Zobrazeno 1 - 10
of 3 965
pro vyhledávání: '"Vaswani, A"'
We study how representation learning can improve the learning efficiency of contextual bandit problems. We study the setting where we play T contextual linear bandits with dimension d simultaneously, and these T bandit tasks collectively share a comm
Externí odkaz:
http://arxiv.org/abs/2410.02068
Signal Processing (SP) and Machine Learning (ML) rely on good math and coding knowledge, in particular, linear algebra, probability, and complex numbers. A good grasp of these relies on scalar algebra learned in middle school. The ability to understa
Externí odkaz:
http://arxiv.org/abs/2409.17304
Autor:
Singh, Ankit Pratap, Vaswani, Namrata
This letter studies the AltGDmin algorithm for solving the noisy low rank column-wise sensing (LRCS) problem. Our sample complexity guarantee improves upon the best existing one by a factor $\max(r, \log(1/\epsilon))/r$ where $r$ is the rank of the u
Externí odkaz:
http://arxiv.org/abs/2409.08384
We consider (stochastic) softmax policy gradient (PG) methods for bandits and tabular Markov decision processes (MDPs). While the PG objective is non-concave, recent research has used the objective's smoothness and gradient domination properties to a
Externí odkaz:
http://arxiv.org/abs/2405.13136
Autor:
Abbasi, Ahmed Ali, Vaswani, Namrata
In this work, we develop and analyze a Gradient Descent (GD) based solution, called Alternating GD and Minimization (AltGDmin), for efficiently solving the low rank matrix completion (LRMC) in a federated setting. LRMC involves recovering an $n \time
Externí odkaz:
http://arxiv.org/abs/2405.06569
Inverse optimization involves inferring unknown parameters of an optimization problem from known solutions and is widely used in fields such as transportation, power systems, and healthcare. We study the contextual inverse optimization setting that u
Externí odkaz:
http://arxiv.org/abs/2402.17890
Stochastic heavy ball momentum (SHB) is commonly used to train machine learning models, and often provides empirical improvements over stochastic gradient descent. By primarily focusing on strongly-convex quadratics, we aim to better understand the t
Externí odkaz:
http://arxiv.org/abs/2401.06738
Autor:
Babu, Silpa, Vaswani, Namrata
This paper focuses studies the following low rank + sparse (LR+S) column-wise compressive sensing problem. We aim to recover an $n \times q$ matrix, $\X^* =[ \x_1^*, \x_2^*, \cdots , \x_q^*]$ from $m$ independent linear projections of each of its $q$
Externí odkaz:
http://arxiv.org/abs/2311.03824
Autor:
Singh, Ankit Pratap, Vaswani, Namrata
This work considers two related learning problems in a federated attack prone setting: federated principal components analysis (PCA) and federated low rank column-wise sensing (LRCS). The node attacks are assumed to be Byzantine which means that the
Externí odkaz:
http://arxiv.org/abs/2309.14512
Autor:
Vaswani, Namrata
Publikováno v:
IEEE Transactions on Information Theory, 2024
This note provides a significantly simpler and shorter proof of our sample complexity guarantee for solving the low rank column-wise sensing problem using the Alternating Gradient Descent (GD) and Minimization (AltGDmin) algorithm. AltGDmin was devel
Externí odkaz:
http://arxiv.org/abs/2306.17782