Online algorithms achieve adaptive calibration bounds of Õ(√T + (TC)^{1/3}) for ℓ1 error and Õ((1+C)^{1/3}) for ℓ2 and pseudo-KL error, matching stationary and adversarial extremes via epoch scheduling and non-uniform prediction partitioning.
Title resolution pending
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
-
Adaptive Calibration in Non-Stationary Environments
Online algorithms achieve adaptive calibration bounds of Õ(√T + (TC)^{1/3}) for ℓ1 error and Õ((1+C)^{1/3}) for ℓ2 and pseudo-KL error, matching stationary and adversarial extremes via epoch scheduling and non-uniform prediction partitioning.