arXiv research

Boosting algorithm reduces error in noisy data.

Efficient algorithm for halfspaces with specific noise conditions.

Solves learning halfspaces with Massart noise for log-concave distributions.

Study shows SQ lower bounds for learning ReLUs with Massart noise.

Near-optimal SQ hardness shows learning halfspaces with Massart noise is hard.

Study on ReLU regression with Massart noise, achieving exact parameter recovery.

Efficient algorithm for online learning with Massart noise achieves near-optimal mistake bound.

New algorithm learns halfspaces with near-optimal sample complexity in noisy conditions.

Study learning halfspaces with Massart noise under Gaussian distribution, improving previous results.

Paper addresses classification under misspecification, providing simpler algorithms and resolving open questions.

We study the problem of {\em distribution-independent} PAC learning of halfspaces in the presence of Massart noise. Specifically, we are given a set of labeled examples $(\mathbf{x}, y)$ drawn from a distribution $\mathcal{D}$ on $\mathbb{R}^{d+1}$ such that the marginal distribution on the unlabeled points $\mathbf{x}…

The study sets limits on how well halfspaces can be learned when labels are corrupted.

New insights on robust learning under strong noise models.

Efficient algorithm for learning halfspaces in a new model with polynomial time complexity.

Improved SGD for robust linear and ReLU regression with adversarial corruptions.

New algorithm learns halfspaces with noise using Forster decomposition.

New algorithms learn from comparisons to classify data robustly to noise.

Study shows multi-distribution learning has slower rates than single-task learning.

Algorithm learns halfspaces in noisy data efficiently.

Near-Exponential Convergence Rates for kNN Classification

Strongly polynomial algorithm for approximate Forster transforms and halfspace learning.

Study intersections of curves on translation surfaces, focusing on regular polygons and their Teichmüller disks.

New method learns to generalize across different data domains efficiently.

This work analyzes label embedding for large multiclass classification problems.

Universal tester-learner for halfspaces over structured distributions.

We consider the classical problem of learning rates for classes with finite VC dimension. It is well known that fast learning rates up to $O\left(\frac{d}{n}\right)$ are achievable by the empirical risk minimization algorithm (ERM) if low noise or margin assumptions are satisfied. These usually require the optimal Baye…

This research analyzes the consistency of convex and nonconvex surrogate losses for adversarially robust classification.

Self-training algorithm improves classifier performance with labeled and unlabeled data.

Random Fourier features classification achieves fast learning rates with fewer features.

Estimates KVol on surfaces with geometric constraints.

Birg{é} and Massart proposed in 2001 the slope heuristics as a way to choose optimally from data an unknown multiplicative constant in front of a penalty. It is built upon the notion of minimal penalty, and it has been generalized since to some "minimal-penalty algorithms". This paper reviews the theoretical results ob…

Paper shows ERM's suboptimality due to bias, not variance.

Measures three types of noise in LLM evaluations.

The study investigates noise effects on parameter estimation for Ornstein-Uhlenbeck processes.

Noise in SGD affects overparameterized models, favoring sparse solutions.

L2R learns to denoise images without needing noise distribution knowledge.

Interpolating label noise makes models vulnerable to adversarial attacks.

Generative adversarial networks (GANs) are neural networks that learn data distributions through adversarial training. In intensive studies, recent GANs have shown promising results for reproducing training images. However, in spite of noise, they reproduce images with fidelity. As an alternative, we propose a novel fa…

We present a noise-injected version of the Expectation-Maximization (EM) algorithm: the Noisy Expectation Maximization (NEM) algorithm. The NEM algorithm uses noise to speed up the convergence of the EM algorithm. The NEM theorem shows that injected noise speeds up the average convergence of the EM algorithm to a local…

BeGIN benchmarks GNNs for instance-dependent label noise in graphs.

Enhanced consistency bounds derived for classification under a new noise condition.

Proposes a progressive label correction method for feature-dependent label noise.

New methods for handling time-varying label noise in time series classification.

NoiseRank reduces label noise without supervision, improving classification accuracy.

Paper tackles online control of linear systems with unbounded noise.

Study on noise models for noisy labels in NLP.

Using a Bayesian approach, we consider the problem of recovering sparse signals under additive sparse and dense noise. Typically, sparse noise models outliers, impulse bursts or data loss. To handle sparse noise, existing methods simultaneously estimate the sparse signal of interest and the sparse noise of no interest.…

TrustNet robustly learns noise patterns from trusted data to improve weakly-supervised classification.