activity
20242026
collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

Optimal Learning Rate Scaling Depends on Data in Deep Scalar Linear Networks

Yedi Zhang, Peter E. Latham, Leena Chennuru Vankadara +1

In this short note we consider the gradient descent dynamics of deep scalar linear networks, , which enjoy exact time-course solutions for any integer d…

cs.LG2026

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning

Nicolas Anguita, Francesco Locatello, Andrew M. Saxe +4

Pretraining and fine-tuning are central stages in modern machine learning systems. In practice, feature learning plays an important role across both stages: deep neural networks le…

cs.LG2025

Algorithm Development in Neural Networks: Insights from the Streaming Parity Task

Loek van Rossem, Andrew M. Saxe

Even when massively overparameterized, deep neural networks show a remarkable ability to generalize. Research on this phenomenon has focused on generalization within distribution,…

cs.LG2025

Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU Networks

Devon Jarvis, Richard Klein, Benjamin Rosman +1

In spite of finite dimension ReLU neural networks being a consistent factor behind recent deep learning successes, a theory of feature learning in these models remains elusive. Cur…

cs.LG2024

When Representations Align: Universality in Representation Learning Dynamics

Loek van Rossem, Andrew M. Saxe

Deep neural networks come in many sizes and architectures. The choice of architecture, in conjunction with the dataset and learning algorithm, is commonly understood to affect the…