Zobrazeno 1 - 10
of 234
pro vyhledávání: '"Mazumdar, Arya"'
Autor:
Li, Xiaxin, Mazumdar, Arya
In Group Testing, the objective is to identify K defective items out of N, K<
Externí odkaz:
http://arxiv.org/abs/2410.14566
In this paper, we study the data-dependent convergence and generalization behavior of gradient methods for neural networks with smooth activation. Our first result is a novel bound on the excess risk of deep networks trained by the logistic loss, via
Externí odkaz:
http://arxiv.org/abs/2410.10024
Recovering the underlying clustering of a set $U$ of $n$ points by asking pair-wise same-cluster queries has garnered significant interest in the last decade. Given a query $S \subset U$, $|S|=2$, the oracle returns yes if the points are in the same
Externí odkaz:
http://arxiv.org/abs/2409.10908
We study transfer learning for estimation in latent variable network models. In our setting, the conditional edge probability matrices given the latent variables are represented by $P$ for the source and $Q$ for the target. We wish to estimate $Q$ gi
Externí odkaz:
http://arxiv.org/abs/2406.03437
Autor:
Ghosh, Avishek, Mazumdar, Arya
Mixed linear regression is a well-studied problem in parametric statistics and machine learning. Given a set of samples, tuples of covariates and labels, the task of mixed linear regression is to find a small list of linear relationships that best fi
Externí odkaz:
http://arxiv.org/abs/2406.01149
Autor:
Matsumoto, Namiko, Mazumdar, Arya
In 1-bit compressed sensing, the aim is to estimate a $k$-sparse unit vector $x\in S^{n-1}$ within an $\epsilon$ error (in $\ell_2$) from minimal number of linear measurements that are quantized to just their signs, i.e., from measurements of the for
Externí odkaz:
http://arxiv.org/abs/2310.08019
Motivated by the need for communication-efficient distributed learning, we investigate the method for compressing a unit norm vector into the minimum number of bits, while still allowing for some acceptable level of distortion in recovery. This probl
Externí odkaz:
http://arxiv.org/abs/2307.07941
Autor:
Hsu, Daniel, Mazumdar, Arya
The logistic regression model is one of the most popular data generation model in noisy binary classification problems. In this work, we study the sample complexity of estimating the parameters of the logistic regression model up to a given $\ell_2$
Externí odkaz:
http://arxiv.org/abs/2307.04191
We propose a first-order method for convex optimization, where instead of being restricted to the gradient from a single parameter, gradients from multiple parameters can be used during each step of gradient descent. This setup is particularly useful
Externí odkaz:
http://arxiv.org/abs/2302.03161
Autor:
Yu, Xiaofan, Cherkasova, Ludmila, Vardhan, Harsh, Zhao, Quanling, Ekaireb, Emily, Zhang, Xiyuan, Mazumdar, Arya, Rosing, Tajana
Federated Learning (FL) has gained increasing interest in recent years as a distributed on-device learning paradigm. However, multiple challenges remain to be addressed for deploying FL in real-world Internet-of-Things (IoT) networks with hierarchies
Externí odkaz:
http://arxiv.org/abs/2301.06646