Alternation makes the adversary weaker in two-player games

Authors: Volkan Cevher, Ashok Cutkosky, Ali Kavis, Georgios Piliouras, Stratis Skoulakis, Luca Viano

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical The paper focuses on theoretical analysis, algorithm design, and establishing regret bounds (e.g., "O((log n)4/3T 1/3) regret"). It presents algorithms in pseudocode (Algorithm 1, 2, 3, 4) and includes lemmas and theorems (e.g., Lemma 3.2, Theorem 3.4, Lemma 4.1) for mathematical proofs. There are no sections describing experimental setups, datasets, empirical evaluations, or performance metrics from executed experiments.
Researcher Affiliation Academia Volkan Cevher LIONS, EPFL volkan.cevher@epfl.ch, Ashok Cutkosky Boston University ashok@cutkosky.com, Ali Kavis LIONS, EPFL ali.kavis@epfl.ch, Georgios Piliouras SUTD georgios@sutd.edu.sg, Stratis Skoulakis LIONS, EPFL efstratios.skoulakis@epfl.ch, Luca Viano LIONS, EPFL luca.viano@epfl.ch
Pseudocode Yes Algorithm 1 Standard and Alternating Online Linear Minimization, Algorithm 2 Online Learning Algorithm for 2D-Simplex, Algorithm 3 An Online Learning Algorithm for the n-Dimensional Simplex, Algorithm 4 Online Learning Algorithm for Unit Ball
Open Source Code No The paper does not mention or provide any links to open-source code for the described methodology.
Open Datasets No The paper is theoretical and does not involve empirical evaluation on datasets. It focuses on deriving theoretical bounds for online learning algorithms within mathematical domains like the n-dimensional simplex and ball of radius ρ.
Dataset Splits No The paper is theoretical and does not describe empirical experiments or dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe any computational experiments that would require specific hardware. Therefore, no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not detail any specific software dependencies or their versions for implementation or experimentation, as no empirical experiments were conducted.
Experiment Setup No The paper is theoretical and focuses on algorithm design and analysis rather than empirical experimentation. As such, it does not include details about an experimental setup, hyperparameters, or system-level training settings.