mlsanityData to 7 Oct 2026

Efficient Projection-Free Online Methods with Stochastic Recursive Gradient

arXiv 1910.09396 ↗First posted 21 Oct 2019cs.LG math.OC stat.MLcited by 19

Not on the map. Why?

Abstract (arXiv)

This paper focuses on projection-free methods for solving smooth Online Convex Optimization (OCO) problems. Existing projection-free methods either achieve suboptimal regret bounds or have high per-iteration computational costs. To fill this gap, two efficient projection-free online methods called ORGFW and MORGFW are proposed for solving stochastic and adversarial OCO problems, respectively. By employing a recursive gradient estimator, our methods achieve optimal regret bounds (up to a logarithmic factor) while possessing low per-iteration computational costs. Experimental results demonstrate the efficiency of the proposed methods compared to state-of-the-arts.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 5; 2022: 5; 2023: 3; 2024: 3; 2025: 3.

19 papers.

Sort:

  1. 2023When Deep Learning Meets Polyhedral Theory: A Surveycited by 39
  2. 2021Complexity of Linear Minimization and Projection on Some Setscited by 19
  3. 2022Adaptive Fairness-Aware Online Meta-Learning for Changing Environmentscited by 17
  4. 2022Compression-aware Training of Neural Networks using Frank-Wolfecited by 16
  5. 2023Projection-Free Methods for Stochastic Simple Bilevel Optimization with Convex Lower-level Problemcited by 13
  6. 2021Projection-Free Algorithm for Stochastic Bi-level Optimizationcited by 8
  7. 2024From Linear to Linearizable Optimization: A Novel Framework with Applications to Stationary and Non-stationary DR-submodular Optimizationcited by 8
  8. 2021Zeroth and First Order Stochastic Frank-Wolfe Algorithms for Constrained Optimizationcited by 6
  9. 2022Continuous Diagnosis and Prognosis by Controlling the Update Process of Deep Neural Networkscited by 4
  10. 2024A Unified Framework for Analyzing Meta-algorithms in Online Convex Optimizationcited by 4
  11. 2022Confidence-Guided Learning Process for Continuous Classification of Time Seriescited by 3
  12. 2025Optimized projection-free algorithms for online learning: construction and worst-case analysiscited by 3
7 more
  1. 2021CDMA: A Practical Cross-Device Federated Learning Algorithm for General Minimax Problemscited by 2
  2. 2021Improved Regret Bounds for Online Submodular Maximizationcited by 2
  3. 2023Projection-Free Online Convex Optimization with Stochastic Constraintscited by 2
  4. 2024Dynamic Environment Responsive Online Meta-Learning with Fairness Awarenesscited by 2
  5. 2022On Private Online Convex Optimization: Optimal Algorithms in ℓp-Geometry and High Dimensional Contextual Banditscited by 1
  6. 2025Don't Be Greedy, Just Relax! Pruning LLMs via Frank-Wolfecited by 1
  7. 2025Quantum Algorithms for Projection-Free Sparse Convex Optimizationcited by 0