On the Interplay between Social Welfare and Tractability of Equilibria

Authors: Ioannis Anagnostides, Tuomas Sandholm

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

Reproducibility Variable Result LLM Response
Research Type Experimental Example A.11. ...Now, through a numerical simulation we draw the following conclusion: Although Po AG = 1, for T 1 OGD with learning rate η := 0.01 and initialization (ˆx(1) 1 , ˆx(1) 2 , ) := ((0.5, 0.25, 0.25), (0.25, 0.5, 0.25), ) satisfies NEGAP(x(t)) 0.1875 for any t JTK, where (x(t))t 1 is the sequence of iterates produced by OGD. We also note that the specific value for the learning rate specified above is used for concreteness, and the conclusion is not tied to that specific value. In particular, we conduct experiments on a set of random normal-form games. Some illustrative results for 10 random games are demonstrated in Figure 1.
Researcher Affiliation Collaboration Ioannis Anagnostides Carnegie Mellon University ianagnos@cs.cmu.edu Tuomas Sandholm Carnegie Mellon University Strategic Machine, Inc. Strategy Robot, Inc. Optimized Markets, Inc. sandholm@cs.cmu.edu
Pseudocode No The paper provides mathematical update rules for OGD and CGD but not a structured pseudocode block or algorithm.
Open Source Code No The paper does not provide any statement or link regarding the public availability of its source code.
Open Datasets No The paper does not provide concrete access information (specific link, DOI, repository name, formal citation with authors/year) for a publicly available or open dataset. It describes generating 'random normal-form games' and using 'Shapley’s game' as constructed examples for its simulations.
Dataset Splits No The paper describes running numerical simulations and experiments but does not specify dataset split information for training, validation, or testing subsets.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup Yes Example A.11. ...for T 1 OGD with learning rate η := 0.01 and initialization (ˆx(1) 1 , ˆx(1) 2 , ) := ((0.5, 0.25, 0.25), (0.25, 0.5, 0.25), ) satisfies NEGAP(x(t)) 0.1875 for any t JTK, where (x(t))t 1 is the sequence of iterates produced by OGD.