Vincent Roulet

According to our database, Vincent Roulet authored at least 22 papers between 2015 and 2024.

Collaborative distances:

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

2024

The Elements of Differentiable Programming.

Mathieu Blondel, Vincent Roulet

CoRR, 2024

2023

Target Propagation via Regularized Inversion for Recurrent Neural Networks.

Vincent Roulet, Zaïd Harchaoui

Trans. Mach. Learn. Res., 2023

On the Interplay Between Stepsize Tuning and Progressive Sharpening.

Vincent Roulet, Atish Agarwala, Fabian Pedregosa

CoRR, 2023

Distributionally Robust Optimization with Bias and Variance Reduction.

Ronak Mehta, Vincent Roulet, Krishna Pillutla, Zaïd Harchaoui

CoRR, 2023

Dual Gauss-Newton Directions for Deep Learning.

Vincent Roulet, Mathieu Blondel

CoRR, 2023

Modified Gauss-Newton Algorithms under Noise.

Krishna Pillutla, Vincent Roulet, Sham M. Kakade, Zaïd Harchaoui

Proceedings of the IEEE Statistical Signal Processing Workshop, 2023

Stochastic Optimization for Spectral Risk Measures.

Ronak Mehta, Vincent Roulet, Krishna Pillutla, Lang Liu, Zaïd Harchaoui

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

Discriminative clustering with representation learning with any ratio of labeled to unlabeled data.

Corinne Jones, Vincent Roulet, Zaïd Harchaoui

Stat. Comput., 2022

Iterative Linear Quadratic Optimization for Nonlinear Control: Differentiable Programming Algorithmic Templates.

Vincent Roulet, Siddhartha S. Srinivasa, Maryam Fazel, Zaïd Harchaoui

CoRR, 2022

Differentiable Programming A La Moreau.

Vincent Roulet, Zaïd Harchaoui

Proceedings of the IEEE International Conference on Acoustics, 2022

2021

Target Propagation via Regularized Inversion.

Vincent Roulet, Zaïd Harchaoui

CoRR, 2021

On the Smoothing of Deep Networks.

Vincent Roulet, Zaïd Harchaoui

Proceedings of the 55th Annual Conference on Information Sciences and Systems, 2021

2020

Sharpness, Restart, and Acceleration.

Vincent Roulet, Alexandre d'Aspremont

SIAM J. Optim., 2020

On the Convergence of the Iterative Linear Exponential Quadratic Gaussian Algorithm to Stationary Points.

Vincent Roulet, Maryam Fazel, Siddhartha S. Srinivasa, Zaïd Harchaoui

Proceedings of the 2020 American Control Conference, 2020

2019

End-to-end Learning, with or without Labels.

Corinne Jones, Vincent Roulet, Zaïd Harchaoui

CoRR, 2019

Kernel-based Translations of Convolutional Networks.

Corinne Jones, Vincent Roulet, Zaïd Harchaoui

CoRR, 2019

Iterative Linearized Control: Stable Algorithms and Complexity Guarantees.

Vincent Roulet, Dmitriy Drusvyatskiy, Siddhartha S. Srinivasa, Zaïd Harchaoui

Proceedings of the 36th International Conference on Machine Learning, 2019

An Elementary Approach to Convergence Guarantees of Optimization Algorithms for Deep Networks.

Vincent Roulet, Zaïd Harchaoui

Proceedings of the 57th Annual Allerton Conference on Communication, 2019

2018

A Smoother Way to Train Structured Prediction Models.

Venkata Krishna Pillutla, Vincent Roulet, Sham M. Kakade, Zaïd Harchaoui

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

2017

Sur la géométrie de problèmes d'optimisation et leur structure. (On the geometry of optimization problems and their structure).

Vincent Roulet

PhD thesis, 2017

Integration Methods and Optimization Algorithms.

Damien Scieur, Vincent Roulet, Francis R. Bach, Alexandre d'Aspremont

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

2015

Supervised Clustering in the Data Cube.

Vincent Roulet, Fajwel Fogel, Alexandre d'Aspremont, Francis R. Bach

CoRR, 2015