Zobrazeno 1 - 10
of 203
pro vyhledávání: '"Sahai, Anant"'
Autor:
Campbell, Ryan, Lojo, Nelson, Viswanadha, Kesava, Tryggestad, Christoffer Grondal, Sun, Derrick Han, Vijapurapu, Sriteja, Rolfsen, August, Sahai, Anant
In-Context Learning (ICL) is a phenomenon where task learning occurs through a prompt sequence without the necessity of parameter updates. ICL in Multi-Headed Attention (MHA) with absolute positional embedding has been the focus of more study than ot
Externí odkaz:
http://arxiv.org/abs/2411.03945
Autor:
Wu, David X., Sahai, Anant
The classic teacher-student model in machine learning posits that a strong teacher supervises a weak student to improve the student's capabilities. We instead consider the inverted situation, where a weak teacher supervises a strong student with impe
Externí odkaz:
http://arxiv.org/abs/2410.04638
Simple function classes have emerged as toy problems to better understand in-context-learning in transformer-based architectures used for large language models. But previously proposed simple function classes like linear regression or multi-layer-per
Externí odkaz:
http://arxiv.org/abs/2407.19346
Precise Asymptotic Generalization for Multiclass Classification with Overparameterized Linear Models
Autor:
Wu, David X., Sahai, Anant
We study the asymptotic generalization of an overparameterized linear model for multiclass classification under the Gaussian covariates bi-level model introduced in Subramanian et al.~'22, where the number of data points, features, and classes all gr
Externí odkaz:
http://arxiv.org/abs/2306.13255
Via an overparameterized linear model with Gaussian features, we provide conditions for good generalization for multiclass classification of minimum-norm interpolating solutions in an asymptotic setting where both the number of underlying features an
Externí odkaz:
http://arxiv.org/abs/2206.01399
State-of-the-art deep learning classifiers are heavily overparameterized with respect to the amount of training examples and observed to generalize well on "clean" data, but be highly susceptible to infinitesmal adversarial perturbations. In this pap
Externí odkaz:
http://arxiv.org/abs/2109.13215
We study the limiting behavior of the mixed strategies that result from optimal no-regret learning strategies in a repeated game setting where the stage game is any 2 by 2 competitive game. We consider optimal no-regret algorithms that are mean-based
Externí odkaz:
http://arxiv.org/abs/2012.02125
Autor:
Muthukumar, Vidya, Narang, Adhyyan, Subramanian, Vignesh, Belkin, Mikhail, Hsu, Daniel, Sahai, Anant
Publikováno v:
Journal of Machine Learning Research, 22(222):1-69, 2021
We compare classification and regression tasks in an overparameterized linear model with Gaussian features. On the one hand, we show that with sufficient overparameterization all training points are support vectors: solutions obtained by least-square
Externí odkaz:
http://arxiv.org/abs/2005.08054
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
We examine the problem of learning to cooperate in the context of wireless communication. In our setting, two agents must learn modulation schemes that enable them to communicate across a power-constrained additive white Gaussian noise channel. We in
Externí odkaz:
http://arxiv.org/abs/1910.09630