On the curses of future and history in future-dependent value functions for off-policy evaluation

Y Zhang, N Jiang - Advances in Neural Information …, 2025 - proceedings.neurips.cc
We study off-policy evaluation (OPE) in partially observable environments with complex
observations, with the goal of develo** estimators whose guarantee avoids exponential …

Probabilistic loop synthesis from sequences of moments

M Stankovič, E Bartocci - … on Quantitative Evaluation of Systems and …, 2024 - Springer
Probabilistic program synthesis consists in automatically creating programs generating
random values adhering to specified distributions. We consider here the family of …

Testing self-reducible samplers

R Bhattacharyya, S Chakraborty, Y Pote… - Proceedings of the …, 2024 - ojs.aaai.org
Samplers are the backbone of the implementations of any randomised algorithm.
Unfortunately, obtaining an efficient algorithm to test the correctness of samplers is very hard …

Causal Learning in Biomedical Applications: A Benchmark

P Ryšavý, X He, J Mareček - arxiv preprint arxiv:2406.15189, 2024 - arxiv.org
Learning causal relationships between a set of variables is a challenging problem in
computer science. Many existing artificial benchmark datasets are based on sampling from …

Monotonicity Testing of High-Dimensional Distributions with Subcube Conditioning

D Chakrabarty, X Chen, S Ristic, C Seshadhri… - arxiv preprint arxiv …, 2025 - arxiv.org
We study monotonicity testing of high-dimensional distributions on $\{-1, 1\}^ n $ in the
model of subcube conditioning, suggested and studied by Canonne, Ron, and …

Probabilistic Loop Synthesis

M Stankovič, E Bartoccid - … of Systems and Formal Modeling and …, 2024 - books.google.com
Probabilistic program synthesis consists in automatically creating programs generating
random values adhering to specified dis-tributions. We consider here the family of …