arXiv Machine Learning

The Dimension of Nonterminating Resampling Computations

arXiv:2607. 17469v1 Announce Type: cross Abstract: A randomized algorithm may terminate almost surely even though exceptional random tapes make it run forever.

arXiv Machine Learning
Jul 9

The Optimal Sample Complexity of Learning Autoregressive Chain-of-Thought

arXiv:2607. 07423v1 Announce Type: new Abstract: We prove that, in the realizable PAC setting, the sample complexity of exact-trace learning for full autoregressive Chain-of-Thought traces is upper bounded by the standard multiclass rate of the local next-token class, where this rate is governed by the Daniely--Shalev-Shwartz dimension.

By Zhiyuan Li
arXiv AI
Jul 28

Formalizing Flag Algebras in Lean

arXiv:2607. 23500v1 Announce Type: cross Abstract: Razborov's flag algebra method is a powerful tool for proving asymptotic inequalities in extremal graph theory, often reducing the task to finding a finite certificate by semidefinite programming.

By Gyeongwon Jeong, Seonghun Park, Jihoon Hyun, Sang-il Oum, Hongseok Yang
arXiv Machine Learning
Aug 10

Sub-Quadratic Bisimulation Metrics via Approximate Nearest Neighbors: Coverage-Augmented Guarantees and Computable Two-Sided Certificates

arXiv:2608. 06762v1 Announce Type: new Abstract: Bisimulation metrics quantify behavioral similarity in Markov decision processes, but their Wasserstein fixed-point operator updates every state pair and incurs quadratic pairwise work.

By Ibne Farabi Shihab, Joyanta Jyoti Mondal
Hugging Face Trending Papers
Aug 3

Optimal Unambiguous DNFs and Alon-Saks-Seymour

We construct unambiguous DNFs having width $O(n)$ but $0$-certificate complexity $Ω(n^2)$. By utilizing the special structure of these DNFs, we prove a lifting theorem with a constant-sized gadget that lifts the DNF to a communication problem, while losslessly translating the separation in certificate complexity to a separation in communication complexity.