Research map / Learning theory and algorithms / Submodular and game algorithms
Learned auction design
Learn revenue-optimal auction and pricing mechanisms from samples, including with deep networks.
105 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Submodular and game algorithms, keyword cluster “voting · allocation · agents”
State History Tried Checklist 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.
21 papers in 2023–24 and 26 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic held steady, from 10.3% to 10.7%.
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 · Sample Complexity of Automated Mechanism Design (NeurIPS 2016 · 30 citations)
- 2017 · Mechanism Design in Social Networks (AAAI 2017 · 64 citations)
- 2018 · MUDA: A Truthful Multi-Unit Double-Auction Mechanism (AAAI 2018 · 28 citations)
- 2019 · Optimal Auctions through Deep Learning (ICML 2019 · 90 citations)
- 2020 · Hitting the High Notes: Subset Selection for Maximizing Expected Order Statistics (NeurIPS 2020 · 8 citations)
- 2021 · PoA of Simple Auctions with Interdependent Values (AAAI 2021 · 11 citations)
- 2022 · Multi-Unit Auction in Social Networks with Budgets (AAAI 2022 · 10 citations)
- 2023 · Utility Maximizer or Value Maximizer: Mechanism Design for Mixed Bidders in Online Advertising (AAAI 2023 · 8 citations)
- 2024 · Machine Learning-Powered Combinatorial Clock Auction (AAAI 2024 · 4 citations)
- 2025 · Increasing Revenue in Efficient Combinatorial Auctions by Learning to Generate Artificial Competition (AAAI 2025 · 1 citation)
- 2026 · From Welfare to Utility: Generalized Objectives in Budget-Feasible Procurement (ICML 2026 · 0 citations)
Earliest papers here
- Sample Complexity of Automated Mechanism Design (NeurIPS 2016 · 30 citations)
- Assignment and Pricing in Roommate Market (AAAI 2016 · 14 citations)
- Optimizing Trading Assignments in Water Right Markets (AAAI 2016 · 7 citations)
What has been tried
70 papers here report 539 measured changes (a component added, removed or swapped, compared with a baseline): helped 63%, no clear effect 10%, hurt 21%, mixed 6%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Remove the feature-dependent slope term from the monotone bid function | Log-normal, profit maximization · AO | 0.9441 -> 0.9242 | Hurt | Simultaneous Optimization of Bid Shading and Internal Auction for Demand-Side Platforms (AAAI 2024 · 3 citations) |
| use CAN instead of CANw/oA, which removes the additional virtual bidder | Three-bidder auctions with irregular distributions (µ close to 0.5) · revenue | Helped | Learning Optimal Auctions with Correlated Value Distributions (AAAI 2025 · 0 citations) | |
| Combine DQ and VQ training rather than train on DQs alone | Price-driven test set (T_p) · R² | -10.07 -> 0.42 | Helped | Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them All (ICML 2025 · 0 citations) |
| Vary the norm used in the quadratic fee | Market-state updates toward μ · convergence path | Mixed | Smooth Quadratic Prediction Markets (NeurIPS 2025 · 0 citations) | |
| increase the bootstrap stepsize too much (d too small) | Synthetic FPPE experiments · distributional approximation | Hurt | Bootstrapping Fisher Market Equilibrium and First-Price Pacing Equilibrium (ICML 2024 · 0 citations) |
What reviewers will expect
Datasets and baselines named in the 15 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Baselines
- VCG · 4 of 15 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 47 papers; from OpenAlex and the papers' affiliations).
- Columbia University · 6 papers
- Renmin University of China · 5 papers
- Google · 4 papers
- Shandong University · 3 papers
- Harvard University · 3 papers
- Shanghai Jiao Tong University · 2 papers
- University of Zurich · 2 papers
- University of Chicago · 2 papers
Use it
Download BibTeX of 40 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
- Matching markets and welfare (119 papers)
- Fair division of indivisible goods (130 papers)
- Committee voting rules (120 papers)
Elsewhere in the topic
- Opponent modeling and subgame solving (116 papers)
- Monotone submodular maximization (116 papers)
- Zero-sum game learning dynamics (107 papers)
- Correlated equilibria in sequential games (86 papers)
- Streaming submodular algorithms (73 papers)
- Submodular influence maximization (33 papers)
- Equilibrium solvers for adversarial games (25 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).