arXiv research

New algorithm resists contamination in high-dimensional regression with optimal performance.

Paper introduces RAS for robust MTL with contamination.

Improved robust regression with clean covariates achieves better rates than Huber's model.

Algorithm identifies Pareto set in bandits with contaminated feedback.

Optimal transport adapted for contaminated probabilities, showing equivalence under specific conditions.

This paper studies active learning in the context of robust statistics. Specifically, we propose a variant of the Best Arm Identification problem for \emph{contaminated bandits}, where each arm pull has probability $\varepsilon$ of generating a sample from an arbitrary contamination distribution instead of the true und…

Efficiently clusters data with weak assumptions, robust to contamination.

The paper develops adaptive confidence intervals for Efron's Gaussian two-groups model with unknown contamination.

Paper proposes CLAIR for efficient LLM fine-tuning across clients.

Study tackles contamination and heterogeneity in multi-task learning, improving robustness and personalization.

New algorithms achieve optimal robustness in stochastic convex optimization under contamination.

This work is motivated by the problem of image mis-registration in remote sensing and we are interested in determining the resulting loss in the accuracy of pattern classification. A statistical formulation is given where we propose to use data contamination to model and understand the phenomenon of image mis-registrat…

New robust estimator for high-dimensional data with outliers and leverage points.

Study sample complexity of robust binary hypothesis testing under different contamination models.

Language model benchmarks often misrepresent true understanding, revealing vulnerabilities in evaluation methods.

New robust estimator improves variable selection and coefficient estimation in linear regression with heavy-tailed errors and outliers.

Study improves scalability of cell-free massive MIMO networks by optimizing UE-AP association.

A contamination in a 3-manifold is an object interpolating between the contact structure and the lamination. Contaminations seem to provide a link between 3-dimensional contact geometry and the classical topology of 3-manifolds, as described in a separate paper. In this paper we deal with contaminations carried by bran…

A robust loss for anomaly mitigation and unsupervised contamination classification

Study minimax robustness in statistical estimation under Wasserstein contamination.

Study shows robust method for estimating density ratios even with heavy contamination.

Generative models can still learn from contaminated data, but with limitations.

Robust VB framework for large datasets with outliers.

Motivated by applications of bandit algorithms in education, we consider a stochastic multi-armed bandit problem with $\varepsilon$-contaminated rewards. We allow an adversary to give arbitrary unbounded contaminated rewards with full knowledge of the past and future. We impose the constraint that for each time $t$ the…

Trimming helps in conformal prediction when it separates anomaly scores.

New algorithms robust to adversarial data achieve optimal performance.

Bayesian method estimates contamination factor for unsupervised anomaly detection.

New test ensures quality of shared data in machine learning.

New method trims network data to resist adversarial contamination.

New algorithm reduces contamination in supervised learning.

This paper examines the role and efficiency of the non-convex loss functions for binary classification problems. In particular, we investigate how to design a simple and effective boosting algorithm that is robust to the outliers in the data. The analysis of the role of a particular non-convex loss for prediction accur…

Paper shows MoM is optimal under adversarial contamination for certain distributions.

The paper analyzes how conformal prediction works with contaminated reference data.

Robust score matching improves parameter estimation in contaminated data.

A low rank matrix X has been contaminated by uniformly distributed noise, missing values, outliers and corrupt entries. Reconstruction of X from the singular values and singular vectors of the contaminated matrix Y is a key problem in machine learning, computer vision and data science. In this paper we show that common…

New algorithm resists corruption in linear contextual bandits.

Efficiently estimates mean in contaminated Gaussian data with near-optimal sample complexity.

A theory of cellwise contamination for compositional data using log-ratios.

We address challenges in estimating parameters from adaptively collected data.

Many machine learning problems can be characterized by mutual contamination models. In these problems, one observes several random samples from different convex combinations of a set of unknown base distributions. It is of interest to decontaminate mutual contamination models, i.e., to recover the base distributions ei…

A new method optimizes anomaly scoring from score distribution to improve AD performance.

Paper uses DNN-based MoM-GAN to estimate contaminated data distributions.

Theoretical study shows AI models can recover from contaminated training data.

We propose in this paper a method for studying contact structures in 3-manifolds by means of branched surfaces. We explain what it means for a contact structure to be carried by a branched surface embedded in a 3-manifold. To make the transition from contact structures to branched surfaces, we first define auxiliary ob…

Study robustness of split conformal prediction in data contamination setting.

Robustly aligns datasets with partial GW distance to handle contamination.

Neural networks compress and sample WDN contamination dynamics efficiently.

The paper analyzes how overparameterized models can generalize well in multiclass classification.