58 citations · 101 across the 14 of their papers we have counts for
14 papers
Influence Diagnostics in High-dimensional M-estimation: Precise Asymptotics
Hugo Cui
The impact of a given training point on a statistical model can be measured through its leave-one-out influence on the model parameters, which quantifies how its removal from the t…
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…
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…
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…
A phase transition between positional and semantic learning in a solvable model of dot-product attention
Hugo Cui, Freya Behrens, Florent Krzakala +1
Many empirical studies have provided evidence for the emergence of algorithmic mechanisms (abilities) in the learning of language models, that lead to qualitative improvements of t…
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-…
High-dimensional Asymptotics of Denoising Autoencoders
Hugo Cui, Lenka Zdeborová
We address the problem of denoising data from a Gaussian mixture using a two-layer non-linear autoencoder with tied weights and a skip connection. We consider the high-dimensional…
Deterministic equivalent and error universality of deep random features learning
Dominik Schröder, Hugo Cui, Daniil Dmitriev +1
This manuscript considers the problem of learning a random Gaussian network function using a fully connected network with frozen intermediate layers and trainable readout layer. Th…
Bayes-optimal Learning of Deep Random Networks of Extensive-width
Hugo Cui, Florent Krzakala, Lenka Zdeborová
We consider the problem of learning a target function corresponding to a deep, extensive-width, non-linear neural network with random Gaussian weights. We consider the asymptotic l…
Error Scaling Laws for Kernel Classification under Source and Capacity Conditions
Hugo Cui, Bruno Loureiro, Florent Krzakala +1
We consider the problem of kernel classification. While worst-case bounds on the decay rate of the prediction error with the number of samples are known for some classifiers, they…
Large Deviations of Semi-supervised Learning in the Stochastic Block Model
Hugo Cui, Luca Saglietti, Lenka Zdeborová
In community detection on graphs, the semi-supervised learning problem entails inferring the ground-truth membership of each node in a graph, given the connectivity structure and a…
Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime
Hugo Cui, Bruno Loureiro, Florent Krzakala +1
In this manuscript we consider Kernel Ridge Regression (KRR) under the Gaussian design. Exponents for the decay of the excess generalization error of KRR have been reported in vari…
Learning curves of generic features maps for realistic datasets with a teacher-student model
Bruno Loureiro, Cédric Gerbelot, Hugo Cui +4
Teacher-student models provide a framework in which the typical-case performance of high-dimensional supervised learning can be described in closed form. The assumptions of Gaussia…
Large deviations for the perceptron model and consequences for active learning
Hugo Cui, Luca Saglietti, Lenka Zdeborová
Active learning is a branch of machine learning that deals with problems where unlabeled data is abundant yet obtaining labels is expensive. The learning algorithm has the possibil…