arXiv research

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

CMRM improves robustness in noisy label settings without requiring privileged knowledge.

Framework for private, noise-tolerant, and efficient learning algorithms.

Method estimates noise variance in Gaussian process regression.

We present a simple noise-robust margin-based active learning algorithm to find homogeneous (passing the origin) linear separators and analyze its error convergence when labels are corrupted by noise. We show that when the imposed noise satisfies the Tsybakov low noise condition (Mammen, Tsybakov, and others 1999; Tsyb…

This work introduces a noise-adaptive conformal inference method for better prediction sets in noisy data.

This work addresses various open questions in the theory of active learning for nonparametric classification. Our contributions are both statistical and algorithmic: -We establish new minimax-rates for active learning under common \textit{noise conditions}. These rates display interesting transitions -- due to the inte…

MARVEL curbs memorization of noisy labels in deep nets.

Interpolation hurts robust generalization even without noise.

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

Study efficient learning of halfspaces with constant noise tolerance.

GNIs induce a regulariser that penalizes high-frequency components in neural network activations.

Study shows a tradeoff between sample complexity and computational efficiency for learning halfspaces with random noise.

The paper analyzes the maximum margin algorithm's performance on noisy data.

Multiplicative noise models are often used instead of additive noise models in cases in which the noise variance depends on the state. Furthermore, when Poisson distributions with relatively small counts are approximated with normal distributions, multiplicative noise approximations are straightforward to implement. Th…

Robust GP model detects and corrects sparse outliers.

DAIS improves AIS for differentiable marginal likelihood estimation.

Improved k-NN active learning with local smoothness assumption.

Conservation laws improve diffusion model training by optimizing likelihood.

Paper tackles noise-robust domain adaptation in noisy environments.

Proposes MvTPMSVM to improve multiview learning with reduced computational complexity.

We present a new boosting algorithm, motivated by the large margins theory for boosting. We give experimental evidence that the new algorithm is significantly more robust against label noise than existing boosting algorithm.

MCD reformulates conditional density estimation into binary classification.

The paper improves alignment methods for deep neural networks using geometric and spectral analysis.

New algorithm learns halfspaces with adversarial noise efficiently.

Data augmentation (DA) is commonly used during model training, as it significantly improves test error and model robustness. DA artificially expands the training set by applying random noise, rotations, crops, or even adversarial perturbations to the input data. Although DA is widely used, its capacity to provably impr…

Study shows sample noise impacts active learning performance.

Deep Gaussian processes (DGPs) can model complex marginal densities as well as complex mappings. Non-Gaussian marginals are essential for modelling real-world data, and can be generated from the DGP by incorporating uncorrelated variables to the model. Previous work on DGP models has introduced noise additively and use…

Non-convex SGD learns halfspaces with adversarial label noise efficiently.

New estimator reduces kernel mean estimation error.

Enhances UPSA to reduce noise in financial data.

Algorithm learns dynamics from past observations.

Explaining the unreasonable effectiveness of deep learning has eluded researchers around the globe. Various authors have described multiple metrics to evaluate the capacity of deep architectures. In this paper, we allude to the radius margin bounds described for a support vector machine (SVM) with hinge loss, apply the…

Study evaluates margin parameter effects on knowledge embedding quality.

SGD-trained neural networks generalize well even with adversarial label noise.

Noise in RNNs promotes flatter minima and more stable dynamics.

Advances robustness of metric learning by adversarial margin in input space.

Paper achieves fast learning rates without margin assumptions in agnostic settings.

We consider the problem of training a model under the presence of label noise. Current approaches identify samples with potentially incorrect labels and reduce their influence on the learning process by either assigning lower weights to them or completely removing them from the training set. In the first case the model…

Jointly learns feature and sample relevancies for robust sparse recovery.

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…

Theory for soft-margin classifiers on object manifolds.

A new method trains and samples from energy-based models using diffusion recovery likelihood.

Paper proposes a new method for training diffusion models using Markov operators.

Proposes MGCE for improved classification performance.

There is a large body of work on convergence rates either in passive or active learning. Here we outline some of the results that have been obtained, more specifically in a nonparametric setting under assumptions about the smoothness and the margin noise. We also discuss the relative merits of these underlying assumpti…

The paper addresses online prediction in marginally stable systems with bounded perturbations.

The Collective Graphical Model (CGM) models a population of independent and identically distributed individuals when only collective statistics (i.e., counts of individuals) are observed. Exact inference in CGMs is intractable, and previous work has explored Markov Chain Monte Carlo (MCMC) and MAP approximations for le…