arXiv Machine Learning
Jun 5
Towards Label-Noise Resistant Learning via Optimal Brain Damage Masking
arXiv:2508. 09697v3 Announce Type: replace Abstract: Noisy labels are inevitable in real-world scenarios.
Label-Noise Resistant Learning via Optimal Brain Damage Masking
arXiv:2508. 09697v4 Announce Type: replace Abstract: Noisy labels are inevitable in real-world multimedia applications.
Related stories
arXiv Machine Learning
Jul 17
Interleaved Noise Injection Improves Clean, Corrupted, and OOD Performance
arXiv:2607. 14466v1 Announce Type: new Abstract: Noise injection is a well-known technique in stochastic optimization.
arXiv Machine Learning
Jul 21
Orthogonal Gradient Constraints Shape Noisy-Label Memorization Dynamics
arXiv:2607. 16231v1 Announce Type: new Abstract: Modern neural networks can fit corrupted training labels, making noisy-label learning a useful setting for studying memorization-driven overfitting.
arXiv AI
Jun 16
ALCL: An Adaptive Log-Correntropy Loss for Robust Learning under Non-Gaussian Noise
arXiv:2606. 16050v1 Announce Type: cross Abstract: Robust deep learning under heavy-tailed and impulsive noise remains challenging because conventional losses such as mean squared error (MSE) exhibit unbounded sensitivity to outliers.
arXiv Machine Learning
Jul 21
Dropout and Random Gradient Masking Are Asymptotically Equivalent in Large ResNets
arXiv:2607. 16761v1 Announce Type: cross Abstract: Dropout and Random Gradient Masking (RaM) are two training techniques used to improve performance in deep learning.
arXiv AI
Jun 30
FedLAS: Feature-Modulated Bidirectional Label Smoothing for Neural Network Calibration
arXiv:2606. 28654v1 Announce Type: cross Abstract: Deep Neural Network (DNN) classifiers suffer from poor calibration when their softmax outputs (predictive confidence) deviate from the empirical likelihoods.
arXiv AI
Sep 1
Forget or Fine-tune? A Comparative Study of Machine Unlearning Strategies for Noisy Label Correction
The paper compares five machine unlearning (MU) methods—NegGrad, Fine‑Tuning (FT), Random Labeling (RL), SalUn, and MUNBa—on noisy‑label correction across CIFAR‑10, CIFAR‑100, and Food‑101N. Results show that the best MU strategy depends on the noise type: FT works well for most closed‑set noise, RL and SalUn are robust and nearly match retraining accuracy under instance‑dependent noise, while MUNBa excels only under extreme symmetric noise. In open‑set noise, retraining on the cleaned data actually hurts performance, indicating that approximating retraining is not suitable in that regime, yet all MU methods still achieve near‑retraining accuracy on Food‑101N with much lower runtime.
arXiv Machine Learning
Jun 24
XConv: Low-memory stochastic backpropagation for convolutional layers
arXiv:2106. 06998v5 Announce Type: replace Abstract: Training convolutional neural networks at scale demands substantial memory, largely because intermediate activations must be stored for backpropagation.
arXiv Machine Learning
Jun 8
An Adaptive Data cleaning Framework for Noisy Label Detection
arXiv:2606. 07086v1 Announce Type: cross Abstract: Deep neural networks (DNNs) excel in computer vision tasks given large annotated datasets.
arXiv Machine Learning
Jul 21
Robust Losses from Univariate Base Functions for Noisy-Label Learning
arXiv:2607. 16768v1 Announce Type: new Abstract: Learning with noisy labels is a fundamental problem in training reliable deep neural networks.
arXiv Machine Learning
Jun 11
Simplicity Suffices for Parameter Noise Injection in Stochastic Gradient Descent
arXiv:2606. 12054v1 Announce Type: new Abstract: Injecting noise into the optimization process is a well-established technique for improving the training and generalization of deep neural networks.
arXiv Machine Learning
1d ago
Learning the identity: a case study of how SGD selects among functional decompositions
The paper investigates how stochastic gradient descent (SGD) selects specific functional decompositions when training a deep linear residual network to learn the identity function. Although many weight configurations minimize the population loss, SGD consistently prefers particular solutions, especially under anisotropic label noise or different parametrizations. The authors explain this bias using an entropic loss term that penalizes the expected squared norm of the minibatch gradient, analytically characterizing its minimizers and showing that trained networks align with these predictions.