arXiv research

Unified analysis of efficient local training methods for distributed variational inequalities.

Deep neural networks are optimal for dependent data using PAC-Bayes bounds.

Negative momentum accelerates convergence in minimax games but at a suboptimal rate.

Sharp inequality between TV and Hellinger distances for Gaussian mixtures.

Paper proposes a transfer learning method for improving matrix completion.

New RL algorithm for linear MDPs with nearly optimal regret.

The paper tackles deep learning from dependent data, achieving optimal performance.

Oracle inequality for sparse neural nets adapts to unknown structure.

Paper sets fundamental limits for distributed covariance estimation with constrained communication.

Study dual representations for quasiconvex systemic risk measures.

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

Paper introduces SGD for nonparametric additive models with optimal risk.

AGDA and variance-reduced methods solve nonconvex-nonconcave minimax problems globally and faster.

Bayesian approach to robust risk measures under model uncertainty.

In this work, we study the problem of aggregating a finite number of predictors for nonstationary sub-linear processes. We provide oracle inequalities relying essentially on three ingredients: (1) a uniform bound of the $\ell^1$ norm of the time varying sub-linear coefficients, (2) a Lipschitz assumption on the predict…

Optimizes treatment allocation using covariates for better outcomes.

Optimal CATE estimation with structured contrast functions using KRR.

The paper proves a diastolic inequality linking surface area and loop length.

MOPI optimizes flexible set-valued mappings to achieve superior shape adaptivity in conformal prediction.

The paper sets bounds on how much regret is unavoidable in adaptive LQR with unknown B-matrix.

Paper proposes a new algorithm to minimize AUC disparities in machine learning models.

Wavelet-based online learning adapts to noisy Besov spaces with high probability.

Sampling without replacement speeds up optimization in minimax problems.

The density matrices are positively semi-definite Hermitian matrices of unit trace that describe the state of a quantum system. The goal of the paper is to develop minimax lower bounds on error rates of estimation of low rank density matrices in trace regression models used in quantum state tomography (in particular, i…

In statistical inference problems, we wish to obtain lower bounds on the minimax risk, that is to bound the performance of any possible estimator. A standard technique to obtain risk lower bounds involves the use of Fano's inequality. In an information-theoretic setting, it is known that Fano's inequality typically doe…

Paper optimizes federated PCA for covariance estimation under privacy constraints.

We consider the problem of dictionary learning under the assumption that the observed signals can be represented as sparse linear combinations of the columns of a single large dictionary matrix. In particular, we analyze the minimax risk of the dictionary learning problem which governs the mean squared error (MSE) perf…

New algorithms find optimal policies without knowing MDP span.

Paper quantizes heavy-tailed data for near optimal estimation rates.

Several problems such as network intrusion, community detection, and disease outbreak can be described by observations attributed to nodes or edges of a graph. In these applications presence of intrusion, community or disease outbreak is characterized by novel observations on some unknown connected subgraph. These prob…

Rényi divergence is related to Rényi entropy much like Kullback-Leibler divergence is related to Shannon's entropy, and comes up in many settings. It was introduced by Rényi as a measure of information that satisfies almost the same axioms as Kullback-Leibler divergence, and depends on a parameter that is called its or…

New algorithm tackles heavy-tailed rewards in RL with instance-dependent regret bounds.

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…

This work optimizes signal estimation for sparse MRA with collision-free signals.

Study uniform rates for estimating Gaussian mixtures without separation assumption.

Study on predicting sequences with Gaussian constraints, linking to intrinsic volumes and metric complexity.

This paper deals with the trace regression model where $n$ entries or linear combinations of entries of an unknown $m_1\times m_2$ matrix $A_0$ corrupted by noise are observed. We propose a new nuclear norm penalized estimator of $A_0$ and establish a general sharp oracle inequality for this estimator for arbitrary val…

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

Ridge regression performs optimally in noisy environments with heavy-tailed distributions.

This paper is devoted to the bipartite ranking problem, a classical statistical learning task, in a high dimensional setting. We propose a scoring and ranking strategy based on the PAC-Bayesian approach. We consider nonlinear additive scoring functions, and we derive non-asymptotic risk bounds under a sparsity assumpti…

Improved GANs estimate convergence rate for density estimation.

Paper analyzes sparse aggregation in GLMs with Kullback-Leibler risk bounds.

We study the regret of optimal strategies for online convex optimization games. Using von Neumann's minimax theorem, we show that the optimal regret in this adversarial setting is closely related to the behavior of the empirical minimization algorithm in a stochastic process setting: it is equal to the maximum, over jo…

The paper analyzes prediction error in nonstationary settings using weighted risk minimization.

New method TLC improves transductive learning bounds.

Improved sampling algorithm with state-of-the-art complexity bounds.

PAC-Bayesian matrix completion with a spectral scaled Student prior offers efficient inference.

DS-GDA solves nonconvex-nonconcave problems without regularity conditions.