arXiv research

Study on SA with heavy-tailed and LRD noise, establishing finite-time bounds.

Paper presents robust boosting methods for label noise.

Paper proposes a self-supervised method to denoise autoregressive signals with heavy-tailed noise.

Paper analyzes finite-time performance of SA in RL with Markovian noise.

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

Simultaneous orthogonal matching pursuit (SOMP) and block OMP (BOMP) are two widely used techniques for sparse support recovery in multiple measurement vector (MMV) and block sparse (BS) models respectively. For optimal performance, both SOMP and BOMP require \textit{a priori} knowledge of signal sparsity or noise vari…

New method bounds stochastic subgradient methods with heavy-tailed noise.

Study efficient power iteration for tensor models, proving convergence under specific conditions.

The paper studies how noise synchronizes tokens in deep transformer models.

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

In recent years, correntropy and its applications in machine learning have been drawing continuous attention owing to its merits in dealing with non-Gaussian noise and outliers. However, theoretical understanding of correntropy, especially in the statistical learning context, is still limited. In this study, within the…

This work obtains novel finite sample guarantees for Principal Component Analysis (PCA). These hold even when the corrupting noise is non-isotropic, and a part (or all of it) is data-dependent. Because of the latter, in general, the noise and the true data are correlated. The results in this work are a significant impr…

Developed LQ MFG theory with common noise, proving existence and uniqueness.

Paper tackles online control of linear systems with unbounded noise.

Unified view on learning unnormalized distributions using NCE.

Classical scaling is shown to be optimal under various noisy conditions.

A new method, Residual-Permuted Sums, improves confidence region construction for linear regression models.

We propose a learning-based approach for estimating the spectrum of a multisinusoidal signal from a finite number of samples. A neural-network is trained to approximate the spectra of such signals on simulated data. The proposed methodology is very flexible: adapting to different signal and noise models only requires m…

New bounds for SA with arbitrary norm contractions and Markovian noise.

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

We study Principal Component Analysis (PCA) in a setting where a part of the corrupting noise is data-dependent and, as a result, the noise and the true data are correlated. Under a bounded-ness assumption on the true data and the noise, and a simple assumption on data-noise correlation, we obtain a nearly optimal samp…

We investigate the problem of classification in the presence of unknown class-conditional label noise in which the labels observed by the learner have been corrupted with some unknown class dependent probability. In order to obtain finite sample rates, previous approaches to classification with unknown class-conditiona…

Optimal ridge regularization computed iteratively from generative parameters.

Inferring the causal structure of a set of random variables from a finite sample of the joint distribution is an important problem in science. Recently, methods using additive noise models have been suggested to approach the case of continuous variables. In many situations, however, the variables of interest are discre…

Paper analyzes convergence of decentralized algorithms with noise and bias.

Linear regression models contaminated by Gaussian noise (inlier) and possibly unbounded sparse outliers are common in many signal processing applications. Sparse recovery inspired robust regression (SRIRR) techniques are shown to deliver high quality estimation performance in such regression models. Unfortunately, most…

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

Robust $Q$-learning for mean-field control under Wasserstein uncertainty

Identifying meaningful signal buried in noise is a problem of interest arising in diverse scenarios of data-driven modeling. We present here a theoretical framework for exploiting intrinsic geometry in data that resists noise corruption, and might be identifiable under severe obfuscation. Our approach is based on uncov…

New method uses random features and Tikhonov regularization for operator learning from noisy data.

I introduce and analyse an anytime version of the Optimally Confident UCB (OCUCB) algorithm designed for minimising the cumulative regret in finite-armed stochastic bandits with subgaussian noise. The new algorithm is simple, intuitive (in hindsight) and comes with the strongest finite-time regret guarantees for a hori…

The paper develops a method to create non-asymptotic confidence ellipsoids for linear regression without strong noise distribution assumptions.

New method bounds hardware noise without assumptions.

We develop a general method for estimating a finite mixture of non-normalized models. Here, a non-normalized model is defined to be a parametric distribution with an intractable normalization constant. Existing methods for estimating non-normalized models without computing the normalization constant are not applicable …

Detects model misspecifications in causal models using observational data.

Paper introduces robust kernel ridge regression using Cauchy loss for handling various noise types.

New discrete-time model shows insider trading dynamics.

Study on signal recovery from low-rank matrix with sparse noise.

Study on estimating rank-one tensors in noisy data with heavy tails.

A method for noise reduction in functional time series using FPCA.

We consider classification in the presence of class-dependent asymmetric label noise with unknown noise probabilities. In this setting, identifiability conditions are known, but additional assumptions were shown to be required for finite sample rates, and so far only the parametric rate has been obtained. Assuming thes…

Orthogonal matching pursuit (OMP) is a widely used algorithm for recovering sparse high dimensional vectors in linear regression models. The optimal performance of OMP requires \textit{a priori} knowledge of either the sparsity of regression vector or noise statistics. Both these statistics are rarely known \textit{a p…

Study non-parametric frequency-domain system identification from finite samples.

Is AdamW effective under heavy-tailed noise?

We consider the dynamic linear regression problem, where the predictor vector may vary with time. This problem can be modeled as a linear dynamical system, with non-constant observation operator, where the parameters that need to be learned are the variance of both the process noise and the observation noise. While var…

Study on deep learning for speckle noise reduction in imaging modalities.

We propose a novel receiver for orthogonal frequency division multiplexing (OFDM) transmissions in impulsive noise environments. Impulsive noise arises in many modern wireless and wireline communication systems, such as Wi-Fi and powerline communications, due to uncoordinated interference that is much stronger than the…

Develops statistical confidence sets for multidimensional scaling.