arXiv research

Proposes engression for extrapolation in distributional regression.

Deep models forecast epidemics with uncertainty quantification.

In the first part of the paper we associate a pre-additive category $\mathcal{C}(Σ)$ to a closed oriented surface $Σ$, called the {\em contact category} and constructed from contact structures on $Σ\times[0,1]$. There are also $\mathcal{C}(Σ,F)$, where $Σ$ is a compact oriented surface with boundary and $F\subset \part…

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.

Efficient algorithm for halfspaces with specific noise conditions.

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.

Noise enhancement improves generalization in training.

HeMPPCAT improves PCA for data with varying noise.

The paper examines various RL algorithms to address overestimation and noise issues.

Geometry-aware noise improves model generalization on complex manifolds.

New insights into noise distribution for self-supervised learning.

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

Paper improves SLCB regret bound for bounded noise.

Proposes DISCO, the first CVI for density-based clustering with noise.

We address noisy Euclidean distances in high dimensions, estimating noise levels and correcting distances.

DA-GNN improves robustness of GNNs by modeling noise dependencies.

The study analyzes how label noise affects deep learning feature learning.

PiNGDA learns beneficial noise for graph augmentation stability.

We introduce a new approach for designing computationally efficient learning algorithms that are tolerant to noise, and demonstrate its effectiveness by designing algorithms with improved noise tolerance guarantees for learning linear separators. We consider both the malicious noise model and the adversarial label nois…

Paper presents robust boosting methods for label noise.

As all physical adaptive quantum-enhanced metrology schemes operate under noisy conditions with only partially understood noise characteristics, so a practical control policy must be robust even for unknown noise. We aim to devise a test to evaluate the robustness of AQEM policies and assess the resource used by the po…

Deep-neural-network (DNN) based noise suppression systems yield significant improvements over conventional approaches such as spectral subtraction and non-negative matrix factorization, but do not generalize well to noise conditions they were not trained for. In comparison to DNNs, humans show remarkable noise suppress…

Additive asynchronous and cyclostationary impulsive noise limits communication performance in OFDM powerline communication (PLC) systems. Conventional OFDM receivers assume additive white Gaussian noise and hence experience degradation in communication performance in impulsive noise. Alternate designs assume a parametr…

The gradient noise of SGD is considered to play a central role in the observed strong generalization abilities of deep learning. While past studies confirm that the magnitude and the covariance structure of gradient noise are critical for regularization, it remains unclear whether or not the class of noise distribution…

Generalized R2R handles non-Gaussian noise for deep network training.

Paper proposes a self-supervised method to denoise autoregressive signals with heavy-tailed noise.

Paper tackles instance-dependent label noise by approximating it with part-dependent noise.

Because large, human-annotated datasets suffer from labeling errors, it is crucial to be able to train deep neural networks in the presence of label noise. While training image classification models with label noise have received much attention, training text classification models have not. In this paper, we propose an…

Inserting label noise can improve model accuracy and fairness.

Noise makes learning linear thresholds hard, but algorithms can still learn near-optimal thresholds.

Develops efficient inference for noise heterogeneity in machine learning models.

Anti-correlated noise improves machine learning model generalization.

In learning with noisy labels, for every instance, its label can randomly walk to other classes following a transition distribution which is named a noise model. Well-studied noise models are all instance-independent, namely, the transition depends only on the original label but not the instance itself, and thus they a…

New insights on robust learning under strong noise models.