New algorithms minimize swap regret against arbitrary functions on convex action sets, yielding O~(T^{1/3}) ℓ2-calibration error and O~(max(T^{1/3}, sqrt(ǫT))) discretized-calibration error.
Selling to a no-regret buyer
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Full Swap Regret and Discretized Calibration
New algorithms minimize swap regret against arbitrary functions on convex action sets, yielding O~(T^{1/3}) ℓ2-calibration error and O~(max(T^{1/3}, sqrt(ǫT))) discretized-calibration error.