AI Paper Atlas

Research map / Bandits and online learning / Online convex optimization and games

Online allocation with constraints

Solve online allocation and knapsack problems using dual mirror descent and primal-dual methods.

77 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Online convex optimization and games, keyword cluster “price · pricing · auctions”

State History Tried Checklist 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.

20 papers in 2023–24 and 24 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic held steady, from 8.7% to 8.7%.

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

2016: 1162017: 3172018: 5182019: 2192020: 5202021: 9212022: 8222023: 12232024: 8242025: 11252026: 1326

Most cited paper of each year

Earliest papers here

What has been tried

56 papers here report 299 measured changes (a component added, removed or swapped, compared with a baseline): helped 67%, no clear effect 8%, hurt 18%, mixed 7%. Papers mostly publish changes that helped, so "helped" is over-represented.

Ablations in recent papers

What was changedMeasured onResultEffectPaper
Remove KWA's fill-up logicExact total weight · competitive ratioW( 1/e (U−L)/L ) + 1 -> ln(U/L) + 1HurtAugmenting Online Algorithms for Knapsack Problem with Total Weight Information (AAAI 2025 · 0 citations)
Set ETCO exploration length to T^(2/3)(K ln T)^(1/3)Bandit matching, small gaps · α-approximation stable regretO((K ln T)^(1/3) T^(2/3))HelpedStable Matching with Ties: Approximation Ratios and Learning (NeurIPS 2025 · 0 citations)
use learning rate η=10^-3 instead of η=10^-2AI inference provisioning, u3=3.5 · Total Cost237.07 -> 246.36HurtFairness-Regularized Online Optimization with Switching Costs (NeurIPS 2025 · 0 citations)
use negative entropy potential instead of squared ℓ2 potentialAssignment problem, ε=1 across n=800, 1500, 3000 · optimality gap (%)1.8±3.9 -> 2.1±4.0; 4.3±3.4 -> 6.0±4.1; 4.3±5.1 -> 10.4±5.2HurtNoisy Dual Mirror Descent: A Near Optimal Algorithm for Jointly-DP Convex Resource Allocation (NeurIPS 2024 · 0 citations)

What reviewers will expect

Datasets and baselines named in the 17 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.

Baselines

  • Hedge · 2 of 17 papers

Recent preprints

Loading recent arXiv preprints…

    Who publishes on it

    Institutions on the most papers of this approach since 2023 (of 44 papers; from OpenAlex and the papers' affiliations).

    Use it

    Download BibTeX of 40 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.

    Same keyword cluster

    Elsewhere in the topic

    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).

    Get the next scime Dispatch and a monthly field update

    Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy