Zobrazeno 1 - 10
of 62
pro vyhledávání: '"Hamidi, Nima"'
Autor:
Kermanshahi, Nazanin, Hamidi, Nima, Weisberg, Jake, Beg, Usman, Dabrowski, Michael, Padmanaban, Varun, Betz, Jeannette, Mansouri, Alireza
Publikováno v:
In World Neurosurgery March 2024 183:e613-e624
Autor:
Hamidi, Nima, Bayati, Mohsen
In this note, we introduce a general version of the well-known elliptical potential lemma that is a widely used technique in the analysis of algorithms in sequential learning and decision-making problems. We consider a stochastic linear bandit settin
Externí odkaz:
http://arxiv.org/abs/2102.07987
Autor:
Hamidi, Nima, Bayati, Mohsen
This paper studies the stochastic linear bandit problem, where a decision-maker chooses actions from possibly time-dependent sets of vectors in $\mathbb{R}^d$ and receives noisy rewards. The objective is to minimize regret, the difference between the
Externí odkaz:
http://arxiv.org/abs/2006.06790
We investigate a Bayesian $k$-armed bandit problem in the \emph{many-armed} regime, where $k \geq \sqrt{T}$ and $T$ represents the time horizon. Initially, and aligned with recent literature on many-armed bandit problems, we observe that subsampling
Externí odkaz:
http://arxiv.org/abs/2002.10121
Autor:
Hamidi, Nima, Bayati, Mohsen
Recent growing adoption of experimentation in practice has led to a surge of attention to multiarmed bandits as a technique to reduce the opportunity cost of online experiments. In this setting, a decision-maker sequentially chooses among a set of gi
Externí odkaz:
http://arxiv.org/abs/2002.05152
Convolutional neural networks (CNN) recently gained notable attraction in a variety of machine learning tasks: including music classification and style tagging. In this work, we propose implementing intermediate connections to the CNN architecture to
Externí odkaz:
http://arxiv.org/abs/1906.06746
Autor:
Hamidi, Nima, Bayati, Mohsen
Publikováno v:
Journal of Machine Learning Research (JMLR), 2022
In this paper, we study the trace regression when a matrix of parameters B* is estimated via the convex relaxation of a rank-regularized regression or via regularized non-convex optimization. It is known that these estimators satisfy near-optimal err
Externí odkaz:
http://arxiv.org/abs/1904.08576
Publikováno v:
In World Neurosurgery August 2021 152:189-197
Autor:
Beg, Usman, Snyder, Brianna Michelle, Madhani, Sarosh Irfan, Hamidi, Nima, Padmanaban, Varun, Tuanquin, Leonard C., Kruser, Timothy J., Connor, James, Mansouri, Alireza
Publikováno v:
In World Neurosurgery July 2021 151:e839-e856
Autor:
Massaad, Elie, Hamidi, Nima, Goetz, Jacalynn, Padmanaban, Varun, Mau, Christine, Tsang, Derek, de Moraes, Fabio Y., Chung, Caroline, Zacharia, Brad E., Mansouri, Alireza
Publikováno v:
In World Neurosurgery February 2021 146:322-331