all AI news
Sample compression schemes for balls in graphs
March 26, 2024, 4:44 a.m. | J\'er\'emie Chalopin, Victor Chepoi, Fionn Mc Inerney, S\'ebastien Ratel, Yann Vax\`es
cs.LG updates on arXiv.org arxiv.org
Abstract: One of the open problems in machine learning is whether any set-family of VC-dimension $d$ admits a sample compression scheme of size $O(d)$. In this paper, we study this problem for balls in graphs. For a ball $B=B_r(x)$ of a graph $G=(V,E)$, a realizable sample for $B$ is a signed subset $X=(X^+,X^-)$ of $V$ such that $B$ contains $X^+$ and is disjoint from $X^-$. A proper sample compression scheme of size $k$ consists of a …
abstract arxiv compression cs.dm cs.lg family graph graphs machine machine learning paper sample set study type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US