Corpus ID: 211097048

# Efficient Distance Approximation for Structured High-Dimensional Distributions via Learning

@article{Bhattacharyya2020EfficientDA,
title={Efficient Distance Approximation for Structured High-Dimensional Distributions via Learning},
author={Arnab Bhattacharyya and Sutanu Gayen and Kuldeep S. Meel and N. V. Vinodchandran},
journal={ArXiv},
year={2020},
volume={abs/2002.05378}
}
• Arnab Bhattacharyya, +1 author N. V. Vinodchandran
• Published in ArXiv 2020
• Mathematics, Computer Science
• We design efficient distance approximation algorithms for several classes of structured high-dimensional distributions. Specifically, we show algorithms for the following problems: Given sample access to two Bayesian networks $P_1$ and $P_2$ over known directed acyclic graphs $G_1$ and $G_2$ having $n$ nodes and bounded in-degree, approximate $d_{tv}(P_1,P_2)$ to within additive error $\epsilon$ using $poly(n,\epsilon)$ samples and time Given sample access to two ferromagnetic Ising models… CONTINUE READING

Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

## Efficiently Learning and Sampling Interventional Distributions from Observations

• Computer Science, Mathematics
• ArXiv
• 2020

#### References

##### Publications referenced by this paper.
SHOWING 1-10 OF 42 REFERENCES

## Efficiently Learning and Sampling Interventional Distributions from Observations

• Computer Science, Mathematics
• ArXiv
• 2020

## On Testing of Uniform Samplers

• Computer Science
• AAAI
• 2019

## Learning and Testing Causal Models with Interventions

• Computer Science, Mathematics
• NeurIPS
• 2018

## The total variation distance between high-dimensional Gaussians

• Mathematics
• 2018

## Learning Graphical Models Using Multiplicative Weights

• Mathematics, Computer Science
• 2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS)
• 2017

## Testing Bayesian Networks

• Computer Science, Mathematics
• COLT
• 2017

## Testing Ising Models

• Computer Science, Mathematics
• SODA
• 2017

## Square Hellinger Subadditivity for Bayesian Networks and its Applications to Identity Testing

• Mathematics, Computer Science
• COLT
• 2016

## A Survey on Distribution Testing: Your Data is Big. But is it Blue?

• Clément L. Canonne
• Mathematics, Computer Science
• Electronic Colloquium on Computational Complexity
• 2015

## On Learning Distributions from their Samples

• Mathematics, Computer Science
• COLT
• 2015