arXiv research

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

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

Method estimates noise variance in Gaussian process regression.

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

Robust GP model detects and corrects sparse outliers.

We introduce a simple framework for designing private boosting algorithms. We give natural conditions under which these algorithms are differentially private, efficient, and noise-tolerant PAC learners. To demonstrate our framework, we use it to construct noise-tolerant and private PAC learners for large-margin halfspa…

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…

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…

Conservation laws improve diffusion model training by optimizing likelihood.

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.

Proposes MvTPMSVM to improve multiview learning with reduced computational complexity.

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.

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…

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…

MCD reformulates conditional density estimation into binary classification.

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

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

DAIS improves AIS for differentiable marginal likelihood estimation.

Jointly learns feature and sample relevancies for robust sparse recovery.

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…

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

Noise in RNNs promotes flatter minima and more stable dynamics.

New algorithm learns halfspaces with adversarial noise efficiently.

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

Paper tackles noise-robust domain adaptation in noisy environments.

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…

Variable clustering is important for explanatory analysis. However, only few dedicated methods for variable clustering with the Gaussian graphical model have been proposed. Even more severe, small insignificant partial correlations due to noise can dramatically change the clustering result when evaluating for example w…

New method designs joint initial noises for diffusion models to improve diversity and alignment.

In the compagnion paper [Marginal density expansions for diffusions and stochastic volatility, part I] we discussed density expansions for multidimensional diffusions $(X^1,...,X^d)$, at fixed time $T$ and projected to their first $l$ coordinates, in the small noise regime. Global conditions were found which replace th…

Learning knowledge representation is an increasingly important technology that supports a variety of machine learning related applications. However, the choice of hyperparameters is seldom justified and usually relies on exhaustive search. Understanding the effect of hyperparameter combinations on embedding quality is …

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.

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

New method handles structural uncertainty in graphs better than existing models.

FLDD improves discrete diffusion models by learning a non-Markovian noising process.

Study shows sample noise impacts active learning performance.

Enhances deep learning robustness to noise without sacrificing clean data accuracy.

New method identifies SDE drift and diffusion from temporal data.

Meta framework generates noise to improve multi-attack robustness.

New estimator reduces kernel mean estimation error.

Noise affects the effectiveness of interpolating models, especially those with strong inductive biases.

RNE provides a flexible framework for diffusion models, enabling inference-time control and energy-based training.

Paper studies statistical properties of DP data synthesis algorithms based on Bayesian networks.