The First Optimal Algorithm for Smooth and Strongly-Convex-Strongly-Concave Minimax Optimization

Authors: Dmitry Kovalev, Alexander Gasnikov

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This is a theoretical work with no forseeable negative societal impact.
Researcher Affiliation Academia Dmitry Kovalev KAUST dakovalev1@gmail.com King Abdullah University of Science and Technology, Thuwal, Saudi Arabia Alexander Gasnikov MIPT , ISP RAS , HSE gasnikov@yandex.ru Moscow Institute of Physics and Technology, Dolgoprudny, Russia Institute for System Programming RAS, Research Center for Trusted Artificial Intelligence, Moscow, Russia National Research University Higher School of Economics, Moscow, Russia
Pseudocode Yes Algorithm 1 Accelerated Gradient Method; Algorithm 2 Accelerated Proximal Point Algorithm; Algorithm 3 Extra Anchored Gradient for Monotone Inclusions; Algorithm 4 FOAM: The First Optimal Algorithm for Minimax Optimization
Open Source Code No Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [N/A]
Open Datasets No The paper is theoretical and does not involve training on datasets. It states 'N/A' for questions related to experiments and data.
Dataset Splits No The paper is theoretical and does not involve data splits for training, validation, or testing. It states 'N/A' for questions related to experiments and data.
Hardware Specification No The paper is theoretical and does not describe hardware used for experiments. It states 'N/A' for questions related to running experiments.
Software Dependencies No The paper is theoretical and does not specify software dependencies with version numbers for experimental reproducibility. It states 'N/A' for questions related to running experiments.
Experiment Setup No The paper is theoretical and does not provide details about an experimental setup, such as hyperparameters or system-level training settings. It states 'N/A' for questions related to running experiments.