Research map / Learning theory and algorithms
Submodular and game algorithms: research map
1,030 accepted papers on Submodular and game algorithms in Learning theory and algorithms, from ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026), grouped into 3 clusters and 11 approaches. The busiest year so far is 2026.
Within Learning theory and algorithms, its share held steady from 9.1% in 2023–24 to 10.0% in 2025–26 (203 → 242 papers at ICML, NeurIPS, CVPR and AAAI, the venues with data for all four years).
Explore Submodular and game algorithms in the interactive map
Working on something in this topic? Describe your idea in scime atlas to see which approach it falls under, the closest papers by meaning and how crowded the spot has become.
Approaches and key papers
voting · allocation · agents · 474 papers
Approaches in this cluster:
- Matching markets and welfare (119 papers)
Analyze matching and social-welfare optimization with strategic or learning agents in platforms. - Learned auction design (105 papers)
Learn revenue-optimal auction and pricing mechanisms from samples, including with deep networks. - Fair division of indivisible goods (130 papers)
Study envy-free and efficient allocation of goods and chores with approximation guarantees. - Committee voting rules (120 papers)
Analyze proportionality and welfare of voting rules and committee selection.
Most cited and most cited since 2024:
- Optimal Auctions through Deep Learning (ICML 2019 · 90 citations)
- Fair and Truthful Mechanisms for Dichotomous Valuations (AAAI 2021 · 53 citations)
- On Optimal Tradeoffs between EFX and Nash Welfare (AAAI 2024 · 12 citations)
- Mixed Fair Division: A Survey (AAAI 2024 · 12 citations)
game · equilibrium · equilibria · 334 papers
Approaches in this cluster:
- Zero-sum game learning dynamics (107 papers)
Analyze complexity and learning dynamics for computing equilibria in two-player zero-sum games. - Opponent modeling and subgame solving (116 papers)
Use search, subgame refinement and meta-learning to play against opponents in imperfect-information games. - Correlated equilibria in sequential games (86 papers)
Compute correlated and Nash equilibria in extensive-form, potential and Markov games. - Equilibrium solvers for adversarial games (25 papers)
Find Nash equilibria with regret-based and first-order solvers, including for GANs.
Most cited and most cited since 2024:
- Safe and Nested Subgame Solving for Imperfect-Information Games (NeurIPS 2017 · 98 citations)
- Multiplicative Weights Update with Constant Step-Size in Congestion Games: Convergence, Limit Cycles and Chaos (NeurIPS 2017 · 56 citations)
- Competition among Pairwise Lottery Contests (AAAI 2024 · 6 citations)
- Pay to (Not) Play: Monetizing Impatience in Mobile Games (AAAI 2024 · 6 citations)
submodular maximization · submodular functions · monotone · 222 papers
Approaches in this cluster:
- Monotone submodular maximization (116 papers)
Develop approximation algorithms for maximizing submodular functions under cardinality and other constraints. - Streaming submodular algorithms (73 papers)
Maximize submodular objectives on data streams with small memory and robust guarantees. - Submodular influence maximization (33 papers)
Select seed nodes to spread influence in networks using submodular cascade models.
Most cited and most cited since 2024:
- Creating Capsule Wardrobes From Fashion Images (CVPR 2018 · 142 citations)
- Guarantees for Greedy Maximization of Non-submodular Functions with Applications (ICML 2017 · 100 citations)
- A Thorough Comparison Between Independent Cascade and Susceptible-Infected-Recovered Models (AAAI 2025 · 8 citations)
- Non-monotone Sequential Submodular Maximization (AAAI 2024 · 4 citations)
Related topics in Learning theory and algorithms
- Matrix and tensor methods (1,074)
- Sample complexity (1,363)
- Combinatorial and search optimization (1,492)
- Fairness (516)
- Prediction and decision losses (2,134)
- Kernels and regression theory (1,004)
- Clustering (725)
- Optimal transport (384)
