Picture for Loucas Pillaud-Vivien

Loucas Pillaud-Vivien

SIERRA

Stochastic Differential Equations models for Least-Squares Stochastic Gradient Descent

Add code
Jul 02, 2024
Viaarxiv icon

An Ordering of Divergences for Variational Inference with Factorized Gaussian Approximations

Add code
Mar 20, 2024
Viaarxiv icon

Computational-Statistical Gaps in Gaussian Single-Index Models

Add code
Mar 12, 2024
Viaarxiv icon

Batch and match: black-box variational inference with a score-based divergence

Add code
Feb 22, 2024
Viaarxiv icon

On Learning Gaussian Multi-index Models with Gradient Flow

Add code
Nov 02, 2023
Viaarxiv icon

On Single Index Models beyond Gaussian Data

Add code
Jul 28, 2023
Viaarxiv icon

Kernelized Diffusion maps

Add code
Feb 13, 2023
Viaarxiv icon

SGD with large step sizes learns sparse features

Add code
Oct 11, 2022
Figure 1 for SGD with large step sizes learns sparse features
Figure 2 for SGD with large step sizes learns sparse features
Figure 3 for SGD with large step sizes learns sparse features
Figure 4 for SGD with large step sizes learns sparse features
Viaarxiv icon

Label noise (stochastic) gradient descent implicitly solves the Lasso for quadratic parametrisation

Add code
Jun 20, 2022
Figure 1 for Label noise (stochastic) gradient descent implicitly solves the Lasso for quadratic parametrisation
Viaarxiv icon

Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs

Add code
Jun 02, 2022
Figure 1 for Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs
Figure 2 for Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs
Figure 3 for Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs
Figure 4 for Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs
Viaarxiv icon