Publication

On the Double Descent of Random Features Models Trained with SGD

Publications associées (30)

The inductive bias of deep learning: Connecting weights and functions

Years of a fierce competition have naturally selected the fittest deep learning algorithms. Yet, although these models work well in practice, we still lack a proper characterization of why they do so. This poses serious questions about the robustness, trus ...

EPFL2023

Traversing Time Dependent Light Fields for Daylight Glare Evaluation

Stephen William Wasilewski

To understand how daylight gives shape and life to architectural spaces, whether existing or imagined, requires quantifying its dynamism and energy. Maintaining these details presents a challenge to simulation and analysis methods that flatten data into di ...

EPFL2023

The inductive bias of deep learning: Connecting weights and functions

Guillermo Ortiz Jimenez

EPFL2023

Traversing Time Dependent Light Fields for Daylight Glare Evaluation

Stephen William Wasilewski

EPFL2023

Byzantine Fault-Tolerance in Federated Local SGD Under 2f-Redundancy

Nirupam Gupta

In this article, we study the problem of Byzantine fault-tolerance in a federated optimization setting, where there is a group of agents communicating with a centralized coordinator. We allow up to

f

Byzantine-faulty agents, which may not follow a prescr ...

Ieee-Inst Electrical Electronics Engineers Inc2023

Center-aware Adversarial Augmentation for Single Domain Generalization

Mathieu Salzmann, Zhiye Wang

Domain generalization (DG) aims to learn a model from multiple training (i.e., source) domains that can generalize well to the unseen test (i.e., target) data coming from a different distribution. Single domain generalization (SingleDG) has recently emerge ...

IEEE COMPUTER SOC2023

Bayes-optimal Learning of Deep Random Networks of Extensive-width

Florent Gérard Krzakala, Lenka Zdeborová, Hugo Chao Cui

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 limit where the number of samples, the input dimension and the network width ...

2023

Stochastic adaptive resampling for the estimation of discrete choice models

Michel Bierlaire, Nicola Marco Ortelli, Matthieu Marie Cochon de Lapparent

In the field of choice modeling, the availability of ever-larger datasets has the potential to significantly expand our understanding of human behavior, but this prospect is limited by the poor scalability of discrete choice models (DCMs): as sample sizes ...

2023

Phenomenological theory of variational quantum ground-state preparation

Ivano Tavernelli, Giuseppe Carleo

The variational approach is a cornerstone of computational physics, considering both conventional and quantum computing computational platforms. The variational quantum eigensolver algorithm aims to prepare the ground state of a Hamiltonian exploiting para ...

Amer Physical Soc2023

Augmented Lagrangian Methods for Provable and Scalable Machine Learning

Mehmet Fatih Sahin

Non-convex constrained optimization problems have become a powerful framework for modeling a wide range of machine learning problems, with applications in k-means clustering, large- scale semidefinite programs (SDPs), and various other tasks. As the perfor ...

EPFL2023

Modelling of metal alloys in realistic conditions with machine learning

Nataliya Lopanitsyna

Computer simulations based on statistical methods have emerged as a powerful tool for studying structure-property relationships at the atomistic level. However, to provide reliable insights into materials in realistic conditions, it is essential to accurat ...

EPFL2023

Epigenome-wide DNA methylation in externalizing behaviours: A review and combined analysis

Maria del Carmen Sandi Perez, Mandy Meijer

DNA methylation (DNAm) is one of the most frequently studied epigenetic mechanisms facilitating the interplay of genomic and environmental factors, which can contribute to externalizing behaviours and related psychiatric disorders. Previous epigenome-wide ...

PERGAMON-ELSEVIER SCIENCE LTD2023

Byzantine Fault-Tolerance in Federated Local SGD Under 2f-Redundancy

Nirupam Gupta

In this article, we study the problem of Byzantine fault-tolerance in a federated optimization setting, where there is a group of agents communicating with a centralized coordinator. We allow up to

f

Byzantine-faulty agents, which may not follow a prescr ...

Ieee-Inst Electrical Electronics Engineers Inc2023