activity
20242026
collaborators

8 papers

cs.LG2026

Self-Supervised Learning by Curvature Alignment

Benyamin Ghojogh, M. Hadi Sepanj, Paul Fieguth

Self-supervised learning (SSL) has recently advanced through non-contrastive methods that couple an invariance term with variance, covariance, or redundancy-reduction penalties. Wh…

stat.ML2026

Kernel VICReg for Self-Supervised Learning in Reproducing Kernel Hilbert Space

M. Hadi Sepanj, Benyamin Ghojogh, Saed Moradi +1

Self-supervised learning (SSL) has emerged as a powerful paradigm for representation learning by optimizing geometric objectives, such as invariance to augmentations, variance pres…

cs.LG2025

Pre-train to Gain: Robust Learning Without Clean Labels

David Szczecina, Nicholas Pellegrino, Paul Fieguth

Training deep networks with noisy labels leads to poor generalization and degraded accuracy due to overfitting to label noise. Existing approaches for learning with noisy labels of…

cs.LG2025

Effects of Initialization Biases on Deep Neural Network Training Dynamics

Nicholas Pellegrino, David Szczecina, Paul W. Fieguth

Untrained large neural networks, just after random initialization, tend to favour a small subset of classes, assigning high predicted probabilities to these few classes and approxi…

cs.LG2025

Hard Samples, Bad Labels: Robust Loss Functions That Know When to Back Off

Nicholas Pellegrino, David Szczecina, Paul Fieguth

Incorrectly labelled training data are frustratingly ubiquitous in both benchmark and specially curated datasets. Such mislabelling clearly adversely affects the performance and ge…

cs.LG2025

Self-Supervised Learning Using Nonlinear Dependence

M. Hadi Sepanj, Benyamin Ghojogh, Paul Fieguth

Self-supervised learning has gained significant attention in contemporary applications, particularly due to the scarcity of labeled data. While existing SSL methodologies primarily…