5 papers
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…
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…
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…
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…
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…