{"total":36,"rows":[{"id":"2102.12318","title":"Set-valued classification -- overview via a unified framework","created":"2021-02-24","cited_by_count":27,"area":null},{"id":"2207.08768","title":"Rank-based Decomposable Losses in Machine Learning: A Survey","created":"2022-07-18","cited_by_count":26,"area":null},{"id":"2302.01425","title":"Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective","created":"2023-02-02","cited_by_count":26,"area":null},{"id":"2405.05968","title":"A Universal Growth Rate for Learning with Smooth Surrogate Losses","created":"2024-05-09","cited_by_count":24,"area":null},{"id":"2106.03300","title":"Sum of Ranked Range Loss for Supervised Learning","created":"2021-06-07","cited_by_count":23,"area":null},{"id":"2108.10566","title":"sigmoidF1: A Smooth F1 Score Surrogate Loss for Multilabel Classification","created":"2021-08-24","cited_by_count":23,"area":null},{"id":"2407.07140","title":"Cardinality-Aware Set Prediction and Top-$k$ Classification","created":"2024-07-09","cited_by_count":23,"area":null},{"id":"2206.07290","title":"Differentiable Top-k Classification Learning","created":"2022-06-15","cited_by_count":21,"area":null},{"id":"2110.14031","title":"Surrogate Regret Bounds for Polyhedral Losses","created":"2021-10-26","cited_by_count":15,"area":null},{"id":"2206.14707","title":"An Embedding Framework for the Design and Analysis of Consistent Polyhedral Surrogates","created":"2022-06-29","cited_by_count":14,"area":null},{"id":"2503.06242","title":"LapSum -- One Method to Differentiate Them All: Ranking, Sorting and Top-k Selection","created":"2025-03-08","cited_by_count":13,"area":null},{"id":"2112.14869","title":"Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity","created":"2021-12-30","cited_by_count":11,"area":null},{"id":"2202.02193","title":"Stochastic smoothing of the top-K calibrated hinge loss for deep imbalanced classification","created":"2022-02-04","cited_by_count":10,"area":null},{"id":"2403.10889","title":"List Sample Compression and Uniform Convergence","created":"2024-03-16","cited_by_count":10,"area":null},{"id":"2209.01398","title":"Optimizing Partial Area Under the Top-k Curve: Theory and Practice","created":"2022-09-03","cited_by_count":9,"area":null},{"id":"2207.08873","title":"Consistent Polyhedral Surrogates for Top-$k$ Classification and Variants","created":"2022-07-18","cited_by_count":8,"area":null},{"id":"2310.10636","title":"Dual-Encoders for Extreme Multi-Label Classification","created":"2023-10-16","cited_by_count":7,"area":null},{"id":"2504.12988","title":"Why Ask One When You Can Ask $k$? Learning-to-Defer to the Top-$k$ Experts","created":"2025-04-17","cited_by_count":7,"area":null},{"id":"2602.20816","title":"Don't Ignore the Tail: Decoupling top-K Probabilities for Efficient Language Model Distillation","created":"2026-02-24","cited_by_count":7,"area":null},{"id":"2408.16862","title":"Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics","created":"2024-08-29","cited_by_count":6,"area":null},{"id":"2103.04635","title":"FEDS -- Filtered Edit Distance Surrogate","created":"2021-03-08","cited_by_count":5,"area":null},{"id":"2403.19625","title":"Top-$k$ Classification and Cardinality-Aware Prediction","created":"2024-03-28","cited_by_count":5,"area":null},{"id":"2604.12952","title":"An Optimal Sauer Lemma Over $k$-ary Alphabets","created":"2026-04-14","cited_by_count":4,"area":null},{"id":"2109.02345","title":"Tensor Normalization and Full Distribution Training","created":"2021-09-06","cited_by_count":3,"area":null},{"id":"2201.12678","title":"A Stochastic Bundle Method for Interpolating Networks","created":"2022-01-29","cited_by_count":3,"area":null},{"id":"2203.06676","title":"Set-valued prediction in hierarchical classification with constrained representation complexity","created":"2022-03-13","cited_by_count":3,"area":null},{"id":"2112.08851","title":"Classification Under Ambiguity: When Is Average-K Better Than Top-K?","created":"2021-12-16","cited_by_count":1,"area":null},{"id":"2209.15380","title":"Identify ambiguous tasks combining crowdsourced labels by weighting Areas Under the Margin","created":"2022-09-30","cited_by_count":1,"area":null},{"id":"2212.14106","title":"Provable Robust Saliency-based Explanations","created":"2022-12-28","cited_by_count":1,"area":null},{"id":"2407.06709","title":"Top-K Pairwise Ranking: Bridging the Gap Among Ranking-Based Measures for Multi-Label Classification","created":"2024-07-09","cited_by_count":1,"area":null},{"id":"2109.05635","title":"Mixing between the Cross Entropy and the Expectation Loss Terms","created":"2021-09-12","cited_by_count":0,"area":null},{"id":"2204.07727","title":"The Tree Loss: Improving Generalization with Many Classes","created":"2022-04-16","cited_by_count":0,"area":null},{"id":"2210.13364","title":"Large Batch and Patch Size Training for Medical Image Segmentation","created":"2022-10-24","cited_by_count":0,"area":null},{"id":"2510.04926","title":"Set to Be Fair: Demographic Parity Constraints for Set-Valued Classification","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2601.22745","title":"Is Softmax Loss All You Need? A Principled Analysis of Softmax-family Loss","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2605.09813","title":"Optimizing Server Placement for Vertical Federated Learning in Dynamic Edge/Fog Networks","created":"2026-05-10","cited_by_count":0,"area":null}],"next_cursor":null}