A Unifying Perspective on Multi-Calibration: Game Dynamics for Multi-Objective Learning
We provide a unifying framework for the design and analysis of multicalibrated predictors. By placing the multicalibration problem in the general setting of multi-objective learning -- where learning guarantees must hold simultaneously over a set of distributions and loss functions -- we exploit connections to game dynamics to achieve state-of-the-art guarantees for a diverse set of multicalibration learning problems. In addition to shedding light on existing multicalibration guarantees and greatly simplifying their analysis, our approach also yields improved guarantees, such as obtaining stronger multicalibration conditions that scale with the square-root of group size and improving the complexity of $k$-class multicalibration by an exponential factor of $k$. Beyond multicalibration, we use these game dynamics to address emerging considerations in the study of group fairness and multi-distribution learning.
Code (1)
Tasks
FairnessSimilar Papers 제목 키워드 기반
A Collective Variational Principle Unifying Bayesian Inference, Game Theory, and Thermodynamics
Collective intelligence emerges across biological, physical, and artificial systems without central coordination, yet a unifying principle governing such behaviour remains elusive. The Free Energy Principle explains how …
Bayesian InferenceA Unifying Perspective on Probabilities as Model Predictions
Although probabilistic statements are ubiquitous, foundational disagreements persist about their understanding, as exemplified by debates between Bayesians and frequentists; moreover, it is unclear when and why acting on…
A Dynamics Perspective of Pursuit-Evasion Games of Intelligent Agents with the Ability to Learn
Pursuit-evasion games are ubiquitous in nature and in an artificial world. In nature, pursuer(s) and evader(s) are intelligent agents that can learn from experience, and dynamics (i.e., Newtonian or Lagrangian) is vital …
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Smooth Calibration, Leaky Forecasts, Finite Recall, and Nash Dynamics
We propose to smooth out the calibration score, which measures how good a forecaster is, by combining nearby forecasts. While regular calibration can be guaranteed only by randomized forecasting procedures, we show that …
Game theory models for communication between agents: a review
In the real world, agents or entities are in a continuous state of interactions. These inter- actions lead to various types of complexity dynamics. One key difficulty in the study of complex agent interactions is the dif…