Derives first lower bound on γ_t for mean-based algorithms in unknown-horizon bandit settings, proposes two new algorithms, and shows some are also no-regret.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Projective strategies enjoy key properties in the usual CHSH game but lose them in its dynamic variant when viewed through team-theoretic solution concepts.
Strategic agents can achieve high-harm outcomes via low-capacity channels by concentrating residual capacity on high-impact predicates of confidential data, so leakage bounds need not bound worst-case harm.
citing papers explorer
-
Mean-based algorithms: A lower bound and regret
Derives first lower bound on γ_t for mean-based algorithms in unknown-horizon bandit settings, proposes two new algorithms, and shows some are also no-regret.
-
Nonlocal Teams and Information Structures
Projective strategies enjoy key properties in the usual CHSH game but lose them in its dynamic variant when viewed through team-theoretic solution concepts.
-
A Note on the Strategic Confinement Problem
Strategic agents can achieve high-harm outcomes via low-capacity channels by concentrating residual capacity on high-impact predicates of confidential data, so leakage bounds need not bound worst-case harm.