arXiv research

This paper analyzes momentum Q-learning with finite-sample guarantees.

The paper analyzes GTD algorithms with finite-sample bounds.

Unified framework for finite-sample RL algorithms using Lyapunov theory.

Paper provides convergence guarantees for off-policy NAC with finite sample complexity.

Paper analyzes Greedy-GQ for reinforcement learning with Markovian noise.

Improved mean estimation for symmetric distributions with finite-sample guarantees.

The paper investigates the convergence of Vendi scores under finite samples and introduces a truncated version for better performance.

MF-TRPO optimizes MFGs with finite sample guarantees.

Study convergence and approximations of entropic regularized Wasserstein distances for Gaussian and RKHS measures.

Paper analyzes online tensorial ICA convergence with stochastic approximation.

New framework improves EM algorithm convergence under log-Sobolev inequality.

We provide finite-sample analysis of a general framework for using k-nearest neighbor statistics to estimate functionals of a nonparametric continuous probability density, including entropies and divergences. Rather than plugging a consistent density estimate (which requires $k \to \infty$ as the sample size $n \to \in…

In reinforcement learning (RL) , one of the key components is policy evaluation, which aims to estimate the value function (i.e., expected long-term accumulated reward) of a policy. With a good policy evaluation method, the RL algorithms will estimate the value function more accurately and find a better policy. When th…

Unified view on learning unnormalized distributions using NCE.

Develops robust MDPs for unknown disturbances with performance guarantees.

Paper analyzes convergence rates of two time-scale AC and NAC algorithms.

In Bayesian inference, the posterior distributions are difficult to obtain analytically for complex models such as neural networks. Variational inference usually uses a parametric distribution for approximation, from which we can easily draw samples. Recently discrete approximation by particles has attracted attention …

The paper analyzes reinforcement learning methods for estimating weights and quality functions with fast convergence rates.

DDPMs are robust to noisy score estimates and achieve optimal convergence rates in Wasserstein-2 distance.

A theorem for debiasing machine learning with finite sample guarantees.

Paper introduces a new reinforcement learning method with improved performance.

This work analyzes nonexpansive stochastic approximations with Markovian noise, proving convergence in reinforcement learning.

Proofs high-dimensional spectrum convergence of weighted sample covariance.

New model-free DR-RL algorithm with finite sample complexity.

In this work we investigate to which extent one can recover class probabilities within the empirical risk minimization (ERM) paradigm. The main aim of our paper is to extend existing results and emphasize the tight relations between empirical risk minimization and class probability estimation. Based on existing literat…

SGDM accelerates faster than SGD with large batch sizes and permits broader learning rates.

This study approximates distances between Gaussian processes and covariance operators using RKHS.

AMP method reconstructs rank-one matrices from noisy data efficiently.

Stochastic Approximation (SA) is a popular approach for solving fixed-point equations where the information is corrupted by noise. In this paper, we consider an SA involving a contraction mapping with respect to an arbitrary norm, and show its finite-sample error bounds while using different stepsizes. The idea is to c…

Gradient descent converges to a small neighborhood of the true parameter in logistic regression with Gaussian design.

SARSA is an on-policy algorithm to learn a Markov decision process policy in reinforcement learning. We investigate the SARSA algorithm with linear function approximation under the non-i.i.d.\ data, where a single sample trajectory is available. With a Lipschitz continuous policy improvement operator that is smooth eno…

Triangular flows ensure statistical consistency and fast rates in generative modeling.

Study proposes efficient estimators for matrix-valued linear regression under sparsity assumptions.

Unified framework for generalized Venn and Venn-Abers calibration for reliable prediction.

Estimating entropy and mutual information consistently is important for many machine learning applications. The Kozachenko-Leonenko (KL) estimator (Kozachenko & Leonenko, 1987) is a widely used nonparametric estimator for the entropy of multivariate continuous random variables, as well as the basis of the mutual inform…

Estimates path-valued data using signature metrics and local kernels.

Unified framework for solving fixed-point equations in deterministic and stochastic settings.

We consider a situation in which we see samples in $\mathbb{R}^d$ drawn i.i.d. from some distribution with mean zero and unknown covariance A. We wish to compute the top eigenvector of A in an incremental fashion - with an algorithm that maintains an estimate of the top eigenvector in O(d) space, and incrementally adju…

Principal component analysis (PCA) has been a prominent tool for high-dimensional data analysis. Online algorithms that estimate the principal component by processing streaming data are of tremendous practical and theoretical interests. Despite its rich applications, theoretical convergence analysis remains largely ope…

Paper analyzes TD($λ$) convergence rates for arbitrary features.

Nearest neighbor methods are a popular class of nonparametric estimators with several desirable properties, such as adaptivity to different distance scales in different regions of space. Prior work on convergence rates for nearest neighbor classification has not fully reflected these subtle properties. We analyze the b…

New method reduces sample complexity for robust reinforcement learning.

A study on $\alpha$-GANs proving convergence and estimation guarantees.

Study best-response learning dynamics in zero-sum polymatrix games under full and minimal information settings.

We present asymptotic and finite-sample results on the use of stochastic blockmodels for the analysis of network data. We show that the fraction of misclassified network nodes converges in probability to zero under maximum likelihood fitting when the number of classes is allowed to grow as the root of the network size …

GANs learn distributions well from samples, with rates depending on intrinsic dimension.

The study provides statistical guarantees for Bayesian variational boosting.

We formalize AURC and develop estimators for SC systems.