no code implementations • ICML 2020 • Stéphane d'Ascoli, Maria Refinetti, Giulio Biroli, Florent Krzakala
We demonstrate that the latter two contributions are the crux of the double descent: they lead to the overfitting peak at the interpolation threshold and to the decay of the test error upon overparametrization.
no code implementations • 10 Feb 2023 • Ravi Srinivasan, Francesca Mignacco, Martino Sorbaro, Maria Refinetti, Avi Cooper, Gabriel Kreiman, Giorgia Dellaferrera
"Forward-only" algorithms, which train neural networks while avoiding a backward pass, have recently gained attention as a way of solving the biologically unrealistic aspects of backpropagation.
1 code implementation • 21 Nov 2022 • Maria Refinetti, Alessandro Ingrosso, Sebastian Goldt
The ability of deep neural networks to generalise well even when they interpolate their training data has been explained using various "simplicity biases".
no code implementations • 9 Feb 2022 • Stéphane d'Ascoli, Maria Refinetti, Giulio Biroli
In this case, it is optimal to keep a large learning rate during the exploration phase to escape the non-convex region as quickly as possible, then use the convex criterion $\beta=1$ to converge rapidly to the solution.
no code implementations • 31 Jan 2022 • Bruno Loureiro, Cédric Gerbelot, Maria Refinetti, Gabriele Sicuro, Florent Krzakala
From the sampling of data to the initialisation of parameters, randomness is ubiquitous in modern Machine Learning practice.
1 code implementation • 6 Jan 2022 • Maria Refinetti, Sebastian Goldt
We derive a set of asymptotically exact equations that describe the generalisation dynamics of autoencoders trained with stochastic gradient descent (SGD) in the limit of high-dimensional inputs.
1 code implementation • 23 Feb 2021 • Maria Refinetti, Sebastian Goldt, Florent Krzakala, Lenka Zdeborová
Here, we show theoretically that two-layer neural networks (2LNN) with only a few hidden neurons can beat the performance of kernel learning on a simple Gaussian mixture classification task.
1 code implementation • 24 Nov 2020 • Maria Refinetti, Stéphane d'Ascoli, Ruben Ohana, Sebastian Goldt
Direct Feedback Alignment (DFA) is emerging as an efficient and biologically plausible alternative to the ubiquitous backpropagation algorithm for training deep neural networks.
no code implementations • 20 Sep 2020 • Antoine Baker, Indaco Biazzo, Alfredo Braunstein, Giovanni Catania, Luca Dall'Asta, Alessandro Ingrosso, Florent Krzakala, Fabio Mazza, Marc Mézard, Anna Paola Muntoni, Maria Refinetti, Stefano Sarao Mannelli, Lenka Zdeborová
We conclude that probabilistic risk estimation is capable to enhance performance of digital contact tracing and should be considered in the currently developed mobile applications.
2 code implementations • 2 Mar 2020 • Stéphane d'Ascoli, Maria Refinetti, Giulio Biroli, Florent Krzakala
We obtain a precise asymptotic expression for the bias-variance decomposition of the test error, and show that the bias displays a phase transition at the interpolation threshold, beyond which it remains constant.