Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Handina, Tinashe"'
The combination of the Bayesian game and learning has a rich history, with the idea of controlling a single agent in a system composed of multiple agents with unknown behaviors given a set of types, each specifying a possible behavior for the other a
Externí odkaz:
http://arxiv.org/abs/2411.07679
Autor:
Handina, Tinashe, Mazumdar, Eric
The deployment of ever-larger machine learning models reflects a growing consensus that the more expressive the model class one optimizes over$\unicode{x2013}$and the more data one has access to$\unicode{x2013}$the more one can improve performance. A
Externí odkaz:
http://arxiv.org/abs/2402.07588
We consider the problem of convex function chasing with black-box advice, where an online decision-maker aims to minimize the total cost of making and switching between decisions in a normed vector space, aided by black-box advice such as the decisio
Externí odkaz:
http://arxiv.org/abs/2206.11780
Autor:
Sehwag, Vikash, Mahloujifar, Saeed, Handina, Tinashe, Dai, Sihui, Xiang, Chong, Chiang, Mung, Mittal, Prateek
While additional training data improves the robustness of deep neural networks against adversarial examples, it presents the challenge of curating a large number of specific real-world samples. We circumvent this challenge by using additional data fr
Externí odkaz:
http://arxiv.org/abs/2104.09425