mlsanityData to 14 Oct 2026

A Consistent Regularization Approach for Structured Prediction

arXiv 1605.07588 ↗First posted 24 May 2016cs.LG stat.MLcited by 33

Not on the map. Why?

Abstract (arXiv)

We propose and analyze a regularization approach for structured prediction problems. We characterize a large class of loss functions that allows to naturally embed structured outputs in a linear space. We exploit this fact to design learning algorithms using a surrogate loss approach and regularization techniques. We prove universal consistency and finite sample bounds characterizing the generalization properties of the proposed methods. Experimental results are provided to demonstrate the practical usefulness of the proposed approach.

Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). First posted on arXiv 24 May 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 6; 2023: 6; 2024: 9; 2025: 5; 2026: 1.

33 papers.

Sort:

By area:

  1. 2023Cross-Entropy Loss Functions: Theoretical Analysis and Applicationscited by 210
  2. 2022Optimal Rates for Regularized Conditional Mean Embedding Learningcited by 50
  3. 2024A Universal Growth Rate for Learning with Smooth Surrogate Lossescited by 24
  4. 2022Learning to Predict Graphs with Fused Gromov-Wasserstein Barycenterscited by 22
  5. 2023Towards Optimal Sobolev Norm Rates for the Vector-Valued Regularized Least-Squares Algorithmcited by 22
  6. 2024H-Consistency Guarantees for Regressioncited by 21
  7. 2024Enhanced H-Consistency Boundscited by 18
  8. 2021Surrogate Regret Bounds for Polyhedral Lossescited by 15
  9. 2023Estimating Koopman operators with sketching to provably learn large scale dynamical systemscited by 15
  10. 2024Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithmscited by 12
  11. 2021Fast rates in structured predictioncited by 11
  12. 2022Lifting Weak Supervision To Structured Predictioncited by 10
21 more
  1. 2022Learning Energy Networks with Generalized Fenchel-Young Lossescited by 8
  2. 2024Nonparametric Instrumental Regression via Kernel Methods is Minimax Optimalcited by 8
  3. 2024Online Structured Prediction with Fenchel--Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic Losscited by 7
  4. 2022Vector-Valued Least-Squares Regression under Output Regularity Assumptionscited by 5
  5. 2023Sketch In, Sketch Out: Accelerating both Learning and Inference for Structured Prediction with Kernelscited by 5
  6. 2023Geometry-Aware Adaptation for Pretrained Modelscited by 5
  7. 2021Disambiguation of weak supervision with exponential convergence ratescited by 4
  8. 2021Fine-grained Generalization Analysis of Structured Output Predictioncited by 4
  9. 2024Generalization Bounds of Surrogate Policies for Combinatorial Optimization Problemscited by 3
  10. 2024Nonparametric Sparse Online Learning of the Koopman Operatorcited by 2
  11. 2024Deep Sketched Output Kernel Regression for Structured Predictioncited by 2
  12. 2025Establishing Linear Surrogate Regret Bounds for Convex Smooth Losses via Convolutional Fenchel-Young Lossescited by 2
  13. 2026Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Predictioncited by 2
  14. 2023A Structured Prediction Approach for Robot Imitation Learningcited by 1
  15. 2025Bandit and Delayed Feedback in Online Structured Predictioncited by 1
  16. 2025A Kernel-based Stochastic Approximation Framework for Nonlinear Operator Learningcited by 1
  17. 2021Structured Prediction for CRiSP Inverse Kinematics Learning with Misspecified Robot Modelscited by 0
  18. 2021Autonomous Driving Implementation in an Experimental Environmentcited by 0
  19. 2022From Weakly Supervised Learning to Active Learningcited by 0
  20. 2025Nonparametric Sparse Online Learning of the Koopman Operatorcited by 0
  21. 2025Non-Stationary Online Structured Prediction with Surrogate Lossescited by 0