Efficient Minimax Strategies for Square Loss Games

Authors: Wouter M. Koolen, Alan Malek, Peter L Bartlett

NeurIPS 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We derive the minimax solutions for the case where the prediction and action spaces are the simplex (this setup is sometimes called the Brier game) and the ℓ2 ball (this setup is related to Gaussian density estimation). We show that in both cases the value of each sub-game is a quadratic function of a simple statistic of the state, with coefficients that can be efficiently computed using an explicit recurrence relation. The resulting deterministic minimax strategy and randomized maximin strategy are linear functions of the statistic.
Researcher Affiliation Academia Wouter M. Koolen Queensland University of Technology and UC Berkeley wouter.koolen@qut.edu.au Alan Malek University of California, Berkeley malek@eecs.berkeley.edu Peter L. Bartlett University of California, Berkeley and Queensland University of Technology peter@berkeley.edu
Pseudocode No The paper contains mathematical derivations and proofs but no pseudocode or algorithm blocks.
Open Source Code No The paper does not mention providing open-source code for the methodology described.
Open Datasets No The paper is theoretical and does not use or refer to any datasets for training.
Dataset Splits No The paper is theoretical and does not use datasets, so there is no mention of training/validation/test splits.
Hardware Specification No The paper is theoretical and does not conduct experiments, therefore, no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not conduct experiments, therefore, no specific software dependencies with version numbers are mentioned.
Experiment Setup No The paper is theoretical and does not include an experimental setup with hyperparameters or training settings.