activity
20182021
collaborators

8 papers

cond-mat.dis-nn2021

Analytical Study of Momentum-Based Acceleration Methods in Paradigmatic High-Dimensional Non-Convex Problems

Stefano Sarao Mannelli, Pierfrancesco Urbani

The optimization step in many machine learning problems rarely relies on vanilla gradient descent but it is common practice to use momentum-based accelerated methods. Despite these…

cs.LG2020

Post-Workshop Report on Science meets Engineering in Deep Learning, NeurIPS 2019, Vancouver

Levent Sagun, Caglar Gulcehre, Adriana Romero +2

Science meets Engineering in Deep Learning took place in Vancouver as part of the Workshop section of NeurIPS 2019. As organizers of the workshop, we created the following report i…

cs.LG2020

Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval

Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota +3

Despite the widespread use of gradient-based algorithms for optimizing high-dimensional non-convex functions, understanding their ability of finding good minima instead of being tr…

cs.LG2020

Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions

Stefano Sarao Mannelli, Eric Vanden-Eijnden, Lenka Zdeborová

We study the dynamics of optimization and the generalization properties of one-hidden layer neural networks with quadratic activation function in the over-parametrized regime where…

cs.LG2020

Thresholds of descending algorithms in inference problems

Stefano Sarao Mannelli, Lenka Zdeborova

We review recent works on analyzing the dynamics of gradient-based algorithms in a prototypical statistical inference problem. Using methods and insights from the physics of glassy…

cs.LG2019

Who is Afraid of Big Bad Minima? Analysis of Gradient-Flow in a Spiked Matrix-Tensor Model

Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota +2

Gradient-based algorithms are effective for many machine learning tasks, but despite ample recent effort and some progress, it often remains unclear why they work in practice in op…