List of published papers and preprints
M. Hihat, G. Garrigos, A. Fermanian and S. Bussy
Multivariate Online Linear Regression for Hierarchical Forecasting
Posted online on 2024-02-22
Links: arXiv:2402.14578.
G. Garrigos, R. M. Gower, U. Simsekli and F. Schaipp
SGD with Clipping is Secretly Estimating the Median Gradient
Posted online on 2024-02-20
Links: arXiv:2402.12828.
G. Garrigos, R. M. Gower and F. Schaipp
Function Value Learning: Adaptive Learning Rates Based on the Polyak Stepsize and Function Splitting in ERM
Posted online on 2023-07-26
Links: arXiv:2307.14528.
M. Hihat, S. Gaïffas, G. Garrigos and S. Bussy
Online Inventory Problems: Beyond the i.i.d. Setting with Online Convex Optimization
Advances in Neural Information Processing Systems, Vol. 36, 2024.
Links: arXiv:2307.06048, editor.
J. Domke, G. Garrigos and R. M. Gower
Provable convergence guarantees for black-box variational inference
Advances in Neural Information Processing Systems, Vol. 36, 2024.
Links: arXiv:2306.03638, editor, slides.
G. Garrigos and R. M. Gower
Handbook of Convergence Theorems for (Stochastic) Gradient Methods
Posted online on 2023-01-26
Links: arXiv:2301.11235.
G. Garrigos
Square distance functions are Polyak-Łojasiewicz and vice-versa
Posted online on 2023-01-24
Links: arXiv:2301.10332.
J. Chen, R. Yuan, G. Garrigos and R. M. Gower
SAN: Stochastic Average Newton Algorithm for Minimizing Finite Sums
25th International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR, Vol. 151, pp. 279–318, 2022.
Links: arXiv:2106.10520, editor.
G. Garrigos, L. Rosasco and S. Villa
Accelerated iterative regularization via dual diagonal descent
SIAM Journal on Optimization, Vol. 31, No. 1, pp. 754–784, 2021.
Links: arXiv:1912.12153, editor.
G. Garrigos, L. Rosasco and S. Villa
Sparse Multiple Kernel Learning: Support Identification via Mirror Stratifiability
IEEE 26th European Signal Processing Conference (EUSIPCO), pp. 1077–1081, 2018.
Links: arXiv:1803.00783, editor.
J. Fadili, G. Garrigos, J. Malick and G. Peyré
Model Consistency for Learning with Mirror-Stratifiable Regularizers
22nd International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR, Vol. 89, pp. 1236–1244, 2019.
Links: arXiv:1803.08381, editor.
G. Garrigos, L. Rosasco and S. Villa
Thresholding gradient methods in Hilbert spaces: support identification and linear convergence
ESAIM: Control, Optimisation and Calculus of Variations, Vol. 26 (28), 2020.
Links: arXiv:1712.00357, editor.
G. Garrigos, L. Rosasco and S. Villa
Iterative regularization via dual diagonal descent
Journal of Mathematical Imaging and Vision, Vol. 60, No. 2, pp. 189–215, 2018.
Links: arXiv:1610.02170, editor, slides.
G. Garrigos, L. Rosasco and S. Villa
Convergence of the Forward-Backward algorithm: beyond the worst case with geometry
Mathematical Programming, Vol. 198, pp. 937–996, 2023
Links: arXiv:1703.09477, editor, slides.
G. Garrigos, L. Rosasco and S. Villa
Iterative regularization via a dual diagonal descent method
9th NIPS Workshop on Optimization for Machine Learning, 2016.
Links: arXiv:1610.02170, editor.
H. Attouch and G. Garrigos
Multiobjective optimization : an inertial dynamical approach to Pareto optima
Posted online on 2015-06-09
Links: arXiv:1506.02823, slides.
H. Attouch, G. Garrigos and X. Goudou
A dynamic gradient approach to Pareto optimization with nonsmooth convex objective functions
Journal of Mathematical Analysis and Applications, Vol. 422, No. 1, pp. 741–771, 2015.
Links: arXiv:1406.1694, editor, slides.
P. Frankel, G. Garrigos and J. Peypouquet
Splitting methods with variable metric for KL functions and general convergence rates
Journal of Optimization Theory and Applications, Vol. 165, No. 3, pp. 874–900, 2015.
Links: arXiv:1405.1357, editor, slides.
Ph. D. Thesis
G. Garrigos
Descent dynamical systems and algorithms for tame optimization and multi-objective problems.
Links: manuscript.
The thesis was defended on November 2nd, 2015 at Université de Montpellier. The members of the committee were H. Attouch, Aris Daniilidis, Jalal Fadili, Pedro Gajardo, Adrian Lewis, Juan Peypouquet and Lionel Thibault.