Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
Towards convergence to Nash equilibria in two-team zero-sum games
Authors: Fivos Kalogiannis, Ioannis Panageas, Emmanouil-Vasileios Vlatakis-Gkaragkounis
ICLR 2023 | Venue PDF | LLM Run Details | Input Tokens: 20,610 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,063 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Finally, in Section 4 we provide a series of experiments in simple two-team zero-sum GAN s. We also show that multi-GAN architectures achieve better performance than single-agent ones, relative to the network capacity when they are trained on synthetic or real-world datasets like CIFAR10. |
| Researcher Affiliation | Academia | Fivos Kalogiannis UC Irvine Ioannis Panageas UC Irvine Emmanouil V. Vlatakis-Gkaragkounis Columbia University |
| Pseudocode | No | The paper defines its proposed method (KPV-GDA) using mathematical equations (e.g., z(k+1) = ΠZ n z(k) + η xf(z(k)) yf(z(k)) + ηK(z(k) θ(k)) o and θ(k+1) = ΠZ n θ(k) + ηP(z(k) θ(k)) o), but it does not present these or any other procedures in a structured pseudocode or algorithm block format. |
| Open Source Code | No | The paper does not contain any explicit statement about releasing source code for the described methodology, nor does it provide a link to a code repository. |
| Open Datasets | Yes | Finally, in Section 4 we provide a series of experiments in simple two-team zero-sum GAN s. We also show that multi-GAN architectures achieve better performance than single-agent ones, relative to the network capacity when they are trained on synthetic or real-world datasets like CIFAR10. |
| Dataset Splits | No | The paper mentions using CIFAR10 and synthetic datasets but does not specify any training, validation, or test splits by percentages, sample counts, or refer to predefined splits with citations. |
| Hardware Specification | No | The paper does not mention any specific hardware used to run its experiments, such as GPU models, CPU models, or cloud computing instance types. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers (e.g., library names like PyTorch 1.9, or solver versions like CPLEX 12.4) that would be needed to replicate the experiment. |
| Experiment Setup | Yes | Assume that ηGDA < 1/4, ηOGDA < min(ω, 1/8), ηEG < ω/2 , and ηOMWU < min 1/2 (bound on the stepsize for GDA, OGDA, OMWU, and EG methods respectively). |