7 citations · 36 across the 24 of their papers we have counts for
6 papers · 1 filter
Improved Support Recovery in Universal One-bit Compressed Sensing
Namiko Matsumoto, Arya Mazumdar, Soumyabrata Pal
One-bit compressed sensing (1bCS) is an extremely quantized signal acquisition method that has been proposed and studied rigorously in the past decade. In 1bCS, linear samples of a…
Sample-Efficient Personalization: Modeling User Parameters as Low Rank Plus Sparse Components
Soumyabrata Pal, Prateek Varshney, Prateek Jain +5
Personalization of machine learning (ML) predictions for individual users/domains/enterprises is critical for practical recommendation systems. Standard personalization approaches…
Online Low Rank Matrix Completion
Prateek Jain, Soumyabrata Pal
We study the problem of {\em online} low-rank matrix completion with users, items and rounds. In each round, the algorithm recommends one ite…
Community Recovery in the Geometric Block Model
Sainyam Galhotra, Arya Mazumdar, Soumyabrata Pal +1
To capture the inherent geometric features of many community detection problems, we propose to use a new random graph model of communities that we call a Geometric Block Model. The…
On Learning Mixture of Linear Regressions in the Non-Realizable Setting
Avishek Ghosh, Arya Mazumdar, Soumyabrata Pal +1
While mixture of linear regressions (MLR) is a well-studied topic, prior works usually do not analyze such models for prediction error. In fact, {\em prediction} and {\em loss} are…
Support Recovery in Mixture Models with Sparse Parameters
Arya Mazumdar, Soumyabrata Pal
Mixture models are widely used to fit complex and multimodal datasets. In this paper we study mixtures with high dimensional sparse latent parameter vectors and consider the proble…