Loucas Pillaud-Vivien

31 papers A* 13A 1Journal 17

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Convergence of Shallow ReLU Networks on Weakly Interacting Data. CoRR Léo Dana, Francis R. Bach, Loucas Pillaud-Vivien
2025	J	`jnl`	Joint Learning in the Gaussian Single Index Model. CoRR Loucas Pillaud-Vivien, Adrien Schertzer
2025	J	`jnl`	Variational Inference for Uncertainty Quantification: an Analysis of Trade-offs. J. Mach. Learn. Res. Charles C. Margossian, Loucas Pillaud-Vivien, Lawrence K. Saul
2024	J	`jnl`	An Ordering of Divergences for Variational Inference with Factorized Gaussian Approximations. CoRR Charles C. Margossian, Loucas Pillaud-Vivien, Lawrence K. Saul
2024	A*	`conf`	Batch and match: black-box variational inference with a score-based divergence. ICML Diana Cai, Chirag Modi, Loucas Pillaud-Vivien, Charles Margossian, Robert M. Gower, David M. Blei, Lawrence K. Saul
2024	J	`jnl`	Batch and match: black-box variational inference with a score-based divergence. CoRR Diana Cai, Chirag Modi, Loucas Pillaud-Vivien, Charles C. Margossian, Robert M. Gower, David M. Blei, Lawrence K. Saul
2024	A*	`conf`	Computational-Statistical Gaps in Gaussian Single-Index Models (Extended Abstract). COLT Alex Damian, Loucas Pillaud-Vivien, Jason D. Lee, Joan Bruna
2024	J	`jnl`	Computational-Statistical Gaps in Gaussian Single-Index Models. CoRR Alex Damian, Loucas Pillaud-Vivien, Jason D. Lee, Joan Bruna
2024	J	`jnl`	Stochastic Differential Equations models for Least-Squares Stochastic Gradient Descent. CoRR Adrien Schertzer, Loucas Pillaud-Vivien
2023	A*	`conf`	Kernelized Diffusion Maps. COLT Loucas Pillaud-Vivien, Francis R. Bach
2023	J	`jnl`	Kernelized Diffusion maps. CoRR Loucas Pillaud-Vivien, Francis R. Bach
2023	J	`jnl`	On Learning Gaussian Multi-index Models with Gradient Flow. CoRR Alberto Bietti, Joan Bruna, Loucas Pillaud-Vivien
2023	J	`jnl`	On Single Index Models beyond Gaussian Data. CoRR Joan Bruna, Loucas Pillaud-Vivien, Aaron Zweig
2023	A*	`conf`	On Single-Index Models beyond Gaussian Data. NeurIPS Aaron Zweig, Loucas Pillaud-Vivien, Joan Bruna
2023	A*	`conf`	On the spectral bias of two-layer linear networks. NeurIPS Aditya Vardhan Varre, Maria-Luiza Vladarean, Loucas Pillaud-Vivien, Nicolas Flammarion
2023	A*	`conf`	SGD with Large Step Sizes Learns Sparse Features. ICML Maksym Andriushchenko, Aditya Vardhan Varre, Loucas Pillaud-Vivien, Nicolas Flammarion
2022	A*	`conf`	Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs. NeurIPS Etienne Boursier, Loucas Pillaud-Vivien, Nicolas Flammarion
2022	J	`jnl`	Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs. CoRR Etienne Boursier, Loucas Pillaud-Vivien, Nicolas Flammarion
2022	A*	`conf`	Label noise (stochastic) gradient descent implicitly solves the Lasso for quadratic parametrisation. COLT Loucas Pillaud-Vivien, Julien Reygner, Nicolas Flammarion
2022	J	`jnl`	Label noise (stochastic) gradient descent implicitly solves the Lasso for quadratic parametrisation. CoRR Loucas Pillaud-Vivien, Julien Reygner, Nicolas Flammarion
2022	J	`jnl`	SGD with large step sizes learns sparse features. CoRR Maksym Andriushchenko, Aditya Varre, Loucas Pillaud-Vivien, Nicolas Flammarion
2021	A*	`conf`	Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity. NeurIPS Scott Pesme, Loucas Pillaud-Vivien, Nicolas Flammarion
2021	J	`jnl`	Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity. CoRR Scott Pesme, Loucas Pillaud-Vivien, Nicolas Flammarion
2021	A*	`conf`	Last iterate convergence of SGD for Least-Squares in the Interpolation regime. NeurIPS Aditya Vardhan Varre, Loucas Pillaud-Vivien, Nicolas Flammarion
2021	J	`jnl`	Last iterate convergence of SGD for Least-Squares in the Interpolation regime. CoRR Aditya Varre, Loucas Pillaud-Vivien, Nicolas Flammarion
2021	A*	`conf`	Overcoming the curse of dimensionality with Laplacian regularization in semi-supervised learning. NeurIPS Vivien Cabannes, Loucas Pillaud-Vivien, Francis R. Bach, Alessandro Rudi
2020	A	`conf`	Statistical Estimation of the Poincaré constant and Application to Sampling Multimodal Distributions. AISTATS Loucas Pillaud-Vivien, Francis R. Bach, Tony Lelièvre, Alessandro Rudi, Gabriel Stoltz
2018	A*	`conf`	Exponential Convergence of Testing Error for Stochastic Gradient Methods. COLT Loucas Pillaud-Vivien, Alessandro Rudi, Francis R. Bach
2018	A*	`conf`	Statistical Optimality of Stochastic Gradient Descent on Hard Learning Problems through Multiple Passes. NeurIPS Loucas Pillaud-Vivien, Alessandro Rudi, Francis R. Bach
2018	J	`jnl`	Statistical Optimality of Stochastic Gradient Descent on Hard Learning Problems through Multiple Passes. CoRR Loucas Pillaud-Vivien, Alessandro Rudi, Francis R. Bach
2017	J	`jnl`	Exponential convergence of testing error for stochastic gradient methods. CoRR Loucas Pillaud-Vivien, Alessandro Rudi, Francis R. Bach