collaborators

5 papers

cs.LG2026

Spectral Analysis of Molecular Features: When Richer Features Do Not Guarantee Better Generalization

Asma Jamali, Tin Sum Cheng, Rodrigo A. Vargas-Hernández

The spectral properties of feature embeddings offer critical insights into model generalization and representation quality. While deep learning models are widely used for molecular…

cs.LG2026

Optimizer choice matters for the emergence of Neural Collapse

Jim Zhao, Tin Sum Cheng, Wojciech Masarczyk +1

Neural Collapse (NC) refers to the emergence of highly symmetric geometric structures in the representations of deep neural networks during the terminal phase of training. Despite…

stat.ML2025

Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data

Anastasis Kratsios, Tin Sum Cheng, Daniel Roy

At its core, machine learning seeks to train models that reliably generalize beyond noisy observations; however, the theoretical vacuum in which state-of-the-art universal approxim…

stat.ML2025

Sharp Generalization Bounds for Foundation Models with Asymmetric Randomized Low-Rank Adapters

Anastasis Kratsios, Tin Sum Cheng, Aurelien Lucchi +1

Low-Rank Adaptation (LoRA) has emerged as a widely adopted parameter-efficient fine-tuning (PEFT) technique for foundation models. Recent work has highlighted an inherent asymmetry…

cs.LG2025

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization

Wojciech Masarczyk, Mateusz Ostaszewski, Tin Sum Cheng +3

The softmax function is a fundamental building block of deep neural networks, commonly used to define output distributions in classification tasks or attention weights in transform…