Tight bounds on the number of rounds are obtained for learning from equivalence queries under symmetric counterexample generators in full-information and bandit settings.
ProofWe first establish the following symmetry inequality for pure strategies: for allh, c∈V, Payoff(h, c) + Payoff(c, h)≤1.(7) Fixh, c∈V
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning from Equivalence Queries, Revisited
Tight bounds on the number of rounds are obtained for learning from equivalence queries under symmetric counterexample generators in full-information and bandit settings.