samples. Small-step online SGD on one unit has this exponent up to logarithms. A two-stage learner uses the curvature of a smoothed denoising loss to recover the hidden direction, then sharpens it and fits a scalar readout. For every even $k^\ast$, it obtains a fixed score gain over the Gaussian baseline from $O(d^{k^\ast/2}\log d)$ clean points. In the covariance-visible regime, the frozen-feature threshold occurs at $d^J/J!$, while projection onto principal components makes the fitted-model, score-risk and generated-law distributions independent of ambient dimension. In the covariance-matched experiments, the measured partial-trace overlaps are consistent with the proposed spectral transition. A width-8 network trained with clean-point reuse shows a $d^2$-like training-set threshold over $d=64$--$192$, with fixed validation and calibration overhead.
Learn-then-Test (LTT) provides a general framework for certifying deployment policies against a prescribed risk target, but its standard formulation targets a fixed population risk estimated from calibration losses. In sequential deployment, losses may instead be dependent and nonstationary, so the risk of a fixed policy can evolve with the observed history. We introduce StreamLTT, which replaces this fixed population risk with average predictable risk, defined by conditioning each decision's loss on the information available before its outcome is revealed. Conditional centering turns empirical deviations from this target into a martingale sum, enabling both a test that adapts to predictable variance and a finite-sample Hoeffding alternative. Combined with family-wise error rate control, StreamLTT yields a simultaneously certified policy region that supports subsequent deployment selection. Across seven forecasting datasets and seven deployment risks, StreamLTT places the certified frontier substantially closer to the prescribed risk target than IID, robust-variance, block-bootstrap, and concentration-based alternatives, while empirical family-wise error closely follows the prescribed level. A finite-sample ablation further shows that the predictable-risk formulation drives the tighter risk frontier, while adaptation to predictable variance makes more effective use of the available family-wise error budget. StreamLTT therefore extends risk-certified policy selection to dependent deployment streams by addressing both what risk should be certified and how it should be tested.
Conformal prediction (CP) provides marginal coverage guarantees, but marginal coverage does not determine where prediction errors occur on a graph. Queries from different graph neighborhoods can exhibit substantially different levels of uncertainty even when aggregate coverage remains near its target. We introduce GLocalCP, an online CP framework for inductive node classification and edge prediction that combines marginal and graph-local calibration with uncertainty-adaptive prediction sets. Specifically, GLocalCP puts forth a novel uncertainty-adaptive nonconformality score that relies on the mutual information obtained from Monte-Carlo (MC) dropout based prediction. Then, it augments a global online threshold with a kernel-based local correction that propagates coverage feedback among similar graph queries. On the theoretical horizon, we establish pathwise $O(N^{-1/2})$ marginal calibration error without exchangeability or stationarity and, for the exact-kernel formulation, an explicit $O(N^{-1/2})$ graph-localized calibration guarantee. Experiments on seven node-classification and seven edge-prediction benchmarks show that similar marginal coverage can conceal substantially different local reliability. Our proposed GLocalCP maintains coverage near the target while consistently reducing graph-local calibration error. Uncertainty scaling in GLocalCP further reduces prediction-set size across all evaluated node and edge datasets while leaving marginal coverage essentially unchanged.
We study the minimization of the average of $n$ convex $(L_0,L_1)$-smooth functions: the Hessian norm of each function is bounded by an affine function of its gradient norm. We assume known upper bounds $R$ on the distance from the starting point to a minimizer and $\delta$ on the difference between the minimum of the average and the average of the infima of the components. We derive upper and lower bounds on the oracle complexity of reaching accuracy $\varepsilon$ in function value in expectation. Up to logarithmic factors, both bounds are of order $n(1+(L_1R)^{2/3}) +\sqrt{\frac{n(L_0+L_1^2\delta)R^2}{\varepsilon}+n(L_1R)^2}$. The upper bound is attained by the proposed method YETI. The method combines ideas of accelerated proximal methods and variance reduction methods with a heuristic for choosing additional points. The number of oracle calls made by the heuristic is bounded, which preserves the upper bound on the total number of queries needed to reach the target accuracy. In the experiments, YETI is compared with first-order methods on synthetic problems and Poisson regression problems. We also examine the stopping criterion and the effect of the heuristic separately. The lower bound is obtained by an explicit construction of families of instances that are hard for any first-order method.
Medicinal plants are usually identified using practitioners' experience, but reproducible, image based methods can complement this knowledge. We present MEDIPI (MEDIcinal Plant Identification), a statistical machine learning approach that classifies medicinal plant leaves from photographs. From each leaf image we extract 52 interpretable features covering shape, texture, color, and a new scagnostics category. We then classify leaves using a three level hierarchy: shape, then edge type, then species. We also release MedLEA, an open R package with 1,099 leaf images of 31 Sri Lankan medicinal plant species. On this dataset, a hierarchical Random Forest achieved the best overall accuracy (100%) in our comparison of hierarchical and non-hierarchical approaches and eight algorithms: Random Forest, XGBoost, Gradient Boosting, linear discriminant analysis, k-nearest neighbor, support vector machine, probabilistic neural network, and artificial neural network. Adding texture, color, and scagnostic features to shape features raised shape level accuracy from 90% to 97%. Linear discriminant analysis plots show how the trained model separates leaf shapes. Accuracy dropped sharply (23-50%) when training and test data came from different datasets, so generalization across datasets remains a challenge.
Standard spatiotemporal graph convolutional networks need a fixed-size adjacency matrix, coupling model weights to a specific sensor count N; they cannot produce any output at a sensor absent from training. We present OmniST, a topology-invariant forecaster whose computation has zero structural dependency on the number of nodes, and which, composed with inductive split-conformal calibration, gives distribution-free, coverage-guaranteed prediction intervals at arbitrary (including never-seen) sensor locations, preserving that guarantee as sensors are added or removed. Topology invariance follows from coordinate-based tokenization, k-nearest-neighbor attention from geographic coordinates at each forward pass, and per-node temporal processing via a bidirectional GRU. On real Delhi air-quality data (37 stations, 2019-2023), OmniST attains a 30-day PM2.5 MAE of 31.0 ug/m3 and degrades at most 1.1 percent when 40 percent of stations are removed. Its inductive forecasts at unseen stations beat nearest-neighbor interpolation (about 12 percent) and a learned kriging GNN (IGNNK, about 21 percent), and, unlike either, carry a finite-sample coverage guarantee. The guarantee holds at 90 percent or above under 30-50 percent node dropout across four real datasets over three domains (Delhi and Beijing air quality, NOAA GHCN weather, Caltrans PeMSD7-M traffic), and still holds at 325 real sensors (full PeMS-BAY). We also fix a temporal-drift failure: static conformal under-covers over time (about 0.50 late), but a rolling adaptive-conformal estimator restores target coverage (0.89 overall, 0.96 late) at the cost of wider intervals.
Quantifying the dimensionality of data is a fundamental need in machine learning and signal processing applications such as representation learning, data compression, and inverse problems, where the extrinsic dimension in which the data is presented can be very different from the intrinsic dimension that determines the operational performance. Various concepts, such as R\'enyi information dimension, rate-distortion dimension, and quantization dimension are useful here. Despite their theoretical significance, estimating these measures are challenging given their asymptotic definitions. Recent research has shown that analyzing the pairwise distortion distribution (PDD) of a data source can provide a tractable lower bound on the distortion of random codebook quantization, from which a tractable notion of intrinsic dimension can be derived. In this paper we extend this line of research in three main ways. First, we develop a related upper bound on distortion of random codebook quantization. Second, we improve the computability of both the lower and upper bounds, using a graph-based adaptive importance sampling approach. Third, we leverage the bounds to define new notions of intrinsic dimension which form upper and lower bounds on the R\'enyi information dimension, rate-distortion dimension, and quantization dimension, and which can be empirically estimated from unknown data sources. We illustrate the concepts by analyzing several artificial and empirical distributions.
We give a proper constant-factor agnostic learner for affine halfspaces under full-dimensional log-concave marginals. For arbitrary binary labels, the algorithm uses independent labeled samples and returns a single affine halfspace with error at most $C\mathrm{OPT}+\varepsilon$. Its sample and real-arithmetic complexity are polynomial in dimension, inverse accuracy, and the logarithm of the reciprocal failure probability. The mean and covariance of the marginal need not be known, and the sample complexity can be made linear in this logarithmic confidence factor. The main geometric result compares global disagreement with disagreement on a balanced restriction: for a minority halfspace of mass $p$, global disagreement is within universal constant factors of $p$ times conditional disagreement, provided the latter is sufficiently small. To construct the restriction from noisy labels, we estimate the minority cap's mean and covariance robustly, approximately minimize the classical zonoid-depth dual objective, and expand a superlevel set to a marginal quantile. The disagreement comparison cancels the noise amplification caused by conditioning and allows the learned halfspace to be used on the entire space. The analysis combines degree-four sum-of-squares moment bounds for log-concave laws with a translation-based reduction from balanced affine learning to homogeneous halfspace learning.
The classical model-based optimal design criteria (D-, T-, L-, C-, and A-optimality) are usually motivated via the Cram\'er--Rao bound as optimizing scalar functions of the Fisher information matrix (FIM). This paper offers a complementary reading in which each criterion appears asymptotically as $N \to \infty$ as the leading-order term of an expected dissimilarity between prior and posterior, with the FIM entering through the Bernstein--von Mises limit. The Kullback--Leibler (KL) divergence of the posterior relative to the prior recovers D-optimality (classically known); a reverse KL of the prior relative to the posterior recovers T-optimality (here defined as maximization of the trace of the FIM, following one common convention) and its weighted-trace generalization; and a first-order approximation of the squared 2-Wasserstein distance recovers L-, C- and A-optimality. The five criteria emerge as instances of a common Bayesian-geometric template, indexed by three choices: the dissimilarity, the prior parametrization, and the approximation scheme used to evaluate it (e.g.\ Taylor expansions of the matrix square root). For the weighted criteria, the Gaussian prior covariance encodes the criterion's weight matrix, so any choice of weights corresponds to a specific prior in the family. The T-, L-, C-, and A-optimality derivations appear novel to the best of my knowledge. A sixth criterion, E-optimality, is recovered not as an independent expected-dissimilarity limit but as a min-max robustification of C-optimality against uncertainty in the modeler's prior direction. The framework is extended to distinguish between a designer's prior over unknown parameters at design time and a modeler's prior used for posterior inference, recovering the classical expected information gain objective as a special case.
Many signal-processing objects are defined by periodicity, normalization, sign or global-phase ambiguity, basis invariance, or positive-semidefinite constraints and therefore cannot be modeled faithfully in ordinary Euclidean space. This paper develops a geometry driven framework for directional statistics in signal processing, connecting signal representations to their natural manifolds or quotient spaces and to probability models compatible with their invariances. After reviewing instances of directional statistics in the signal processing literature, we review circular, toroidal, spherical, projective, Stiefel, Grassmann, and covariance-valued distributions, emphasizing their statistical assumptions, computational requirements, and dimensional limitations relevant to signal processing. We describe various modeling and estimation strategies, including analytical and gradient-based maximum likelihood, structured low-rank parameterizations, mixtures and hidden Markov models (HMMs), score-based and contrastive estimation, and geometry-aware K-means. To exemplify the consequences of geometry-aware modeling, we study multivariate phase coherence in synthetic data and functional neuroimaging, comparing toroidal phase vectors to projective, Grassmann, and positive-semidefinite representations. We also study speaker separation in a car environment, showing that directional representations outperform a standard Euclidean model. These examples demonstrate that when the geometric representation, statistical distribution, inference method, and computational regime are considered together, they have the potential to lead to improved models across a broad range of signal processing applications.
LLM agents often give conflicting answers to the same question, and many deployed agents are variants of one base model, so their errors are correlated. We study truth discovery among such agents: inferring the true answer and each agent's reliability without labels. Classical truth-discovery and crowdsourcing estimators reward an agreeing bloc and can fall below majority vote. We propose BP-TD, which adds per-agent decorrelation weights to mean-field variational inference on a one-coin Dawid-Skene model, so that agents sharing a base model count together as about one vote. Its first iteration is exactly a weighted vote; later iterations estimate agent reliability. With 13 local agents on MMLU, BP-TD beats majority vote without any labels (0.716 vs. 0.624 on 160 questions; 0.707 vs. 0.674 on 10,000) and ranks agents by their true accuracy, which classical estimators invert. The gain depends on the pool: over 2,852 sub-pools of four benchmarks, decorrelation helps when the largest correlated bloc is weaker than the other agents and hurts when it is the strongest, and we found no label-free statistic that tells the two cases apart. Labels change the picture quickly: with 20 labelled questions, selecting the single best agent is more accurate than every aggregator we tested on MMLU, ARC and TruthfulQA.
Variable selection is an important task for interpreting potentially complex systems in fields such as biology, business, and sociology. The importance of variable selection has attracted considerable attention in statistics and machine learning. In this paper, we are mainly interested in model-agnostic variable selection for identifying variables that have general nonlinear dependence on the response. We propose MambaPFN, short for Model-Agnostic Markov BlAnket selection with Prior-data Fitted Networks, which is built upon the Transformer, a building block of many popular large language models. Specifically, we consider a functional-mapping perspective on variable-selection learning, in which the Transformer is treated as a learnable mapping from a dataset to its relevant variables. To learn this mapping, MambaPFN introduces three new components: (i) a faithful, rich, and scalable scheme for generating pretraining data, (ii) an objective that targets each variable's posterior inclusion probability, and (iii) a modified Transformer architecture tailored to variable selection. Once pretrained, MambaPFN is applied to new datasets without parameter updates. Empirically, MambaPFN achieves desirable variable-selection performance in simulation studies and exhibits a scaling law---more pretraining datasets and larger models can continuously improve its performance. Applied to a Facebook comments dataset, MambaPFN selects the fewest variables and achieves the highest computational efficiency and predictive performance, improving upon the best baselines by about 20%.
Cluster labels are often used twice: first to discover groups, and then to test whether the discovered groups differ. This double use of the data makes ordinary two-sample $p$-values anti-conservative. Selective inference fixes this by conditioning on the clustering event, but for spectral clustering the event appears difficult because the algorithm combines an affinity map, an eigendecomposition, and a rounding step. We show that, for spectral clustering based on unweighted $\varepsilon$- or $k$-nearest-neighbor graphs, the obstruction is the affinity construction rather than the eigendecomposition. Along the one-dimensional perturbation used by the truncated-$\chi$ selective test, graph changes occur only at finitely many real roots of data-dependent quadratic distance comparisons. Between these breakpoints, the graph, Laplacian spectrum, embedding, rounding, and reported cluster pair are deterministic functions of a finite graph state. Consequently, in real arithmetic and under a known-scale spherical Gaussian model, the selection set is an exact finite union of intervals, yielding finite-sample selective $p$-values for selected spectral-cluster pairs. The same argument gives feature-wise truncated-normal tests. We also record direct extensions to known feature covariance, eigengap-selected $K$, and auxiliary-coordinate graphs. We validate null and partial-null calibration, operational power, numerical sensitivity, and model-scope diagnostics, and give a working-model PBMC algorithmic illustration. Smooth kernels such as RBF affinities fall outside the finite-state guarantee.
We give an algorithm for PAC learning intersections of $k$ degree-2 polynomial threshold functions over $R^d$ under a Gaussian distribution. Our algorithm achieves classification error $\epsilon$ using $d^{O(k)}2^{O_k(\log^3(1/\epsilon))}$ time and samples, improving over the $d^{O(k^2/\epsilon^2)}$ running time of the polynomial regression approach. To our knowledge, our result is the first to obtain a dimension exponent independent of the accuracy parameter, even for $k=2$. We complement our algorithmic result with an SQ lower bound showing that the complexity dependence of $d^{\Omega(k)}$ is unavoidable. Lifting the input to polynomial features turns the target into an intersection of $k$ halfspaces. This suggests using the first two labeled moments for subspace recovery. In the lifted space, however, these moments can reveal nothing. Our starting point is a Gaussian comparison theorem showing that, for sufficiently regular defining quadratics, the labeled moments needed for subspace recovery are approximately preserved. To handle arbitrary defining quadratics, we establish a new structural result showing that every direction with significant resampling influence can be detected through degree-$O(k)$ moments. These results yield an initial $d^{O(k)}2^{\mathrm{poly}_k(1/\epsilon)}$-time learner using adaptive restrictions. To improve the exponential dependence on $1/\epsilon$, we develop a two-stage dimension-reduction approach that avoids the costly adaptive partitioning. After identifying a subspace containing all directions with large influence, we use generalized regularity and Gaussian comparison to recover the remaining relevant quadratic features through a new derivative-based moment operator. The recovered features support an intersection close to the target. Combining them with robust hinge-loss minimization gives our quasipolynomial-time learner.
Many scientific simulations are computationally expensive, limiting their use in simulation-based inference, uncertainty quantification, and decision making. We introduce macrocanonical generator networks, a framework for learning fast, data-efficient neural surrogates for amortized simulation of stationary physical processes by matching multiscale statistics of a target process. Inspired by microcanonical maximum-entropy synthesis, which matches feature statistics per sample by inner-loop optimization, our approach instead trains a neural generator to satisfy the same constraints in expectation, preserving physically realistic sample-to-sample fluctuations. We prove that gradient-descent training induces preconditioned gradient-descent dynamics in sample space that inherit the symmetry-preservation properties of the microcanonical gradient descent of Bruna and Mallat, amortizing its per-sample inner-loop optimization into a single training run after which every sample is generated in one forward pass. We further show that residual generator parameterizations initialized near the identity, trained with a small learning rate, preserve entropy locally during early optimization and mitigate mode collapse. Experiments on cosmology and fluid simulations show that macrocanonical generators recover realistic samples from extremely small training sets, in some cases a single training example, while generating new realizations more than $10^6$ times faster per sample than the reference simulator and more than $10^3$ times faster than microcanonical gradient descent. The trained generators can be reused for downstream pretraining, including simulation-based inference, providing a data-efficient route to multi-fidelity scientific machine learning workflows.
We provide the first computationally efficient, differentially private algorithms for agnostically learning halfspaces. In particular, we study three different settings of agnostic learning: improper learning under Gaussian and log-concave marginals; proper learning under Gaussian marginals; and semi-agnostic learning under Gaussian marginals. In all three aforementioned settings, the added cost in the sample complexity due to privacy matches the respective non-private sample complexity, implying that we get privacy for free.
Alternating online mirror descent (AltOMD) is a simple learning rule for zero-sum games, which improves upon simultaneous OMD numerically and theoretically. Previous work obtained $O(T^{1/3})$ and $O(T^{1/5})$ regret bounds for AltOMD, by leveraging modified-energy-function-based analyses. However, settling whether AltOMD achieves near-constant regret has remained an open question. In this paper we resolve the question of whether AltOMD achieves near-constant regret in the affirmative. In particular, we show an $O(log(T))$ regret bound on the sum of the players' external regrets for any two-player zero-sum bilinear game with compact convex strategy sets, under mild regularity assumptions on the regularizers. We verify that our assumptions hold for the negative entropy regularizer, thereby obtaining logarithmic regret for the alternating multiplicative weights updates algorithm. The regret bound also yields an $O(log(T)/T)$ duality gap bound for the averaged strategies.
Efficient preconditioning plays an important role in large-scale first-order optimization. In this paper, we propose an adaptive accelerated optimistic dual averaging ($\text{A}^2$ODA) method for unconstrained convex optimization that adopts low-cost preconditioning based on $p$-norm geometry for $p\in[2,\infty]$. The method is line-search-free and employs a new stepsize selection technique based on an aggregated affine lower model. Its update structure is simple and unified across $p\in[2,\infty]$, with the case $p>2$ requiring no more elaborate updates than the Euclidean case $p=2$. Under a generalized local smoothness condition, we derive a convergence bound that separates the effects of constant and gap-dependent curvature, with the latter potentially yielding faster-decaying terms. In the special case of local smoothness, this bound recovers a nearly optimal convergence rate.