A Bregman divergence approach yields a unified calibeating framework for general proper losses, delivering U-calibration and logarithmic regret for Tsallis losses with weaker dimension dependence than prior work.
Biometrika , volume=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
A single algorithm for online multicalibration achieves instance-adaptive rates by dynamically refining a dyadic prediction grid, recovering the worst-case Õ(T^{2/3}) bound and improving to Õ(√T) in marginal stochastic settings and Õ(√(JT)) for J-piecewise stationary means.
Response times modeled as drift-diffusion processes enable consistent estimation of population-average preferences from heterogeneous anonymous binary choices.
citing papers explorer
-
Calibeating for general proper losses: A Bregman divergence approach
A Bregman divergence approach yields a unified calibeating framework for general proper losses, delivering U-calibration and logarithmic regret for Tsallis losses with weaker dimension dependence than prior work.
-
Instance-Adaptive Online Multicalibration
A single algorithm for online multicalibration achieves instance-adaptive rates by dynamically refining a dyadic prediction grid, recovering the worst-case Õ(T^{2/3}) bound and improving to Õ(√T) in marginal stochastic settings and Õ(√(JT)) for J-piecewise stationary means.
-
Response Time Enhances Alignment with Heterogeneous Preferences
Response times modeled as drift-diffusion processes enable consistent estimation of population-average preferences from heterogeneous anonymous binary choices.