mlsanityData to 7 Oct 2026

Learning Classifiers with Fenchel-Young Losses: Generalized Entropies, Margins, and Algorithms

arXiv 1805.09717 ↗First posted 24 May 2018stat.ML cs.LGcited by 27

Not on the map. Why?

Abstract (arXiv)

This paper studies Fenchel-Young losses, a generic way to construct convex loss functions from a regularization function. We analyze their properties in depth, showing that they unify many well-known loss functions and allow to create useful new ones easily. Fenchel-Young losses constructed from a generalized entropy, including the Shannon and Tsallis entropies, induce predictive probability distributions. We formulate conditions for a generalized entropy to yield losses with a separation margin, and probability distributions with sparse support. Finally, we derive efficient algorithms, making Fenchel-Young losses appealing both in theory and practice.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 3; 2024: 3; 2025: 8; 2026: 9.

27 papers.

Sort:

By area:

  1. 2021DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learningcited by 114
  2. 2024CaDA: Cross-Problem Routing Solver with Constraint-Aware Dual-Attentioncited by 23
  3. 2023From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Modulecited by 19
  4. 2025AdaSplash: Adaptive Sparse Flash Attentioncited by 12
  5. 2023Joint Sensing, Communication, and AI: A Trifecta for Resilient THz User Experiencescited by 10
  6. 2024MANO: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shiftscited by 8
  7. 2022Contrasting quadratic assignments for set-based representation learningcited by 6
  8. 2026MonarchRT: Efficient Attention for Real-Time Video Generationcited by 6
  9. 2025MonarchAttention: Zero-Shot Conversion to Fast, Hardware-Aware Structured Attentioncited by 5
  10. 2024Learning with Fitzpatrick Lossescited by 3
  11. 2026AdaSplash-2: Faster Differentiable Sparse Attentioncited by 3
  12. 2026DashAttention: Differentiable and Adaptive Sparse Hierarchical Attentioncited by 3
15 more
  1. 2022Adaptive Sparse and Monotonic Attention for Transformer-based Automatic Speech Recognitioncited by 2
  2. 2025Robust Classification with Noisy Labels Based on Posterior Maximizationcited by 2
  3. 2026Entropy-Generated Attention Beyond Softmax and Entmax: Kaniadakis and Reciprocal-Symmetric Abe Operatorscited by 2
  4. 2021Memory Wrap: a Data-Efficient and Interpretable Extension to Image Classification Modelscited by 1
  5. 2025Fenchel-Young Variational Learningcited by 1
  6. 2025Hierarchical Self-Attention: Generalizing Neural Attention Mechanics to Multi-Scale Problemscited by 1
  7. 2026Differentiable Knapsack and Top-k Operators via Dynamic Programmingcited by 1
  8. 2023On Inductive Biases for Machine Learning in Data Constrained Settingscited by 0
  9. 2025A Fenchel-Young Loss Approach to Data-Driven Inverse Optimizationcited by 0
  10. 2025Weighted Graph Structure Learning with Attention Denoising for Node Classificationcited by 0
  11. 2025Alpha Divergence Losses for Biometric Verificationcited by 0
  12. 2026Weighted Graph Clustering via Scale Contraction and Graph Structure Learningcited by 0
  13. 2026EntmaxKV: Support-Aware Decoding for Entmax Attentioncited by 0
  14. 2026Sparsity-Inducing Divergence Losses for Biometric Verificationcited by 0
  15. 2026Sparse Attention for Dense Open-Vocabulary Prediction in CLIPcited by 0