mlsanityData to 14 Oct 2026

Smoothed Online Optimization for Regression and Control

arXiv 1810.10132 ↗First posted 23 Oct 2018cs.LG cs.DS math.OCcited by 26

Not on the map. Why?

Abstract (arXiv)

We consider Online Convex Optimization (OCO) in the setting where the costs are m-strongly convex and the online learner pays a switching cost for changing decisions between rounds. We show that the recently proposed Online Balanced Descent (OBD) algorithm is constant competitive in this setting, with competitive ratio 3 + O(1/m), irrespective of the ambient dimension. Additionally, we show that when the sequence of cost functions is ε-smooth, OBD has near-optimal dynamic regret and maintains strong per-round accuracy. We demonstrate the generality of our approach by showing that the OBD framework can be used to construct competitive algorithms for a variety of online problems across learning and control, including online variants of ridge regression, logistic regression, maximum likelihood estimation, and LQR control.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 8; 2022: 10; 2023: 4; 2024: 1; 2025: 1; 2026: 2.

26 papers.

Sort:

  1. 2021Non-stationary Online Learning with Memory and Non-stochastic Controlcited by 33
  2. 2021Revisiting Smoothed Online Learningcited by 29
  3. 2022Optimal Dynamic Regret in Proper Online Learning with Strongly Convex Losses and Beyondcited by 28
  4. 2022Chasing Convex Bodies and Functions with Black-Box Advicecited by 19
  5. 2023Online Label Shift: Optimal Dynamic Regret meets Practical Algorithmscited by 11
  6. 2021Regret-optimal Estimation and Controlcited by 10
  7. 2022Smoothed Online Optimization with Unreliable Predictionscited by 10
  8. 2021Competitive Controlcited by 8
  9. 2022Second Order Path Variationals in Non-Stationary Online Learningcited by 7
  10. 2022Movement Penalized Bayesian Optimization with Application to Wind Energy Systemscited by 7
  11. 2021Online Convex Optimization with Continuous Switching Constraintcited by 6
  12. 2022Smoothed Online Convex Optimization Based on Discounted-Normal-Predictorcited by 6
14 more
  1. 2022Optimal Dynamic Regret in LQR Controlcited by 6
  2. 2022Best of Both Worlds in Online Control: Competitive Ratio and Policy Regretcited by 6
  3. 2021Online Optimization with Feedback Delay and Nonlinear Switching Costcited by 5
  4. 2022Efficient Online Linear Control with Stochastic Convex Costs and Unknown Dynamicscited by 4
  5. 2023Near-Optimal Adversarial Reinforcement Learning with Switching Costscited by 4
  6. 2021Online Learning for Predictive Control with Provable Regret Guaranteescited by 3
  7. 2023Online Convex Optimization with Switching Cost and Delayed Gradientscited by 3
  8. 2022Optimal Competitive-Ratio Controlcited by 2
  9. 2023Best of Both Worlds Guarantees for Smoothed Online Quadratic Optimizationcited by 2
  10. 2026Parameter-free Dynamic Regret: Time-varying Movement Costs, Delayed Feedback, and Memorycited by 2
  11. 2025Online Convex Optimization with Switching Cost with Only One Single Gradient Evaluationcited by 1
  12. 2021Online estimation and control with optimal pathlength regretcited by 0
  13. 2024Capacity Provisioning Motivated Online Non-Convex Optimization Problem with Memory and Switching Costcited by 0
  14. 2026SCaLE: Switching Cost aware Learning and Explorationcited by 0