Research map / Learning theory and algorithms / Prediction and decision losses
Ranking-based loss optimization
Optimize rank-based and multivariate losses with consistent or differentiable surrogates.
50 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Prediction and decision losses, keyword cluster “losses · loss functions · surrogate”
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 7 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 1.9% 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 · Discriminative Analysis Dictionary Learning (AAAI 2016 · 68 citations)
- 2017 · Multiclass Capped ℓp-Norm SVM for Robust Classifications (AAAI 2017 · 69 citations)
- 2018 · Smooth Loss Functions for Deep Top-k Classification (ICLR 2018 · 70 citations)
- 2019 · Improving One-Class Collaborative Filtering via Ranking-Based Implicit Regularizer (AAAI 2019 · 23 citations)
- 2020 · NeurQuRI: Neural Question Requirement Inspector for Answerability Prediction in Machine Reading Comprehension (ICLR 2020 · 19 citations)
- 2021 · An Alternative Probabilistic Interpretation of the Huber Loss (CVPR 2021 · 182 citations)
- 2022 · Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones Is Enough (AAAI 2022 · 13 citations)
- 2023 · Cross-Entropy Loss Functions: Theoretical Analysis and Applications (ICML 2023 · 217 citations)
- 2024 · Wormhole Loss for Partial Shape Matching (NeurIPS 2024 · 6 citations)
- 2025 · A Versatile Influence Function for Data Attribution with Non-Decomposable Loss (ICML 2025 · 0 citations)
- 2026 · Marginalized Generalized IoU (MGIoU): A Unified Objective Function for Optimizing Convex Parametric Shapes (AAAI 2026 · 2 citations)
Earliest papers here
- Discriminative Analysis Dictionary Learning (AAAI 2016 · 68 citations)
- Loss Functions for Top-k Error: Analysis and Insights (CVPR 2016 · 65 citations)
- Optimal Classification with Multivariate Losses (ICML 2016 · 3 citations)
What has been tried
42 papers here report 406 measured changes (a component added, removed or swapped, compared with a baseline): helped 66%, no clear effect 14%, hurt 15%, mixed 4%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| use wormhole criterion C_W instead of C_T to derive the binary mask | HOLES · geodesic error ×100 | 18.8 -> 15.3 | Helped | Wormhole Loss for Partial Shape Matching (NeurIPS 2024 · 6 citations) |
| Use Tanh instead of ReLU as the PSL surrogate activation | IID: Amazon-Book, Amazon-Electronic, Amazon-Movie, Gowalla · NDCG@20 | 0.1227 -> 0.1225; 0.0541 -> 0.0535; 0.0945 -> 0.0941; 0.1647 -> 0.1646 | Mixed | PSL: Rethinking and Improving Softmax Loss from Pairwise Perspective for Recommendation (NeurIPS 2024 · 2 citations) |
| Add ensemble across 5 models | Ablation evaluation set (not specified) · DockQ>0.23 | 0.375 -> 0.438 | Helped | FAFE: Immune Complex Modeling with Geodesic Distance Loss on Noisy Group Frames (ICML 2024 · 0 citations) |
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 17 papers; from OpenAlex and the papers' affiliations).
- Google · 5 papers
- Courant Institute of Mathematical Sciences · 3 papers
- University of Illinois, Urbana Champaign · 2 papers
Use it
Download BibTeX of 31 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
- Consistency of surrogate losses (72 papers)
- Losses for decision-making (68 papers)
- Loss landscape analysis (61 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)
- Conformal prediction sets (116 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).