Zobrazeno 1 - 10
of 42
pro vyhledávání: '"Nouiehed, Maher"'
Current techniques for Out-of-Distribution (OoD) detection predominantly rely on quantifying predictive uncertainty and incorporating model regularization during the training phase, using either real or synthetic OoD samples. However, methods that ut
Externí odkaz:
http://arxiv.org/abs/2310.08040
Publikováno v:
INFORMS Journal on Data Science, 2024
Cost-sensitive classification is critical in applications where misclassification errors widely vary in cost. However, over-parameterization poses fundamental challenges to the cost-sensitive modeling of deep neural networks (DNNs). The ability of a
Externí odkaz:
http://arxiv.org/abs/2208.11739
Publikováno v:
Informs Journal on Data Science, 2022
In this paper we propose \texttt{GIFAIR-FL}: a framework that imposes \textbf{G}roup and \textbf{I}ndividual \textbf{FAIR}ness to \textbf{F}ederated \textbf{L}earning settings. By adding a regularization term, our algorithm penalizes the spread in th
Externí odkaz:
http://arxiv.org/abs/2108.02741
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems, 2023
In an effort to improve generalization in deep learning and automate the process of learning rate scheduling, we propose SALR: a sharpness-aware learning rate update technique designed to recover flat minimizers. Our method dynamically updates the le
Externí odkaz:
http://arxiv.org/abs/2011.05348
Autor:
Razaviyayn, Meisam, Huang, Tianjian, Lu, Songtao, Nouiehed, Maher, Sanjabi, Maziar, Hong, Mingyi
Publikováno v:
IEEE Signal Processing Magazine (Volume: 37, Issue: 5, Sept. 2020)
The min-max optimization problem, also known as the saddle point problem, is a classical optimization problem which is also studied in the context of zero-sum games. Given a class of objective functions, the goal is to find a value for the argument w
Externí odkaz:
http://arxiv.org/abs/2006.08141
Publikováno v:
International Conference on Learning Representation, 2020
Machine learning algorithms have been increasingly deployed in critical automated decision-making systems that directly affect human lives. When these algorithms are only trained to minimize the training/test error, they could suffer from systematic
Externí odkaz:
http://arxiv.org/abs/1906.12005
Autor:
Nouiehed, Maher, Razaviyayn, Meisam
Motivated by TRACE algorithm [Curtis et al. 2017], we propose a trust region algorithm for finding second order stationary points of a linearly constrained non-convex optimization problem. We show the convergence of the proposed algorithm to (\epsilo
Externí odkaz:
http://arxiv.org/abs/1904.06784
Recent applications that arise in machine learning have surged significant interest in solving min-max saddle point games. This problem has been extensively studied in the convex-concave regime for which a global equilibrium solution can be computed
Externí odkaz:
http://arxiv.org/abs/1902.08297
We consider the problem of finding an approximate second-order stationary point of a constrained non-convex optimization problem. We first show that, unlike the gradient descent method for unconstrained optimization, the vanilla projected gradient de
Externí odkaz:
http://arxiv.org/abs/1810.02024
Autor:
Nouiehed, Maher, Razaviyayn, Meisam
With the increasing popularity of non-convex deep models, developing a unifying theory for studying the optimization problems that arise from training these models becomes very significant. Toward this end, we present in this paper a unifying landsca
Externí odkaz:
http://arxiv.org/abs/1803.02968