AEW achieves the excess risk bound T log(M)/(n+1) in expectation for sufficiently large constant temperature T under i.i.d. random design and bounded L-Lipschitz μ-strongly convex losses.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.ST 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Aggregation with Exponential Weights is Optimal in Expectation
AEW achieves the excess risk bound T log(M)/(n+1) in expectation for sufficiently large constant temperature T under i.i.d. random design and bounded L-Lipschitz μ-strongly convex losses.