2 citations · 2 across the 4 of their papers we have counts for
4 papers
Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model
Peter Súkeník, Marco Mondelli, Christoph Lampert
Neural collapse (NC) refers to the surprising structure of the last layer of deep neural networks in the terminal phase of gradient descent training. Recently, an increasing amount…
Mismatched estimation of non-symmetric rank-one matrices corrupted by structured noise
Teng Fu, YuHao Liu, Jean Barbier +3
We study the performance of a Bayesian statistician who estimates a rank-one signal corrupted by non-symmetric rotationally invariant noise with a generic distribution of singular…
Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels
Simone Bombari, Shayan Kiyani, Marco Mondelli
Machine learning models are vulnerable to adversarial perturbations, and a thought-provoking paper by Bubeck and Sellke has analyzed this phenomenon through the lens of over-parame…
Capacity-Achieving Rate-Compatible Polar Codes for General Channels
Marco Mondelli, S. Hamed Hassani, Ivana Marić +2
We present a rate-compatible polar coding scheme that achieves the capacity of any family of channels. Our solution generalizes the previous results [1], [2] that provide capacity-…