Research map / Learning theory and algorithms / Submodular and game algorithms
Equilibrium solvers for adversarial games
Find Nash equilibria with regret-based and first-order solvers, including for GANs.
25 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Submodular and game algorithms, keyword cluster “game · equilibrium · equilibria”
State History Tried Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
10 papers in 2023–24 and 3 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 4.9% to 1.2%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2016 · Poker-CNN: A Pattern Learning Strategy for Making Draws and Bets in Poker Games Using Convolutional Networks (AAAI 2016 · 23 citations)
- 2019 · Finding Mixed Nash Equilibria of Generative Adversarial Networks (ICML 2019 · 16 citations)
- 2020 · Do GANs always have Nash equilibria? (ICML 2020 · 30 citations)
- 2021 · On Characterizing GAN Convergence Through Proximal Duality Gap (ICML 2021 · 5 citations)
- 2022 · Turbocharging Solution Concepts: Solving NEs, CEs and CCEs with Neural Equilibrium Solvers (NeurIPS 2022 · 1 citation)
- 2023 · Rethinking Data-Free Quantization as a Zero-Sum Game (AAAI 2023 · 19 citations)
- 2024 · No Free Lunch Theorem and Black-Box Complexity Analysis for Adversarial Optimisation (NeurIPS 2024 · 2 citations)
- 2025 · Towards Runtime Analysis of Population-Based Co-evolutionary Algorithms on Sparse Binary Zero-Sum Game (AAAI 2025)
- 2026 · On the Computational Complexity of Performative Prediction (ICML 2026)
Earliest papers here
- Poker-CNN: A Pattern Learning Strategy for Making Draws and Bets in Poker Games Using Convolutional Networks (AAAI 2016 · 23 citations)
- Deep Learning Games (NeurIPS 2016 · 19 citations)
- Finding Mixed Nash Equilibria of Generative Adversarial Networks (ICML 2019 · 16 citations)
What has been tried
22 papers here report 149 measured changes (a component added, removed or swapped, compared with a baseline): helped 59%, no clear effect 8%, hurt 26%, mixed 7%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Increase the mutation rate above χ = 0.5 | DIAGONAL · runtime | χ = 0.5 | Hurt | Towards Runtime Analysis of Population-Based Co-evolutionary Algorithms on Sparse Binary Zero-Sum Game (AAAI 2025) |
| Solve the BRO linear relaxation first | 3-player Leduc 3^3L1_14 · runtime | 381s -> 188s | Helped | DAG-Based Column Generation for Adversarial Team Games (ICML 2024) |
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 13 papers; from OpenAlex and the papers' affiliations).
- Nanyang Technological University · 2 papers
- University of Birmingham · 2 papers
- Carnegie Mellon University · 2 papers
- Google DeepMind · 2 papers
Use it
Download BibTeX of 25 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Zero-sum game learning dynamics (107 papers)
- Opponent modeling and subgame solving (116 papers)
- Correlated equilibria in sequential games (86 papers)
Elsewhere in the topic
- Fair division of indivisible goods (130 papers)
- Committee voting rules (120 papers)
- Matching markets and welfare (119 papers)
- Monotone submodular maximization (116 papers)
- Learned auction design (105 papers)
- Streaming submodular algorithms (73 papers)
- Submodular influence maximization (33 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).