mlsanityData to 14 Oct 2026

Expressivity of Contradiction Graphs

arXiv 2605.20434 ↗First posted 19 May 2026stat.ML cs.DM cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We study the contradiction graphs associated with a binary concept class. For a class Hsubseteq0,1X, the order-m contradiction graph Gm(H) has as vertices the H-realizable labeled sequences of length m, with two vertices adjacent when the two sequences assign opposite labels to some common domain point. First, we identify a graph-theoretic property that determines the threshold predicate operatornameVCdim(H)≥ m. Consequently, the sequence (Gm(H))m≥1 determines the exact VC dimension and, in particular, distinguishes finite from infinite VC dimension, answering a question posed by Alon et al. (2024). We then generalize this result by proving that the sequence of contradiction graphs determines, up to signed relabeling, the realizable datasets of any fixed length. Thus, any learning-theoretic property determined by the realizable datasets of a fixed length and invariant under signed relabeling can be recovered from the contradiction graph sequence. As an application, we explicitly provide a characterization of Littlestone dimension.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 6 of its 27 references that are in the map. First posted on arXiv 19 May 2026.

Builds on

6 of 27 references.

References · 6

  1. 2014Private Learning and Sanitization: Pure vs. Approximate Differential Privacycited by 63
  2. 2014Sample Complexity Bounds on Differentially Private Learning via Communication Complexitycited by 31
  3. 2020Sample-efficient proper PAC learning with approximate differential privacycited by 29
  4. 2023The Bayesian Stability Zoocited by 13
  5. 2023A Unified Characterization of Private Learnability via Graph Theorycited by 5
  6. 2024Private PAC Learning May be Harder than Online Learningcited by 4

Built on by

Not cited yet.