arXiv research

The paper analyzes GTD algorithms with finite-sample bounds.

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

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

Despite the increasing interest in multi-agent reinforcement learning (MARL) in multiple communities, understanding its theoretical foundation has long been recognized as a challenging problem. In this work, we address this problem by providing a finite-sample analysis for decentralized batch MARL with networked agents…

The paper shows how to learn causal representations with few environments and finite samples.

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…

Paper analyzes online tensorial ICA convergence with stochastic approximation.

This work analyzes tree-based methods from a ranking perspective, providing insights and new statistics.

We test for departures from normal and independent and identically distributed (NIID) returns, when returns under the alternative hypothesis are self-affine. Self-affine returns are either fractionally integrated and long-range dependent, or drawn randomly from an L-stable distribution with infinite higher-order moment…

This study analyzes LTS in sparse models with finite sample error bounds.

Paper analyzes PSGLD for adaptive IRL with finite-sample bounds.

This work closes the gap between theory and practice for nICA identifiability.

The paper introduces a frequency-domain estimator for low-order systems from noisy data.

We study finite sample properties of estimators of power-law cross-correlations -- detrended cross-correlation analysis (DCCA), height cross-correlation analysis (HXA) and detrending moving-average cross-correlation analysis (DMCA) -- with a special focus on short-term memory bias as well as power-law coherency. Presen…

The paper analyzes off-policy TD-learning using generalized Bellman operators and provides finite-sample bounds.

The paper studies how more data affects prediction risk in high-dimensional models.

Method constructs nonparametric prediction intervals with finite-sample guarantees.

Paper introduces a new reinforcement learning method with improved performance.

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

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…

New method reduces sample complexity for robust reinforcement learning.

The paper investigates topic models, ensuring their statistical identifiability and accuracy.

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…

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…

The paper analyzes how the one-dimensional Wasserstein distance captures pointwise density differences in finite samples.

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

Study on distributional TD learning with linear approximations for better return estimation.

MF-TRPO optimizes MFGs with finite sample guarantees.

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

Bitcoin volatility analysis shows decreasing HE with longer sampling periods.

New method predicts state evolution for non-first-order algorithms on nonconvex problems.

Proposes MPCA for robust PCA using mode estimation.

We learn linear models from nonlinear systems using multiple trajectories and regularization.

Deep learning method improves regression accuracy.

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

We adapt a Markov Random Field learning algorithm for continuous variables.

A study on a surprising phase transition in model generalization error as parameters approach sample size.

In risk management, tail risks are of crucial importance. The assessment of risks should be carried out in accordance with the regulatory authority's requirement at high quantiles. In general, the underlying distribution function is unknown, the database is sparse, and therefore special tail models are used. Very often…

Algorithm improves online canonical correlation analysis.

Unified method for MMD variance estimation improves accuracy and computational efficiency.

In this paper, we analyze the finite sample complexity of stochastic system identification using modern tools from machine learning and statistics. An unknown discrete-time linear system evolves over time under Gaussian noise without external inputs. The objective is to recover the system parameters as well as the Kalm…

Unified theoretical guarantees for distribution-free changepoint detection and testing.

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…

Develops methods to adjust prediction set coverage based on post-selection analysis.

Unified coverage analysis for linear off-policy evaluation in reinforcement learning.

Study shows DQN's performance degrades with temporal dependence in data.

The paper provides bounds on estimation error in a distributed online learning setting.

Study shows interpolating predictor's risk is optimal in low-dimensional factor regression models.