Solving Min-Max Optimization with Hidden Structure via Gradient Descent Ascent

Authors: Emmanouil-Vasileios Vlatakis-Gkaragkounis, Lampros Flokas, Georgios Piliouras

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirically, these results are robust to discrete and stochastic updates using sampling as shown in Figure 4.
Researcher Affiliation Academia Lampros Flokas Department of Computer Science Columbia University New York, NY 10025 lamflokas@cs.columbia.edu Emmanouil V. Vlatakis-Gkaragkounis Department of Computer Science Columbia University New York, NY 10025 emvlatakis@cs.columbia.edu Georgios Piliouras Singapore University of Technology & Design georgios.piliouras@sutd.edu.sg
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes 3.a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [Yes]
Open Datasets No The paper mentions using 'fully mixed distribution' and 'Gaussian distributions' for experiments, implying synthetic or internally generated data without providing specific access information (e.g., URL, DOI, specific citation with author/year) for a publicly available dataset.
Dataset Splits No The paper does not specify exact percentages or sample counts for training, validation, or test dataset splits.
Hardware Specification No 3.d) Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)? [No] The presented experiments are used for illustrative purposes and only to validate the theoretical findings which are the core results of this work.
Software Dependencies No The paper mentions 'Stochastic GDA' but does not specify any software dependencies (e.g., libraries, frameworks) with version numbers.
Experiment Setup No While the checklist states that training details were specified, the main text does not contain specific hyperparameter values (e.g., learning rate, batch size, epochs) or detailed system-level training configurations. It vaguely mentions 'small learning rates' in a figure caption but no concrete values.