Online Calibration

Follow this topic Ask about this topic

Latest papers

14 papers3 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Learning vs. Optimizing Players in Budgeted Games
Nov 3, 2026Giannis Fikioris, Balasubramanian Sivan, Éva TardosGame Theory Stackelberg Games
Google Research · Cornell University & Google Research
How Much Fresh Data Should CTR Recalibration Use? A Temporal Evaluation of Post-hoc Calibration
Oct 23, 2026Rui LiuPost-Hoc Calibration CTR Prediction
Independent Researcher
CALM-5G: Event-Level Conformal Risk Control for Predictive Service-Assurance Alarms
Oct 13, 2026Ömer Faruk İşcanlı, Yağmur Sabucu SandalOnline Calibration Conformal Risk Control
Siemens A.¸S., Istanbul, Türkiye
High-dimensional online calibration from harmonic weights
Oct 6, 2026Maxwell Fishelson, Mehryar MohriOnline Calibration Probability Calibration
Institute for Advanced Study. · Google Research and Courant Institute of Mathematical Sciences, New York.
Model-Agnostic Online Certificate-Driven Calibration for Time Series Forecasting Under Distribution Shift
Sep 25, 2026Chenfeng Huang, Zixuan Ma, George MichailidisOnline Calibration Time Series Forecasting
Department of Statistics and Data Science, University of California, Los Angeles, Los Angeles, California, USA
DreamLedger: Where to Refuse World-Model Imagination Using Execution-Settled Credit
Aug 24, 2026Xianyao Li, Ruitong Tian, Rui Min +2Online Calibration Selective Prediction
Department of Civil and Coastal Engineering, University of Florida, Gainesville, FL 32611, USA · Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL 32611, USA
Truthful Calibration Measures for Sequential Prediction
Aug 21, 2026Anagha Gokul, Jason Hartline, Lunjia Hu +2Online Calibration Sequence Prediction
Northeastern University. Khoury College of Computer Sciences. · Northwestern University. Department of Computer Science. · Microsoft Research. Microsoft Research New England.
Optimal Recalibration of an Online Predictor
Jul 22, 2026Lunjia Hu, Kevin Tian, Chutong YangModel Calibration Online Calibration
Northeastern University · University of Texas at Austin
Efficient Sequential Calibration with $O(T^{2/3-ε})$ Error Bound
Jul 14, 2026Zihan ZhangBlackwell Approachability Online Calibration
Department of CSE, HKUST
Anomaly-Informed Confidence Calibration for Vision-Based Safety Prediction
May 20, 2026Zhenjiang Mao, Jiawen Wu, Gabriel Wagner +2Online Calibration Post-Hoc Calibration
Trustworthy Engineered Autonomy (TEA) Lab, Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL 32611, USA
Adaptive Calibration in Non-Stationary Environments
May 12, 2026Junyan Liu, Haipeng Luo, Lillian J. RatliffOnline Calibration Model Calibration
University of Washington · University of Southern California
Instance-Adaptive Online Multicalibration
May 10, 2026Zhiming Huang, Jamie Morgenstern, Aaron Roth +1Probability Calibration Model Calibration
Paul G. Allen School of Computer Science and Engineering, University of Washington · Department of Computer and Information Sciences, University of Pennsylvania
Calibeating Made Simple
Mar 23, 2026Yurong Chen, Zhiyi Huang, Michael I. Jordan +1Online Calibration Probability Calibration
Inria, École Normale Supérieure, PSL Research University · The University of Hong Kong · University of California, Berkeley +1
Airborne Magnetic Anomaly Navigation with Neural-Network-Augmented Online Calibration
Mar 9, 2026Antonia Hager, Sven Nebendahl, Alexej Klushyn +3Online Calibration GNSS-Denied Localization
Airbus, 82024 Taufkirchen, Germany. · Norwegian University of Science and Technology, 7034 Trondheim, Norway.

Nov 3, 2026J/K move · Enter open · S save

Learning vs. Optimizing Players in Budgeted Games

Giannis Fikioris, Balasubramanian Sivan, Éva Tardos

Google Research · Cornell University & Google Research

Game Theory Stackelberg Games Online Calibration

Open paper AskPDF arXiv

We study repeated general games over

T

rounds between a utility-maximizing optimizer and a learning agent, where budget constraints couple the players' decisions across rounds. Without budgets, low swap regret simultaneously guarantees the learner sublinear regret and caps the optimizer at its Stackelberg value. Budgets break this picture: adversarial no-regret becomes impossible, so the natural goals are non-manipulability---no adaptive optimizer earns more than

\mathtt{BSE} \cdot T + o(T)

, where

\mathtt{BSE}

is its Budgeted Stackelberg Equilibrium value---and low stochastic regret when the optimizer plays a fixed mixed strategy. We give an efficient, budget-feasible learning algorithm that achieves both goals in every budgeted game: any adaptive optimizer, budgeted or not, earns at most

\mathtt{BSE} \cdot T + O(\sqrt{T})

in expectation, and if the optimizer plays a fixed mixed strategy on each of a constant number of intervals, the learner has

O(\sqrt{T})

regret on each such interval. Our learner best responds to forecasts of the optimizer's play that are calibrated in two novel senses, since under budgets the calibration that prevents manipulation no longer yields low stochastic regret. Response calibration, which conditions on the learner's own mixed response by embedding its continuous mixing weight as a step function in

L^2([-1,1])

, prevents manipulation without discretizing responses; dual-weighted Lagrangian calibration ensures low regret. Although low calibration error requires randomized forecasts---distributions over a continuous space that need not have a succinct representation or be directly computable---we construct such forecasts in polynomial time by simulating online gradient ascent.