Research map / Bandits and online learning / Online convex optimization and games
Dynamic and adaptive regret
Reduce and bound dynamic and adaptive regret for convex and smooth losses.
57 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Online convex optimization and games, keyword cluster “convex optimization · online convex · functions”
State History Tried Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
14 papers in 2023–24 and 16 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic held steady, from 6.1% to 5.8%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2016 · Tracking Slowly Moving Clairvoyant: Optimal Dynamic Regret of Online Learning with True and Noisy Gradient (ICML 2016 · 17 citations)
- 2017 · Improved Dynamic Regret for Non-degenerate Functions (NeurIPS 2017 · 66 citations)
- 2018 · Adaptive Online Learning in Dynamic Environments (NeurIPS 2018 · 70 citations)
- 2019 · Logarithmic Regret for Online Control (NeurIPS 2019 · 47 citations)
- 2020 · A new regret analysis for Adam-type algorithms (ICML 2020 · 22 citations)
- 2021 · On Online Optimization: Dynamic Regret Analysis of Strongly Convex and Smooth Problems (AAAI 2021 · 15 citations)
- 2022 · Optimal Dynamic Regret in LQR Control (NeurIPS 2022 · 2 citations)
- 2023 · A General Regret Bound of Preconditioned Gradient Method for DNN Training (CVPR 2023 · 3 citations)
- 2024 · Cumulative Regret Analysis of the Piyavskii–Shubert Algorithm and Its Variants for Global Optimization (AAAI 2024 · 2 citations)
- 2025 · On the Dynamic Regret of Following the Regularized Leader: Optimism with History Pruning (ICML 2025 · 0 citations)
- 2026 · A Perturbation Approach to Unconstrained Linear Bandits (ICML 2026 · 0 citations)
Earliest papers here
- Tracking Slowly Moving Clairvoyant: Optimal Dynamic Regret of Online Learning with True and Noisy Gradient (ICML 2016 · 17 citations)
- Optimistic Bandit Convex Optimization (NeurIPS 2016 · 14 citations)
- Improved Dynamic Regret for Non-degenerate Functions (NeurIPS 2017 · 66 citations)
What has been tried
34 papers here report 165 measured changes (a component added, removed or swapped, compared with a baseline): helped 72%, no clear effect 7%, hurt 13%, mixed 8%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Choose the interval midpoint as the candidate instead of the lowest possible-value point | Lipschitz continuous and Lipschitz smooth functions · cumulative regret | No clear effect | Cumulative Regret Analysis of the Piyavskii–Shubert Algorithm and Its Variants for Global Optimization (AAAI 2024 · 2 citations) | |
| use uniform distribution for the observation query instead of StABL's designed distribution | Learning from expert advice, volatile environments · moving-average reward | Hurt | Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 2024 · 0 citations) |
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 30 papers; from OpenAlex and the papers' affiliations).
- Princeton University · 3 papers
- Boston University · 3 papers
- Carnegie Mellon University · 2 papers
- Google · 2 papers
- University of Alberta · 2 papers
- Nanjing University · 2 papers
- University of Milan · 2 papers
- Tsinghua University · 2 papers
Use it
Download BibTeX of 39 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Constrained and unconstrained OCO algorithms (85 papers)
- Parameter-free non-stationary online learning (45 papers)
Elsewhere in the topic
- Online learning with feedback graphs (155 papers)
- Best-of-both-worlds bandit algorithms (125 papers)
- Learning for pricing and auctions (101 papers)
- Online decision-making with feedback structure (81 papers)
- Online allocation with constraints (77 papers)
- Learning-augmented online algorithms (73 papers)
- Last-iterate convergence in games (65 papers)
- Fast no-regret dynamics in games (37 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).