Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Learning CNF Formulas from Uniform Random Solutions: Near-Tight Sample Complexity for Valiant's Algorithm
Weiming Feng, Yixiao Yu, Yiyao Zhang
We revisit Valiant's algorithm (Commun. ACM'84) for learning -variable CNF formulas with clause size and variable degree from i.i.d. uniform random solutions in the loca…
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,…