arXiv research

New statistical test for change-point detection using relative entropy.

Paper improves confidence intervals for LSA with multiplier bootstrap.

Paper develops efficient incomplete U-statistics for degenerate cases.

Deep Gaussian Processes with polynomial kernels can collapse rapidly without proper hyperparameter tuning.

Paper derives convergence rates and confidence intervals for LSA with Markovian noise.

New bounds for SGD in high dimensions improve inference efficiency.

Kernel smoothing on unknown manifolds with bounds and asymptotic normality.

Paper stabilizes bandit learning with regularization, improving inference under adaptive sampling.

We give a comprehensive theoretical characterization of a nonparametric estimator for the $L_2^2$ divergence between two continuous distributions. We first bound the rate of convergence of our estimator, showing that it is $\sqrt{n}$-consistent provided the densities are sufficiently smooth. In this smooth regime, we t…

Paper develops robust methods for large-scale testing without tuning parameters.

Mondrian random forests improve statistical inference for regression.

Study on volumes of random inscribed polytopes in projective geometries.

Random forests remain among the most popular off-the-shelf supervised learning algorithms. Despite their well-documented empirical success, however, until recently, few theoretical results were available to describe their performance and behavior. In this work we push beyond recent work on consistency and asymptotic no…

The paper provides Gaussian approximations for decentralized Federated Learning.

We consider the problem of providing nonparametric confidence guarantees for undirected graphs under weak assumptions. In particular, we do not assume sparsity, incoherence or Normality. We allow the dimension $D$ to increase with the sample size $n$. First, we prove lower bounds that show that if we want accurate infe…

Novel bounds improve TD learning consistency in RL.

Paper develops Gaussian approximations and bootstrap for federated LSA with trade-off bounds.

Paper improves CLT and bootstrap approximations for LSA with decreasing step size.

Cheap methods improve uncertainty in SGD solutions.

Study on financial systems using perturbed unimodal maps with heteroscedastic noise.

New statistical methods improve TD learning for policy evaluation.

We present a generic compact computational framework relying on structured random matrices that can be applied to speed up several machine learning algorithms with almost no loss of accuracy. The applications include new fast LSH-based algorithms, efficient kernel computations via random feature maps, convex optimizati…

The paper improves conformal prediction by analyzing the beta law of conditional coverage.

The paper provides rigorous guarantees for m-out-of-n bootstrap estimators of sample quantiles.

Motivated by modern applications in which one constructs graphical models based on a very large number of features, this paper introduces a new class of cluster-based graphical models, in which variable clustering is applied as an initial step for reducing the dimension of the feature space. We employ model assisted cl…

This work studies the smooth 1-Wasserstein distance and its limit distribution in high dimensions.

This paper improves reinforcement learning by estimating return distributions using quantiles.

This paper improves reinforcement learning by estimating return distributions using quantiles.

Paper provides Edgeworth expansions for network moments, improving accuracy of sampling distributions.