arXiv research

Study robust estimation under varying corruption probabilities in data.

Estimates GLMs robustly against label corruptions.

Efficiently estimates rotations with corrupted data.

We study the problem of robust mean estimation and introduce a novel Hamming distance-based measure of distribution shift for coordinate-level corruptions. We show that this measure yields adversary models that capture more realistic corruptions than those used in prior works, and present an information-theoretic analy…

New method makes robust estimators work without knowing corruption levels.

New method tackles adversarial sign-corrupted isotonic regression, estimating monotonic signals under heavy dependence.

Robustly estimates mean with quantized data and corruption.

Binary classification improves with a small fraction of corrupted labels.

New estimator reduces kernel mean estimation error.

Novel method solves group synchronization with robust corruption tolerance.

This study tackles adversarial corruption in model-based reinforcement learning.

Reinforcement Learning (RL) agents require the specification of a reward signal for learning behaviours. However, introduction of corrupt or stochastic rewards can yield high variance in learning. Such corruption may be a direct result of goal misspecification, randomness in the reward signal, or correlation of the rew…

New algorithm for robust density estimation in corrupted data.

Subsampling methods have been recently proposed to speed up least squares estimation in large scale settings. However, these algorithms are typically not robust to outliers or corruptions in the observed covariates. The concept of influence that was developed for regression diagnostics can be used to detect such corrup…

Study on measuring vulnerability of neural network parameters via corruption.

We study the problem of robust linear regression with response variable corruptions. We consider the oblivious adversary model, where the adversary corrupts a fraction of the responses in complete ignorance of the data. We provide a nearly linear time estimator which consistently estimates the true regression vector, e…

New spectral algorithm estimates random graph parameters robustly against corrupted nodes.

We analyze the performance of the Tukey median estimator under total variation (TV) distance corruptions. Previous results show that under Huber's additive corruption model, the breakdown point is 1/3 for high-dimensional halfspace-symmetric distributions. We show that under TV corruptions, the breakdown point reduces …

This work presents a new robust PCA method for foreground-background separation on freely moving camera video with possible dense and sparse corruptions. Our proposed method registers the frames of the corrupted video and then encodes the varying perspective arising from camera motion as missing data in a global model.…

Proposes a robust IV estimator using optimal transport for corrupted or adversarial data.

Efficiently learns distributions corrupted by both global and local adversarial modifications.

A diffusion model estimates data manifold dimension by tracking likelihood increases.

Robust Kalman filter for corrupted measurements.

New algorithm robustly estimates sparse models in high dimensions with corrupted data.

Method estimates noise transition matrix from noisy labels without relying on unreliable class-posterior estimation.

New algorithm optimizes robust estimation under mixed local and global corruptions.

New algorithm robustly learns from corrupted demonstrations, even with constant fraction of noise.

Study linear regression with missing or corrupted data, showing error bounds.

We study the problem of robust time series analysis under the standard auto-regressive (AR) time series model in the presence of arbitrary outliers. We devise an efficient hard thresholding based algorithm which can obtain a consistent estimate of the optimal AR model despite a large fraction of the time series points …

Robust CG methods avoid data corruption and solve structured statistical estimation problems.

ScaledGD algorithm estimates low-rank tensors efficiently from corrupted data.

We propose a general framework for solving the group synchronization problem, where we focus on the setting of adversarial or uniform corruption and sufficiently small noise. Specifically, we apply a novel message passing procedure that uses cycle consistency information in order to estimate the corruption levels of gr…

Robust Lasso-Zero handles missing covariates and sparse corruptions.

Robustly estimates mean in incomplete data with corrupted examples.

Model predicts counterfactuals under domain shift and inaccessible variables.

In today's era of big data, robust least-squares regression becomes a more challenging problem when considering the adversarial corruption along with explosive growth of datasets. Traditional robust methods can handle the noise but suffer from several challenges when applied in huge dataset including 1) computational i…

Study robust distribution estimation with Wasserstein distance, achieving optimal risk.

Solving inverse problems continues to be a central challenge in computer vision. Existing techniques either explicitly construct an inverse mapping using prior knowledge about the corruption, or learn the inverse directly using a large collection of examples. However, in practice, the nature of corruption may be unknow…

Improved model robustness against corruptions using online adaptation.

New methods tackle robust reinforcement learning in sparse, corrupted data.

A new algorithm reduces regret in bandit problems with adversarial corruptions.

New algorithm estimates eigenspace with faulty nodes, matching performance of existing methods.

New algorithm reduces regret in RL with adversarial corruption.

We consider a general statistical learning problem where an unknown fraction of the training data is corrupted. We develop a robust learning method that only requires specifying an upper bound on the corrupted data fraction. The method minimizes a risk function defined by a non-parametric distribution with unknown prob…

Study examines mean estimation in high dimensions with small data.

We study high-dimensional sparse estimation tasks in a robust setting where a constant fraction of the dataset is adversarially corrupted. Specifically, we focus on the fundamental problems of robust sparse mean estimation and robust sparse PCA. We give the first practically viable robust estimators for these problems.…

Develops a robust GMM estimator for outlier-tolerant inference.

This paper examines a general class of noisy matrix completion tasks where the goal is to estimate a matrix from observations obtained at a subset of its entries, each of which is subject to random noise or corruption. Our specific focus is on settings where the matrix to be estimated is well-approximated by a product …