activity
20242026
collaborators

10 papers

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

Saddle-To-Saddle Dynamics in Deep ReLU Networks: Low-Rank Bias in the First Saddle Escape

Ioannis Bantzis, James B. Simon, Arthur Jacot

When a deep ReLU network is initialized with small weights, gradient descent (GD) is at first dominated by the saddle at the origin in parameter space. We study the so-called escap…

cs.LG2026

Polynomial Speedup in Diffusion Models with the Multilevel Euler-Maruyama Method

Arthur Jacot

We introduce the Multilevel Euler-Maruyama (ML-EM) method compute solutions of SDEs and ODEs using a range of approximators to the drift with increasing accurac…

stat.ML2026

Deep Learning as a Convex Paradigm of Computation: Minimizing Circuit Size with ResNets

Arthur Jacot

This paper argues that DNNs implement a computational Occam's razor -- finding the `simplest' algorithm that fits the data -- and that this could explain their incredible and wide-…

stat.ML2026

Hamiltonian Mechanics of Feature Learning: Bottleneck Structure in Leaky ResNets

Arthur Jacot, Alexandre Kaiser

We study Leaky ResNets, which interpolate between ResNets and Fully-Connected nets depending on an 'effective depth' hyper-parameter . In the infinite depth limit, we st…

stat.ML2025

How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning

Arthur Jacot, Seok Hoan Choi, Yuxiao Wen

We show that deep neural networks (DNNs) can efficiently learn any composition of functions with bounded -norm, which allows DNNs to break the curse of dimensionality in way…