Personne
Fabian Ricardo Latorre Gomez
Cette personne n’est plus à l’EPFL
Publications associées (9)
Improving SAM Requires Rethinking its Optimization Formulation
Volkan Cevher, Kimon Antonakopoulos, Thomas Michaelsen Pethick, Wanyun Xie, Fabian Ricardo Latorre Gomez
This paper rethinks Sharpness-Aware Minimization (SAM), which is originally formulated as a zero-sum game where the weights of a network and a bounded perturbation try to minimize/maximize, respectively, the same differentiable loss. We argue that SAM shou ...
2024Adversarial Training Should Be Cast As a Non-Zero-Sum Game
Volkan Cevher, Seyed Hamed Hassani, Fabian Ricardo Latorre Gomez
One prominent approach toward resolving the adversarial vulnerability of deep neural networks is the two-player zero-sum paradigm of adversarial training, in which predictors are trained against adversarially-chosen perturbations of data. Despite the promi ...
2023Robust Training and Verification of Deep Neural Networks
According to the proposed Artificial Intelligence Act by the European Comission (expected to pass at the end of 2023), the class of High-Risk AI Systems (Title III) comprises several important applications of Deep Learning like autonomous driving vehicles ...
EPFL2023Controlling the Complexity and Lipschitz Constant improves Polynomial Nets
Volkan Cevher, Grigorios Chrysos, Fabian Ricardo Latorre Gomez
While the class of Polynomial Nets demonstrates comparable performance to neural networks (NN), it currently has neither theoretical generalization characterization nor robustness guarantees. To this end, we derive new complexity bounds for the set of Coup ...
2022A Plug-and-Play Deep Image Prior
Volkan Cevher, Fabian Ricardo Latorre Gomez, Thomas Sanchez, Zhaodong Sun
Deep image priors (DIP) offer a novel approach for the regularization that leverages the inductive bias of a deep convolutional architecture in inverse problems. However, the quality of DIP approaches often degrades when the number of iterations exceeds a ...
IEEE2021Lipschitz constant estimation for Neural Networks via sparse polynomial optimization
Volkan Cevher, Paul Thierry Yves Rolland, Fabian Ricardo Latorre Gomez
We introduce LiPopt, a polynomial optimization framework for computing increasingly tighter upper bounds on the Lipschitz constant of neural networks. The underlying optimization problems boil down to either linear (LP) or semidefinite (SDP) programming. W ...
2020Efficient Proximal Mapping of the 1-path-norm of Shallow Networks
Volkan Cevher, Paul Thierry Yves Rolland, Fabian Ricardo Latorre Gomez, Shaul Nadav Hallak
We demonstrate two new important properties of the 1-path-norm of shallow neural networks. First, despite its non-smoothness and non-convexity it allows a closed form proximal operator which can be efficiently computed, allowing the use of stochastic proxi ...
2020An Inexact Augmented Lagrangian Framework for Nonconvex Optimization with Nonlinear Constraints
Volkan Cevher, Ahmet Alacaoglu, Armin Eftekhari, Fabian Ricardo Latorre Gomez, Mehmet Fatih Sahin
We propose a practical inexact augmented Lagrangian method (iALM) for nonconvex problems with nonlinear constraints. We characterize the total computational complexity of our method subject to a verifiable geometric condition, which is closely related to t ...
2019Fast and Provable ADMM for Learning with Generative Priors
Volkan Cevher, Armin Eftekhari, Fabian Ricardo Latorre Gomez
In this work, we propose a (linearized) Alternating Direction Method-of-Multipliers (ADMM) algorithm for minimizing a convex function subject to a nonconvex constraint. We focus on the special case where such constraint arises from the specification that a ...
2019