activity
20242026
collaborators
Showing stat.MLShow all

6 papers · 1 filter

stat.ML2026

There Will Be a Scientific Theory of Deep Learning

Jamie Simon, Daniel Kunin, Alexander Atanasov +11

In this paper, we make the case that a scientific theory of deep learning is emerging. By this we mean a theory which characterizes important properties and statistics of the train…

stat.ML2025

Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and Time

Blake Bordelon, Mary I. Letey, Cengiz Pehlevan

We study in-context learning (ICL) of linear regression in a deep linear self-attention model, characterizing how performance depends on various computational and statistical resou…

stat.ML2025

How Feature Learning Can Improve Neural Scaling Laws

Blake Bordelon, Alexander Atanasov, Cengiz Pehlevan

We develop a solvable model of neural scaling laws beyond the kernel limit. Theoretical analysis of this model shows how performance scales with model size, training time, and the…

stat.ML2024

Infinite Limits of Multi-head Transformer Dynamics

Blake Bordelon, Hamza Tahir Chaudhry, Cengiz Pehlevan

In this work, we analyze various scaling limits of the training dynamics of transformer models in the feature learning regime. We identify the set of parameterizations that admit w…

stat.ML2024

A Dynamical Model of Neural Scaling Laws

Blake Bordelon, Alexander Atanasov, Cengiz Pehlevan

On a variety of tasks, the performance of neural networks predictably improves with training time, dataset size and model size across many orders of magnitude. This phenomenon is k…

stat.ML2024

Grokking as the Transition from Lazy to Rich Training Dynamics

Tanishq Kumar, Blake Bordelon, Samuel J. Gershman +1

We propose that the grokking phenomenon, where the train loss of a neural network decreases much earlier than its test loss, can arise due to a neural network transitioning from la…