arXiv research

This work uses sampling theory to analyze smoothness and error bounds of finite neural networks.

The study sets lower bounds on MMSE for inferring sensitive features from noisy data.

New bounds show current methods overestimate system parameter errors.

Estimates barycenter in geodesic spaces with finite sample bounds.

The paper analyzes LOCV for high-dimensional risk estimation, proving error bounds.

This paper analyzes error bounds for biased SMC samplers in conditional sampling.

End-to-end algorithm for controlling bilinear systems with probabilistic noise.

We identify linear models from nonlinear systems with initialization constraints.

CNFs learn distributions from samples with error bounds.

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

Sparse feature selection improves batch RL efficiency.

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

Paper analyzes online tensorial ICA convergence with stochastic approximation.

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

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

The paper analyzes GTD algorithms with finite-sample bounds.

Detect changes in noisy dynamical systems using empirical approximations and finite-sample bounds.

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

Paper derives PAC-Bayesian bounds for LTI systems learning from empirical data.

Study identifies and analyzes three types of errors in learning Fourier operators.

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…

Consider the task of estimating a 3-order $n \times n \times n$ tensor from noisy observations of randomly chosen entries in the sparse regime. We introduce a similarity based collaborative filtering algorithm for estimating a tensor from sparse observations and argue that it achieves sample complexity that nearly matc…

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…

Learn dynamics of a system using auxiliary data from similar systems.

The paper provides guarantees for feedback control with sensor errors.

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…

Study error bounds in evaluating distributional computational graphs.

The study establishes minimax bounds for estimating operators from noisy samples.

New bounds derived for KG algorithm's performance in finite time.

We consider least squares estimation in a general nonparametric regression model. The rate of convergence of the least squares estimator (LSE) for the unknown regression function is well studied when the errors are sub-Gaussian. We find upper bounds on the rates of convergence of the LSE when the errors have uniformly …

FQE with deep neural networks achieves asymptotic normality and finite-sample bounds.

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

Adapts RKHS methods to estimate density ratios with optimal error.

The paper analyzes the probabilistic structure of DDPMs and bounds their sampling error.

We consider the dynamics of a linear stochastic approximation algorithm driven by Markovian noise, and derive finite-time bounds on the moments of the error, i.e., deviation of the output of the algorithm from the equilibrium point of an associated ordinary differential equation (ODE). We obtain finite-time bounds on t…

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

Estimates time-series drifts from i.i.d. data using a direct Nadaraya-Watson plug-in method.

Sharp bounds derived for test error of finite-rank kernel ridge regression.

We consider the problem of off-policy evaluation for reinforcement learning, where the goal is to estimate the expected reward of a target policy $π$ using offline data collected by running a logging policy $μ$. Standard importance-sampling based approaches for this problem suffer from a variance that scales exponentia…

In this paper, we study the performance of extremum estimators from the perspective of generalization ability (GA): the ability of a model to predict outcomes in new samples from the same population. By adapting the classical concentration inequalities, we derive upper bounds on the empirical out-of-sample prediction e…

The paper improves methods for estimating set size using samples.

The OLS estimator optimally identifies stable linear systems with a finite number of samples.

New method improves understanding of machine learning model performance.

Paper reduces sample complexity for bilinear systems identification to nearly constant.

We introduce a simulation method for dynamic portfolio valuation and risk management building on machine learning with kernels. We learn the dynamic value process of a portfolio from a finite sample of its cumulative cash flow. The learned value process is given in closed form thanks to a suitable choice of the kernel.…

New algorithm learns changing discrete distributions with minimal drift error.

Study tests whether trade-off functions are above or below benchmarks using finite samples.

Improved stochastic optimization outperforms standard methods.