Rishiraj Bhattacharyya — accepted AI-conference papers

2026

Instance Dependent Testing of Samplers Using Interval Conditioning

Rishiraj Bhattacharyya, Sourav Chakraborty, Yash Pote, Uddalok Sarkar, Sayantan Sen

AAAI 2026technical

Sampling algorithms play a pivotal role in probabilistic AI. However, verifying if a sampler program indeed samples from the claimed distribution is a notoriously hard problem. Provably correct testers like Barbarik,Teq,Flash, Cubeprobe for testing of different kinds of samplers were proposed only

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Testing Self-Reducible Samplers

Rishiraj Bhattacharyya, Sourav Chakraborty, Yash Pote, Uddalok Sarkar, Sayantan Sen

AAAI 2024technical

Samplers are the backbone of the implementations of any randomized algorithm. Unfortunately, obtaining an efficient algorithm to test the correctness of samplers is very hard to find. Recently, in a series of works, testers like Barbarik, Teq, Flash for testing of some particular kinds of samplers,…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗