arXiv research

Diffusion models tackle noisy inverse problems with posterior sampling.

A fast method approximates likelihood scores for noisy linear inverse problems.

Deep neural networks solve noisy, complex problems accurately.

Self-supervised methods learn from noisy data alone, useful for imaging problems.

Leveraging weak or noisy supervision for building effective machine learning models has long been an important research problem. Its importance has further increased recently due to the growing need for large-scale datasets to train deep learning models. Weak or noisy supervision could originate from multiple sources i…

Paper presents efficient algorithms for reconstructing noisy pooled data.

New algorithm finds k-centers from noisy distance estimates.

Efficiently clusters noisy data with minimal queries.

Deep neural networks (DNNs) trained on large-scale datasets have exhibited significant performance in image classification. Many large-scale datasets are collected from websites, however they tend to contain inaccurate labels that are termed as noisy labels. Training on such noisy labeled datasets causes performance de…

NES improves robust optimization with noisy inputs.

Simplifies solving noisy SDPs for low rank matrix recovery problems.

JoCoR improves deep learning with noisy labels by reducing network diversity.

Paper improves $\ell^{0}$-SSC for noisy data by proving SDP and proposing Noisy-DR-$\ell^{0}$-SSC.

We consider the problem of clustering noisy high-dimensional data points into a union of low-dimensional subspaces and a set of outliers. The number of subspaces, their dimensions, and their orientations are unknown. A probabilistic performance analysis of the thresholding-based subspace clustering (TSC) algorithm intr…

Bayes classifier cannot be learned from noisy labels without knowing noise distribution.

CNT leverages noisy targets to guide model learning.

New algorithm optimizes matrix reordering for noisy disordered matrices.

Study efficient graph optimization with noisy data.

We present a principled framework to address resource allocation for realizing boosting algorithms on substrates with communication or computation noise. Boosting classifiers (e.g., AdaBoost) make a final decision via a weighted vote from the outputs of many base classifiers (weak classifiers). Suppose that the base cl…

Thompson Sampling tackles noisy context in stochastic bandits.

Bayesian PINNs solve noisy PDE problems with physics constraints.

Most existing image denoising approaches assumed the noise to be homogeneous white Gaussian distributed with known intensity. However, in real noisy images, the noise models are usually unknown beforehand and can be much more complex. This paper addresses this problem and proposes a novel blind image denoising algorith…

The paper tackles learning true rankings from noisy, incomplete data.

Subspace clustering is the problem of clustering data points into a union of low-dimensional linear/affine subspaces. It is the mathematical abstraction of many important problems in computer vision, image processing and machine learning. A line of recent work (4, 19, 24, 20) provided strong theoretical guarantee for s…

Simplifies noisy convex optimization with a new algorithm.

We investigate the problem of estimating a given real symmetric signal matrix $\textbf{C}$ from a noisy observation matrix $\textbf{M}$ in the limit of large dimension. We consider the case where the noisy measurement $\textbf{M}$ comes either from an arbitrary additive or multiplicative rotational invariant perturbati…

CrossFilter tackles noisy labels in audio tagging.

New algorithms for decision trees with noisy outcomes improve learning efficiency.

INN method refines clean labeled data from noisy labels.

The ability of learning from noisy labels is very useful in many visual recognition tasks, as a vast amount of data with noisy labels are relatively easy to obtain. Traditionally, the label noises have been treated as statistical outliers, and approaches such as importance re-weighting and bootstrap have been proposed …

Paper tackles noisy bandit feedback for multiclass classification.

We address the problem of estimating the parameters of a time-homogeneous Markov chain given only noisy, aggregate data. This arises when a population of individuals behave independently according to a Markov chain, but individual sample paths cannot be observed due to limitations of the observation process or the need…

Paper analyzes noisy low-rank matrix optimization, improving RIP bounds and convergence rates.

A framework for multi-agent communication over noisy channels in reinforcement learning.

Paper shows how noisy data can improve robust decision-making.

We study the problem of black-box optimization of a noisy function in the presence of low-cost approximations or fidelities, which is motivated by problems like hyper-parameter tuning. In hyper-parameter tuning evaluating the black-box function at a point involves training a learning algorithm on a large data-set at a …

New methods ensure fairness in noisy protected groups.

New algorithm mitigates bias in subset selection with noisy protected attributes.

New method improves convergence and reduces variance in noisy optimization problems.

Paper tackles robust imitation learning from noisy demonstrations.

A new algorithm estimates aggregate marginals from noisy data in an online manner.

Given a matrix M of low-rank, we consider the problem of reconstructing it from noisy observations of a small, random subset of its entries. The problem arises in a variety of applications, from collaborative filtering (the `Netflix problem') to structure-from-motion and positioning. We study a low complexity algorithm…

DiEM trains diffusion models from noisy data using EM.

Survey on deep learning robust training methods for noisy labels.

INGB improves oversampling for noisy imbalanced datasets.

Saliency Map, the gradient of the score function with respect to the input, is the most basic technique for interpreting deep neural network decisions. However, saliency maps are often visually noisy. Although several hypotheses were proposed to account for this phenomenon, there are few works that provide rigorous ana…

Learn ODEs from noisy data using RKHS and optimization.

Paper tackles noisy labels for non-decomposable performance measures.