Prediction Accuracy of Learning in Games : Follow-the-Regularized-Leader meets Heisenberg

Authors: Yi Feng, Georgios Piliouras, Xiao Wang

ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In this section we provide numerical experiments illustrating the covariance evolution results proved for Euclidean norm regularized FTRL in Theorem 5.1.
Researcher Affiliation Collaboration 1Shanghai University of Finance and Economics, Shanghai, China 2Google Deep Mind, London, United Kingdom 3Key Laboratory of Interdisciplinary Research of Computation and Economics, China.
Pseudocode No The paper presents mathematical formulations and derivations but does not include any pseudocode or algorithm blocks.
Open Source Code No The paper does not provide explicit statements about the release of open-source code for the described methodology or links to code repositories.
Open Datasets No The experiments are conducted using 'randomly generated initial conditions' and 'randomly generated game', implying synthetic data rather than a specific public dataset with access information.
Dataset Splits No The paper describes numerical experiments based on initial conditions, but it does not specify any training, validation, or test dataset splits.
Hardware Specification No The paper describes numerical experiments but does not provide any specific hardware details such as GPU/CPU models, processor types, or memory used for running the experiments.
Software Dependencies No The paper describes numerical experiments but does not list specific software dependencies with version numbers used for these experiments.
Experiment Setup No The paper discusses the 'step size η' and 'randomly generated initial conditions' for numerical experiments, but it does not provide specific hyperparameter values, model initialization details, or other system-level training settings in the main text.