30 citations · 59 across the 10 of their papers we have counts for
10 papers
Improving SAM Requires Rethinking its Optimization Formulation
Wanyun Xie, Fabian Latorre, Kimon Antonakopoulos +2
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/…
Adversarial Training Should Be Cast as a Non-Zero-Sum Game
Alexander Robey, Fabian Latorre, George J. Pappas +2
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 t…
OTW: Optimal Transport Warping for Time Series
Fabian Latorre, Chenghao Liu, Doyen Sahoo +1
Dynamic Time Warping (DTW) has become the pragmatic choice for measuring distance between time series. However, it suffers from unavoidable quadratic time complexity when the optim…
Controlling the Complexity and Lipschitz Constant improves polynomial nets
Zhenyu Zhu, Fabian Latorre, Grigorios G Chrysos +1
While the class of Polynomial Nets demonstrates comparable performance to neural networks (NN), it currently has neither theoretical generalization characterization nor robustness…
Solving Inverse Problems with Hybrid Deep Image Priors: the challenge of preventing overfitting
Zhaodong Sun, Thomas Sanchez, Fabian Latorre +1
We mainly analyze and solve the overfitting problem of deep image prior (DIP). Deep image prior can solve inverse problems such as super-resolution, inpainting and denoising. The m…
Efficient Proximal Mapping of the 1-path-norm of Shallow Networks
Fabian Latorre, Paul Rolland, Nadav Hallak +1
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 oper…
An Inexact Augmented Lagrangian Framework for Nonconvex Optimization with Nonlinear Constraints
Mehmet Fatih Sahin, Armin Eftekhari, Ahmet Alacaoglu +2
We propose a practical inexact augmented Lagrangian method (iALM) for nonconvex problems with nonlinear constraints. We characterize the total computational complexity of our metho…
Complexity Regularization and Local Metric Entropy
Fabián Latorre
In the context of Structural Risk Minimization, one is presented a sequence of classes from which, given a random sample one wants to choose a stron…
An incidence Hopf Algebra of Convex Geometries
Fabian Latorre
A lattice L is "meet-distributive" if for each element of L, the meets of the elements directly below it form a Boolean lattice. These objects are in bijection with "convex geometr…
The Maxflow problem and a generalization to simplicial complexes
Fabian Latorre
The problem of Maxflow is a widely developed subject in modern mathematics. Efficient algorithms exist to solve this problem, that is why a good generalization may permit these alg…