no code implementations • 17 Sep 2023 • Arnab Bhattacharyya, Sutanu Gayen, Kuldeep S. Meel, Dimitrios Myrisiotis, A. Pavan, N. V. Vinodchandran
In particular, we present an efficient, structure-preserving reduction from relative approximation of TV distance to probabilistic inference over directed graphical models.
no code implementations • 25 Jul 2021 • Arnab Bhattacharyya, Sutanu Gayen, Saravanan Kandasamy, Vedant Raval, N. V. Vinodchandran
For sets $\mathbf{X},\mathbf{Y}\subseteq \mathbf{V}$, and setting ${\bf x}$ to $\mathbf{X}$, let $P_{\bf x}(\mathbf{Y})$ denote the interventional distribution on $\mathbf{Y}$ with respect to an intervention ${\bf x}$ to variables ${\bf x}$.
1 code implementation • 22 Jul 2021 • Arnab Bhattacharyya, Davin Choo, Rishikesh Gajjala, Sutanu Gayen, Yuhao Wang
We also study a couple of new algorithms for the problem: - BatchAvgLeastSquares takes the average of several batches of least squares solutions at each node, so that one can interpolate between the batch size and the number of batches.
no code implementations • 29 Dec 2020 • Arnab Bhattacharyya, Sutanu Gayen, Saravanan Kandasamy, N. V. Vinodchandran
We study the problems of identity and closeness testing of $n$-dimensional product distributions.
no code implementations • 9 Nov 2020 • Arnab Bhattacharyya, Sutanu Gayen, Eric Price, N. V. Vinodchandran
For a distribution $P$ on $\Sigma^n$ and a tree $T$ on $n$ nodes, we say $T$ is an $\varepsilon$-approximate tree for $P$ if there is a $T$-structured distribution $Q$ such that $D(P\;||\;Q)$ is at most $\varepsilon$ more than the best possible tree-structured distribution for $P$.
no code implementations • NeurIPS 2020 • Arnab Bhattacharyya, Sutanu Gayen, Kuldeep S. Meel, N. V. Vinodchandran
We design efficient distance approximation algorithms for several classes of structured high-dimensional distributions.
no code implementations • ICML 2020 • Arnab Bhattacharyya, Sutanu Gayen, Saravanan Kandasamy, Ashwin Maran, N. V. Vinodchandran
Assuming that $G$ has bounded in-degree, bounded c-components ($k$), and that the observational distribution is identifiable and satisfies certain strong positivity condition, we give an algorithm that takes $m=\tilde{O}(n\epsilon^{-2})$ samples from $P$ and $O(mn)$ time, and outputs with high probability a description of a distribution $\hat{P}$ such that $d_{\mathrm{TV}}(P_x, \hat{P}) \leq \epsilon$, and: 1.