Loucas Pillaud-Vivien

According to our database, Loucas Pillaud-Vivien authored at least 16 papers between 2018 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

An Ordering of Divergences for Variational Inference with Factorized Gaussian Approximations.

Charles C. Margossian, Loucas Pillaud-Vivien, Lawrence K. Saul

CoRR, 2024

Computational-Statistical Gaps in Gaussian Single-Index Models.

Alex Damian, Loucas Pillaud-Vivien, Jason D. Lee, Joan Bruna

CoRR, 2024

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

Diana Cai, Chirag Modi, Loucas Pillaud-Vivien, Charles C. Margossian, Robert M. Gower, David M. Blei, Lawrence K. Saul

CoRR, 2024

2023

On Learning Gaussian Multi-index Models with Gradient Flow.

Alberto Bietti, Joan Bruna, Loucas Pillaud-Vivien

CoRR, 2023

On Single-Index Models beyond Gaussian Data.

Aaron Zweig, Loucas Pillaud-Vivien, Joan Bruna

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

On the spectral bias of two-layer linear networks.

Aditya Vardhan Varre, Maria-Luiza Vladarean, Loucas Pillaud-Vivien, Nicolas Flammarion

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

SGD with Large Step Sizes Learns Sparse Features.

Maksym Andriushchenko, Aditya Vardhan Varre, Loucas Pillaud-Vivien, Nicolas Flammarion

Proceedings of the International Conference on Machine Learning, 2023

Kernelized Diffusion Maps.

Loucas Pillaud-Vivien, Francis R. Bach

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

2022

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

Etienne Boursier, Loucas Pillaud-Vivien, Nicolas Flammarion

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

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

Loucas Pillaud-Vivien, Julien Reygner, Nicolas Flammarion

Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022

2021

Last iterate convergence of SGD for Least-Squares in the Interpolation regime.

Aditya Vardhan Varre, Loucas Pillaud-Vivien, Nicolas Flammarion

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity.

Scott Pesme, Loucas Pillaud-Vivien, Nicolas Flammarion

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Overcoming the curse of dimensionality with Laplacian regularization in semi-supervised learning.

Vivien Cabannes, Loucas Pillaud-Vivien, Francis R. Bach, Alessandro Rudi

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

Statistical Estimation of the Poincaré constant and Application to Sampling Multimodal Distributions.

Loucas Pillaud-Vivien, Francis R. Bach, Tony Lelièvre, Alessandro Rudi, Gabriel Stoltz

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2018

Statistical Optimality of Stochastic Gradient Descent on Hard Learning Problems through Multiple Passes.

Loucas Pillaud-Vivien, Alessandro Rudi, Francis R. Bach

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Exponential Convergence of Testing Error for Stochastic Gradient Methods.

Loucas Pillaud-Vivien, Alessandro Rudi, Francis R. Bach

Proceedings of the Conference On Learning Theory, 2018