Zobrazeno 1 - 10
of 258
pro vyhledávání: '"Heidari Mohsen"'
Autor:
Heidari Mohsen, Faramarzi Vahid, Sharifi Zohreh, Hashemi Mahdieh, Bahadori-Haghighi Shahram, Janjan Babak, Abbott Derek
Publikováno v:
Nanophotonics, Vol 10, Iss 13, Pp 3451-3463 (2021)
The reversible insulating-to-conducting phase transition (ICPT) of vanadium dioxide (VO2) makes it a versatile candidate for the implementation of integrated optical devices. In this paper, a bi-functional in-line optical device based on a four-layer
Externí odkaz:
https://doaj.org/article/f8653597f15d49ceafdd84ff1897c857
Autor:
Heidari, Mohsen, Szpankowski, Wojciech
This paper studies quantum supervised learning for classical inference from quantum states. In this model, a learner has access to a set of labeled quantum samples as the training set. The objective is to find a quantum measurement that predicts the
Externí odkaz:
http://arxiv.org/abs/2408.12683
Hybrid quantum-classical optimization and learning strategies are among the most promising approaches to harnessing quantum information or gaining a quantum advantage over classical methods. However, efficient estimation of the gradient of the object
Externí odkaz:
http://arxiv.org/abs/2404.05108
Autor:
Heidari, Mohsen, Naved, Mobasshir A, Honjani, Zahra, Xie, Wenbo, Grama, Arjun Jacob, Szpankowski, Wojciech
Gradient-based optimizers have been proposed for training variational quantum circuits in settings such as quantum neural networks (QNNs). The task of gradient estimation, however, has proven to be challenging, primarily due to distinctive quantum fe
Externí odkaz:
http://arxiv.org/abs/2310.06935
The reliability function of a channel is the maximum achievable exponential rate of decay of the error probability as a function of the transmission rate. In this work, we derive bounds on the reliability function of discrete memoryless multiple-acce
Externí odkaz:
http://arxiv.org/abs/2306.06796
Autor:
Heidari, Mohsen, Szpankowski, Wojciech
Many conventional learning algorithms rely on loss functions other than the natural 0-1 loss for computational efficiency and theoretical tractability. Among them are approaches based on absolute loss (L1 regression) and square loss (L2 regression).
Externí odkaz:
http://arxiv.org/abs/2303.04859
Autor:
Shirani, Farhad, Heidari, Mohsen
The non-interactive source simulation (NISS) scenario is considered. In this scenario, a pair of distributed agents, Alice and Bob, observe a distributed binary memoryless source $(X^d,Y^d)$ generated based on joint distribution $P_{X,Y}$. The agents
Externí odkaz:
http://arxiv.org/abs/2212.09239
Autor:
Hemati, Sara1 (AUTHOR), Heidari, Mohsen2 (AUTHOR), Momenbeik, Fariborz3 (AUTHOR), khodabakhshi, Abbas1 (AUTHOR), Fadaei, Abdolmajid1 (AUTHOR), Farhadkhani, Marzieh4 (AUTHOR), Mohammadi-Moghadam, Fazel1 (AUTHOR) fm.moghadam@skums.ac.ir
Publikováno v:
PLoS ONE. 9/6/2024, Vol. 19 Issue 9, p1-15. 15p.
Publikováno v:
Published in Transactions on Machine Learning Research (08/2023). URL: https://openreview.net/forum?id=H1SekypXKA
We study the problem of sequential prediction and online minimax regret with stochastically generated features under a general loss function. We introduce a notion of expected worst case minimax regret that generalizes and encompasses prior known min
Externí odkaz:
http://arxiv.org/abs/2209.04417
Publikováno v:
Advances in Neural Information Processing Systems 35 (NeurIPS 2022)
We study the sequential general online regression, known also as the sequential probability assignments, under logarithmic loss when compared against a broad class of experts. We focus on obtaining tight, often matching, lower and upper bounds for th
Externí odkaz:
http://arxiv.org/abs/2205.03728