Zobrazeno 1 - 7
of 7
pro vyhledávání: '"SHIDANI, AMITIS"'
Autor:
Ramapuram, Jason, Danieli, Federico, Dhekane, Eeshan, Weers, Floris, Busbridge, Dan, Ablin, Pierre, Likhomanenko, Tatiana, Digani, Jagrit, Gu, Zijin, Shidani, Amitis, Webb, Russ
Attention is a key part of the transformer architecture. It is a sequence-to-sequence mapping that transforms each sequence element into a weighted sum of values. The weights are typically obtained as the softmax of dot products between keys and quer
Externí odkaz:
http://arxiv.org/abs/2409.04431
Autor:
Shidani, Amitis, Hjelm, Devon, Ramapuram, Jason, Webb, Russ, Dhekane, Eeshan Gunesh, Busbridge, Dan
Contrastive learning typically matches pairs of related views among a number of unrelated negative views. Views can be generated (e.g. by augmentations) or be observed. We investigate matching when there are more than two related views which we call
Externí odkaz:
http://arxiv.org/abs/2403.05490
Autor:
Shidani, Amitis, Vakili, Sattar
We consider regret minimization in a general collaborative multi-agent multi-armed bandit model, in which each agent faces a finite set of arms and may communicate with other agents through a central controller. The optimal arm for each agent in this
Externí odkaz:
http://arxiv.org/abs/2312.09674
Publikováno v:
AAAI 2024 Workshop on Recommendation Ecosystems: Modeling, Optimization and Incentive Design
We study the ranking problem in generalized linear bandits. At each time, the learning agent selects an ordered list of items and observes stochastic outcomes. In recommendation systems, displaying an ordered list of the most attractive items is not
Externí odkaz:
http://arxiv.org/abs/2207.00109
Publikováno v:
Proceedings of the 35th Conference on Learning Theory, PMLR 178:4212-4257, 2022
This work discusses how to derive upper bounds for the expected generalisation error of supervised learning algorithms by means of the chaining technique. By developing a general theoretical framework, we establish a duality between generalisation bo
Externí odkaz:
http://arxiv.org/abs/2203.00977
We study a ranking problem in the contextual multi-armed bandit setting. A learning agent selects an ordered list of items at each time step and observes stochastic outcomes for each position. In online recommendation systems, showing an ordered list
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::34c4fcbdb1768e579c079a2b89ac780c
Autor:
AASHTAB, ARMAN1 armanpmsht@gmail.com, AKBARI, SAIEED1 s_akbari@sharif.edu, GHANBARI, MARYAM1 marghanbari@gmail.com, SHIDANI, AMITIS2 amitis.shidani@gmail.com
Publikováno v:
Discussiones Mathematicae: Graph Theory. 2023, Vol. 43 Issue 2, p385-399. 15p.
