mlsanityData to 7 Oct 2026

Multiclass learning with margin: exponential rates with no bias-variance trade-off

arXiv 2202.01773 ↗First posted 3 Feb 2022stat.ML cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

We study the behavior of error bounds for multiclass classification under suitable margin conditions. For a wide variety of methods we prove that the classification error under a hard-margin condition decreases exponentially fast without any bias-variance trade-off. Different convergence rates can be obtained in correspondence of different margin assumptions. With a self-contained and instructive analysis we are able to generalize known results from the binary to the multiclass setting.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 4 of its 25 references that are in the map. First posted on arXiv 3 Feb 2022.

Builds on

4 of 25 references.

References · 4

  1. 2017Exponential convergence of testing error for stochastic gradient methodscited by 13
  2. 2018Sharp Analysis of Learning with Discrete Lossescited by 13
  3. 2021Fast rates in structured predictioncited by 11
  4. 2018Stochastic Gradient Descent with Exponential Convergence Rates of Expected Classification Errorscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 0; 2024: 1; 2025: 1; 2026: 1.

5 papers.

  1. 2022A Case of Exponential Convergence Rates for SVMcited by 3
  2. 2022From Weakly Supervised Learning to Active Learningcited by 0
  3. 2024Accounting for Missing Covariates in Heterogeneous Treatment Estimationcited by 0
  4. 2025Super-fast Rates of Convergence for Neural Network Classifiers under the Hard Margin Conditioncited by 0
  5. 2026Near-Exponential Convergence Rates for kNN Classification based on Boltzmann Margincited by 0