Research map / Learning theory and algorithms / Prediction and decision losses
Algorithms with explicit predictors
Model prediction error and predictor quality to analyze algorithms using ML predictions.
62 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Prediction and decision losses, keyword cluster “conformal · predictions · online”
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.
17 papers in 2023–24 and 21 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 3.2% to 3.6%.
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 · Avoiding Imposters and Delinquents: Adversarial Crowdsourcing and Peer Prediction (NeurIPS 2016 · 3 citations)
- 2017 · Best Response Regression (NeurIPS 2017 · 14 citations)
- 2018 · A Coverage-Based Utility Model for Identifying Unknown Unknowns (AAAI 2018 · 33 citations)
- 2019 · Attentive Neural Processes (ICLR 2019 · 24 citations)
- 2020 · Predictive Multiplicity in Classification (ICML 2020 · 29 citations)
- 2021 · Contract Scheduling With Predictions (AAAI 2021 · 2 citations)
- 2022 · Machine-Learned Prediction Equilibrium for Dynamic Traffic Assignment (AAAI 2022 · 5 citations)
- 2023 · On Manipulating Weight Predictions in Signed Weighted Networks (AAAI 2023 · 5 citations)
- 2024 · Learning-Augmented Algorithms with Explicit Predictors (NeurIPS 2024 · 2 citations)
- 2025 · Imputation for prediction: beware of diminishing returns. (ICLR 2025 · 3 citations)
- 2026 · Optimizing Health Coverage in Ethiopia: A Learning-augmented Approach and Persistent Proportionality Under an Online Budget (AAAI 2026 · 1 citation)
Earliest papers here
- Avoiding Imposters and Delinquents: Adversarial Crowdsourcing and Peer Prediction (NeurIPS 2016 · 3 citations)
- Best Response Regression (NeurIPS 2017 · 14 citations)
- A Coverage-Based Utility Model for Identifying Unknown Unknowns (AAAI 2018 · 33 citations)
What has been tried
44 papers here report 350 measured changes (a component added, removed or swapped, compared with a baseline): helped 63%, no clear effect 9%, hurt 22%, 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 |
|---|---|---|---|---|
| Add the missingness indicator | MCAR · prediction performance | Helped | Imputation for prediction: beware of diminishing returns. (ICLR 2025 · 3 citations) | |
| replace CatBoost with a 4-depth decision tree | German jobseekers · R² | 5% decrease in R² | Hurt | The Value of Prediction in Identifying the Worst-Off (ICML 2025 · 0 citations) |
| Increase MFCS weight-estimation depth d | Blue and red fluorescent protein design · coverage | Helped | Conformal Validity Guarantees Exist for Any Data Distribution (and How to Find Them) (ICML 2024 · 0 citations) | |
| Use a waiting time depending on k instead of τ = 0.2 | Pareto weights · competitive ratio | Mixed | The Secretary Problem with Predicted Additive Gap (NeurIPS 2024 · 0 citations) |
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 38 papers; from OpenAlex and the papers' affiliations).
- University of Massachusetts Amherst · 3 papers
- California Institute of Technology · 3 papers
- Tel Aviv University · 2 papers
- Johns Hopkins University · 2 papers
- University of California, Berkeley · 2 papers
- Columbia University · 2 papers
- RelationalAI · 2 papers
- Google · 2 papers
- Carnegie Mellon University · 2 papers
Use it
Download BibTeX of 37 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
- Conformal prediction sets (116 papers)
- Probabilistic calibration (55 papers)
Elsewhere in the topic
- Adaptive testing and experiments (201 papers)
- Active learning and subset selection (199 papers)
- Distributionally robust optimization (184 papers)
- Data attribution and recourse (160 papers)
- Theory of neural network sensitivity (143 papers)
- Ranking models from comparisons (127 papers)
- Determinantal point process inference (122 papers)
- Provable post-hoc explanations (92 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).