Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks
2024-03-10. Proceedings of the 27th International Conference on Artificial Intelligence and Statistics (AIS- TATS) 2024, , Valencia, Spain, May 2-4, 2024.Scalable constrained optimization
Lausanne, EPFL, 2024.Saddle-to-Saddle Dynamics in Diagonal Linear Networks
2023-04-02. 37th Conference on Neural Information Processing Systems (NeurIPS 2023), New Orleans, LA, United States, December 10-16, 2023.Model agnostic methods meta-learn despite misspecifications
2023-03-03
Penalising the biases in norm regularisation enforces sparsity
2023-03-03
(S)GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stability
2023-02-17. 37th Conference on Neural Information Processing Systems (NeurIPS 2023), New Orleans, LA, United States, December 10-16, 2023.Improved bounds for discretization of Langevin diffusions: Near-optimal rates without convexity
Bernoulli. 2022-08-01. Vol. 28, num. 3, p. 1577-1601. DOI : 10.3150/21-BEJ1343.Utility/privacy trade-off as regularized optimal transport
Mathematical Programming. 2022-04-22. DOI : 10.1007/s10107-022-01811-w.Accelerated SGD for Non-Strongly-Convex Least Squares
2022-03-03
An Efficient Sampling Algorithm for Non-smooth Composite Potentials
Journal Of Machine Learning Research. 2022-01-01. Vol. 23.Towards Understanding Sharpness-Aware Minimization
2022-01-01. 38th International Conference on Machine Learning (ICML), Baltimore, MD, Jul 17-23, 2022. p. 639-668.Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks
2022-01-01. 36th AAAI Conference on Artificial Intelligence / 34th Conference on Innovative Applications of Artificial Intelligence / 12th Symposium on Educational Advances in Artificial Intelligence, ELECTR NETWORK, Feb 22-Mar 01, 2022. p. 6437-6445. DOI : 10.1609/aaai.v36i6.20595.Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs
2022
Trace norm regularization for multi-task learning with scarce data
2022
Last iterate convergence of SGD for Least-Squares in the Interpolation regime
2021-09-28
Is there an analog of Nesterov acceleration for gradient-based MCMC?
Bernoulli. 2021-08-01. Vol. 27, num. 3, p. 1942-1992. DOI : 10.3150/20-BEJ1297.Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity
2021-06-16. 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Virtual Conference, December 6-14, 2021.On the effectiveness of adversarial training against common corruptions
2021-03-03
A Continuized View on Nesterov Acceleration
2021
On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines
2021. 9th International Conference on Learning Representations, Virtual, May 4-8, 2021.RobustBench: a standardized adversarial robustness benchmark
2020-10-19
Square Attack: a query-efficient black-box adversarial attack via random search
2020-08-28. European Conference on Computer Vision (ECCV 2020), [Online], August 23-28, 2020. p. 484–501. DOI : 10.1007/978-3-030-58592-1_29.Understanding and Improving Fast Adversarial Training
2020-07-06. Advances In Neural Information Processing Systems 33 (NeurIPS 2020), [Online], December 2020.Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks
2020-06-23