Zobrazeno 1 - 10
of 672
pro vyhledávání: '"Sadeghi,Omid"'
Autor:
Sadeghi, Omid, Fazel, Maryam
We study a generalization of the online binary prediction with expert advice framework where at each round, the learner is allowed to pick $m\geq 1$ experts from a pool of $K$ experts and the overall utility is a modular or submodular function of the
Externí odkaz:
http://arxiv.org/abs/2305.15331
In the context of online interactive machine learning with combinatorial objectives, we extend purely submodular prior work to more general non-submodular objectives. This includes: (1) those that are additively decomposable into a sum of two terms (
Externí odkaz:
http://arxiv.org/abs/2207.03091
Autor:
Sadeghi, Omid, Fazel, Maryam
Continuous DR-submodular functions are a class of functions that satisfy the Diminishing Returns (DR) property, which implies that they are concave along non-negative directions. Existing works have studied monotone continuous DR-submodular maximizat
Externí odkaz:
http://arxiv.org/abs/2111.07990
Autor:
Fotouhi Ardakani, Amirmahdi, Anjom-Shoae, Javad, Sadeghi, Omid, Marathe, Chinmay S., Feinle-Bisset, Christine, Horowitz, Michael
Publikováno v:
In Clinical Nutrition August 2024 43(8):1941-1955
In this paper, we consider an online optimization problem over $T$ rounds where at each step $t\in[T]$, the algorithm chooses an action $x_t$ from the fixed convex and compact domain set $\mathcal{K}$. A utility function $f_t(\cdot)$ is then revealed
Externí odkaz:
http://arxiv.org/abs/2106.07836
Autor:
Shojaeian, Zahra, Ebrahimi, Zohreh, Amiri, Fatemehsadat, Esmaillzadeh, Ahmad, Sadeghi, Omid, Jahed, Seyed Adel, Esteghamati, Alireza, Ebrahimkhani, Ali
Publikováno v:
In Preventive Medicine Reports February 2024 38
Publikováno v:
In Clinical Nutrition February 2024 43(2):505-518
We study the problem of online resource allocation, where multiple customers arrive sequentially and the seller must irrevocably allocate resources to each incoming customer while also facing a procurement cost for the total allocation. Assuming reso
Externí odkaz:
http://arxiv.org/abs/2012.12457
In this paper, we consider online continuous DR-submodular maximization with linear stochastic long-term constraints. Compared to the prior work on online submodular maximization, our setting introduces the extra complication of stochastic linear con
Externí odkaz:
http://arxiv.org/abs/2005.14708
Autor:
Shirani, Mahsa, Talebi, Shokoofeh, Sadeghi, Omid, Hassanizadeh, Shirin, Askari, Gholamreza, Bagherniya, Mohammad, Sahebkar, Amirhossein
Publikováno v:
In Pharmacological Research November 2023 197