16 citations · 30 across the 12 of their papers we have counts for
14 papers
Algorithms and Hardness for Estimating Statistical Similarity
Arnab Bhattacharyya, Sutanu Gayen, Kuldeep S. Meel +3
We introduce and study the computational problem of determining statistical similarity between probability distributions. For distributions and over a finite sample space,…
Computational Explorations of Total Variation Distance
Arnab Bhattacharyya, Sutanu Gayen, Kuldeep S. Meel +3
We investigate some previously unexplored (or underexplored) computational aspects of total variation (TV) distance. First, we give a simple deterministic polynomial-time algorithm…
Efficient Sample-optimal Learning of Gaussian Tree Models via Sample-optimal Testing of Gaussian Mutual Information
Sutanu Gayen, Sanket Kale, Sayantan Sen
Learning high-dimensional distributions is a significant challenge in machine learning and statistics. Classical research has mostly concentrated on asymptotic analysis of such dat…
Learnability of Parameter-Bounded Bayes Nets
Arnab Bhattacharyya, Davin Choo, Sutanu Gayen +1
Bayes nets are extensively used in practice to efficiently represent joint probability distributions over a set of random variables and capture dependency relations. In a seminal p…
Total Variation Distance for Product Distributions is -Complete
Arnab Bhattacharyya, Sutanu Gayen, Kuldeep S. Meel +3
We show that computing the total variation distance between two product distributions is -complete. This is in stark contrast with other distance measures such as Kul…
Distribution Learning Meets Graph Structure Sampling
Arnab Bhattacharyya, Sutanu Gayen, Philips George John +2
This work establishes a novel link between the problem of PAC-learning high-dimensional graphical models and the task of (efficient) counting and sampling of graph structures, usin…
Total Variation Distance Meets Probabilistic Inference
Arnab Bhattacharyya, Sutanu Gayen, Kuldeep S. Meel +3
In this paper, we establish a novel connection between total variation (TV) distance estimation and probabilistic inference. In particular, we present an efficient, structure-prese…
On Approximating Total Variation Distance
Arnab Bhattacharyya, Sutanu Gayen, Kuldeep S. Meel +3
Total variation distance (TV distance) is a fundamental notion of distance between probability distributions. In this work, we introduce and study the problem of computing the TV d…
Efficient inference of interventional distributions
Arnab Bhattacharyya, Sutanu Gayen, Saravanan Kandasamy +2
We consider the problem of efficiently inferring interventional distributions in a causal Bayesian network from a finite number of observations. Let be a causal model…
Learning Sparse Fixed-Structure Gaussian Bayesian Networks
Arnab Bhattacharyya, Davin Choo, Rishikesh Gajjala +2
Gaussian Bayesian networks (a.k.a. linear Gaussian structural equation models) are widely used to model causal interactions among continuous variables. In this work, we study the p…
Testing Product Distributions: A Closer Look
Arnab Bhattacharyya, Sutanu Gayen, Saravanan Kandasamy +1
We study the problems of identity and closeness testing of -dimensional product distributions. Prior works by Canonne, Diakonikolas, Kane and Stewart (COLT 2017) and Daskalakis…
Near-Optimal Learning of Tree-Structured Distributions by Chow-Liu
Arnab Bhattacharyya, Sutanu Gayen, Eric Price +1
We provide finite sample guarantees for the classical Chow-Liu algorithm (IEEE Trans.~Inform.~Theory, 1968) to learn a tree-structured graphical model of a distribution. For a dist…
Efficient Distance Approximation for Structured High-Dimensional Distributions via Learning
Arnab Bhattacharyya, Sutanu Gayen, Kuldeep S. Meel +1
We design efficient distance approximation algorithms for several classes of structured high-dimensional distributions. Specifically, we show algorithms for the following problems:…
Learning and Sampling of Atomic Interventions from Observations
Arnab Bhattacharyya, Sutanu Gayen, Saravanan Kandasamy +2
We study the problem of efficiently estimating the effect of an intervention on a single variable (atomic interventions) using observational samples in a causal Bayesian network. O…