1.3k citations · 1.6k across the 25 of their papers we have counts for
26 papers
Convex Optimization Is Free When Accuracy Is Expensive
Arthur Paing, Arthur Jacot
This paper studies convex optimization when the gradient cannot be evaluated exactly, but only approximated by a hierarchy of algorithms whose compute grows like in the ac…
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…
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…
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-…
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…
Shallow diffusion networks provably learn hidden low-dimensional structure
Nicholas M. Boffi, Arthur Jacot, Stephen Tu +1
Diffusion-based generative models provide a powerful framework for learning to sample from a complex target distribution. The remarkable empirical success of these models applied t…