A High Dimensional Model for Adversarial Training: Geometry and Trade-Offs

1 code implementation • 8 Feb 2024 • Kasimir Tanner, Matteo Vilucchio, Bruno Loureiro, Florent Krzakala

This work investigates adversarial training in the context of margin-based linear classifiers in the high-dimensional regime where the dimension $d$ and the number of data points $n$ diverge with a fixed ratio $\alpha = n / d$.

Adversarial Robustness

Asymptotic Characterisation of Robust Empirical Risk Minimisation Performance in the Presence of Outliers

1 code implementation • 30 May 2023 • Matteo Vilucchio, Emanuele Troiani, Vittorio Erba, Florent Krzakala

We study robust linear regression in high-dimension, when both the dimension $d$ and the number of data points $n$ diverge with a fixed ratio $\alpha=n/d$, and study a data model that includes outliers.

Genealogical Population-Based Training for Hyperparameter Optimization

1 code implementation • 30 Sep 2021 • Antoine Scardigli, Paul Fournier, Matteo Vilucchio, David Naccache

HyperParameter Optimization (HPO) aims at finding the best HyperParameters (HPs) of learning models, such as neural networks, in the fastest and most efficient way possible.

Hyperparameter Optimization