Presents a deterministic minimax-optimal multicalibration algorithm and its generalization to outcome indistinguishability and omniprediction, resolving open questions on randomization necessity.
On general minimax theorems
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
The direct exponent in binary quantum state discrimination for correlation detection equals the doubly minimized Petz Renyi mutual information for alpha in (1/2,1), while the strong converse exponent equals the doubly minimized sandwiched version for alpha in (1,infty).
citing papers explorer
-
Optimal Deterministic Multicalibration and Omniprediction
Presents a deterministic minimax-optimal multicalibration algorithm and its generalization to outcome indistinguishability and omniprediction, resolving open questions on randomization necessity.
-
Doubly minimized Petz and sandwiched Renyi mutual information: Operational interpretation from binary quantum state discrimination
The direct exponent in binary quantum state discrimination for correlation detection equals the doubly minimized Petz Renyi mutual information for alpha in (1/2,1), while the strong converse exponent equals the doubly minimized sandwiched version for alpha in (1,infty).