pith. sign in

Since the game is finite (both players’ strategy sets are the finite setV⊆ H), von Neumann’s minimax theorem applies (von Neumann, 1928; Cesa-Bianchi and Lugosi, 2006)

In other words, for every adversary strategyqthere exists a learner strategyp(such asp=q) satisfyingPayoff(p, q)≤ 1 2, hence themaximinvalue of the game is at most 1 2 · 1928

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Learning from Equivalence Queries, Revisited

cs.LG · 2026-04-06 · unverdicted · novelty 6.0

Tight bounds on the number of rounds are obtained for learning from equivalence queries under symmetric counterexample generators in full-information and bandit settings.

citing papers explorer

Showing 1 of 1 citing paper.

  • Learning from Equivalence Queries, Revisited cs.LG · 2026-04-06 · unverdicted · none · ref 3

    Tight bounds on the number of rounds are obtained for learning from equivalence queries under symmetric counterexample generators in full-information and bandit settings.