3 papers
math.CO2026
-Polytopes with Exponentially Small Edge Expansion
Xiongxin Yang
We present a construction of a family of -polytopes whose edge expansion decreases exponentially with the dimension, which disproves the Mihail-Vazirani conjecture that the gr…
cs.LG2026
Learning under Locally Sampleable Graphical Models
Weiming Feng, Xiongxin Yang, Yixiao Yu +1
The problem of learning constant-depth circuits holds profound implications for computational learning theory. In a seminal result, by introducing the low-degree algorithm, Linial,…
cs.DS2025
Learning CNF formulas from uniform random solutions in the local lemma regime
Weiming Feng, Xiongxin Yang, Yixiao Yu +1
We study the problem of learning a -variables -CNF formula from its i.i.d. uniform random solutions, which is equivalent to learning a Boolean Markov random field (MRF)…