collaborators

14 papers

q-bio.NC2026

Dynamics of learning to integrate in linear recurrent neural networks

Blake Bordelon, Jordan Cotler, Cengiz Pehlevan +1

Learning recurrent connectivity that supports memory over long intrinsic timescales is a basic problem in the theory of dynamical computation. While continuous attractor and integr…

cond-mat.dis-nn2026

Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer

Clarissa Lauditi, Cengiz Pehlevan, Blake Bordelon

We study the evolution of hidden-weight spectra in wide neural networks trained by (stochastic) gradient descent. We develop a two-level dynamical mean-field theory (DMFT) that joi…

cs.LG2026

Hyperparameter Transfer with Mixture-of-Expert Layers

Tianze Jiang, Blake Bordelon, Cengiz Pehlevan +1

Mixture-of-Experts (MoE) layers have emerged as an important tool in scaling up modern neural networks by decoupling total trainable parameters from activated parameters in the for…

cond-mat.dis-nn2026

Theory of Optimal Learning Rate Schedules and Scaling Laws for a Random Feature Model

Blake Bordelon, Francesco Mori

Setting the learning rate (LR) for a deep learning model is a critical part of successful training. Choosing LRs is often done empirically with trial and error. In this work, we ex…

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…

cs.LG2026

Transfer Learning in Infinite Width Feature Learning Networks

Clarissa Lauditi, Blake Bordelon, Cengiz Pehlevan

We develop a theory of transfer learning in infinitely wide neural networks under gradient flow that quantifies when pretraining on a source task improves generalization on a targe…