collaborators
Showing stat.MLShow all

5 papers · 1 filter

stat.ML2026

Influence Diagnostics in High-dimensional M-estimation: Precise Asymptotics

Hugo Cui

The impact of a given training point on a statistical model is classically measured through its leave-one-out influence, which quantifies the effect of its removal from the trainin…

stat.ML2024

A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities

Yatin Dandi, Luca Pesce, Hugo Cui +3

A key property of neural networks is their capacity of adapting to data during training. Yet, our current mathematical understanding of feature learning and its relationship to gen…

stat.ML2024

Analysis of learning a flow-based generative model from limited sample complexity

Hugo Cui, Florent Krzakala, Eric Vanden-Eijnden +1

We study the problem of training a flow-based generative model, parametrized by a two-layer autoencoder, to sample from a high-dimensional Gaussian mixture. We provide a sharp end-…

stat.ML2024

Asymptotics of Learning with Deep Structured (Random) Features

Dominik Schröder, Daniil Dmitriev, Hugo Cui +1

For a large class of feature maps we provide a tight asymptotic characterisation of the test error associated with learning the readout layer, in the high-dimensional limit where t…

stat.ML2024

Asymptotics of feature learning in two-layer networks after one gradient-step

Hugo Cui, Luca Pesce, Yatin Dandi +4

In this manuscript, we investigate the problem of how two-layer neural networks learn features from data, and improve over the kernel regime, after being trained with a single grad…