Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Eghbali, Reza"'
Transformer-based networks applied to image patches have achieved cutting-edge performance in many vision tasks. However, lacking the built-in bias of convolutional neural networks (CNN) for local image statistics, they require large datasets and mod
Externí odkaz:
http://arxiv.org/abs/2407.01367
In this paper, we study a certain class of online optimization problems, where the goal is to maximize a function that is not necessarily concave and satisfies the Diminishing Returns (DR) property under budget constraints. We analyze a primal-dual a
Externí odkaz:
http://arxiv.org/abs/1907.00312
We consider a new and general online resource allocation problem, where the goal is to maximize a function of a positive semidefinite (PSD) matrix with a scalar budget constraint. The problem data arrives online, and the algorithm needs to make an ir
Externí odkaz:
http://arxiv.org/abs/1802.01312
Autor:
Eghbali, Reza, Fazel, Maryam
Online optimization covers problems such as online resource allocation, online bipartite matching, adwords (a central problem in e-commerce and advertising), and adwords with separable concave returns. We analyze the worst case competitive ratio of t
Externí odkaz:
http://arxiv.org/abs/1611.00507
Autor:
Eghbali, Reza, Fazel, Maryam
We study the convergence rate of the proximal-gradient homotopy algorithm applied to norm-regularized linear least squares problems, for a general class of norms. The homotopy algorithm reduces the regularization parameter in a series of steps, and u
Externí odkaz:
http://arxiv.org/abs/1501.06711
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Online optimization problems arise in many resource allocation tasks, where the future demands for each resource and the associated utility functions change over time and are not known apriori, yet resources need to be allocated at every point in tim
Externí odkaz:
http://arxiv.org/abs/1410.7171
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Eghbali, Reza1 eghbali@uw.edu, Fazel, Maryam1 mfazel@uw.edu
Publikováno v:
Computational Optimization & Applications. Mar2017, Vol. 66 Issue 2, p345-381. 37p.
Publikováno v:
2016 IEEE 55th Conference on Decision & Control (CDC); 2016, p1945-1950, 6p