Science Explorer Back to mapMap
Discussion
Topic · Management Science and Operations Research

Advanced Bandit Algorithms Research

Advanced Bandit Algorithms Research is a research topic within Management Science and Operations Research. Science Explorer counts 8.2k research works in it since 1956. 10.2% of them reached the world's top 10% most cited for their field and year.

This cluster of papers focuses on the optimization of multi-armed bandit problems, including topics such as Bayesian optimization, contextual bandits, online learning, convex optimization, Thompson sampling, regret analysis, Gaussian process optimization, hyperparameter optimization, and adversarial multi-armed bandits.

  • Bandit Optimization
  • Bayesian Optimization
  • Contextual Bandits
  • Online Learning
  • Convex Optimization
  • Thompson Sampling
  • Regret Analysis
  • Gaussian Process Optimization
  • Hyperparameter Optimization
  • Adversarial Multi-Armed Bandits
Research works
8.2k
fractional, since 1956
In the world top 10%
829
per year above
Top-10% rate
10.2%
share of its works in the world top 10%
Growth, 2018-21 → 2022-25
+19%
the tick is no change
Largest producer
China
37% of the 10 largest, 2022-now
Advanced Bandit Algorithms Research

Which countries lead Advanced Bandit Algorithms Research research?

By volume, China and the United States publish the most (849 and 786 works in 2022-now).

By volume, 2022-now

  1. 1 China 849 works
  2. 2 United States 786 works
  3. 3 India 158 works
  4. 4 United Kingdom 104 works
  5. 5 France 82 works
  6. 6 Germany 78 works
  7. 7 Canada 70 works
  8. 8 Italy 66 works
  9. 9 Japan 65 works
  10. 10 Australia 54 works

How concentrated that is

The same countries as shares of everything the list above accounts for. A node where two countries do two thirds of the work and one spread evenly across twelve read alike as a ranking and not at all alike here.

China: 36.7%United States: 34.0%India: 6.8%United Kingdom: 4.5%6 others listed: 17.9%37%largest
China849 · 36.7%United States786 · 34.0%India158 · 6.8%United Kingdom104 · 4.5%6 others listed415 · 17.9%

Shares of the rows listed above, not of the whole node.

Which institutions lead Advanced Bandit Algorithms Research research?

By volume in 2022-now, American Society of Genealogists publishes the most Advanced Bandit Algorithms Research research, followed by Tsinghua University and Shanghai Jiao Tong University.

By volume, 2022-now

  1. 1 American Society of GenealogistsUnited States 39 works
  2. 2 Tsinghua UniversityChina 34 works
  3. 3 Shanghai Jiao Tong UniversityChina 29 works
  4. 4 Alphabet (United States)United States 27 works
  5. 5 Centre National de la Recherche ScientifiqueFrance 24 works
  6. 6 Chinese Academy of SciencesChina 22 works
  7. 7 Cornell UniversityUnited States 22 works
  8. 8 Carnegie Mellon UniversityUnited States 20 works
  9. 9 University of Illinois Urbana-ChampaignUnited States 19 works
  10. 10 Stanford UniversityUnited States 19 works

Who are the leading researchers in Advanced Bandit Algorithms Research?

The most-cited researchers publishing on Advanced Bandit Algorithms Research include Yoshua Bengio, Kai You Wang and David H. Haussler.

  1. 1 Yoshua Bengio Canada 476k citations
  2. 2 Kai You Wang China 224k citations
  3. 3 David H. Haussler United States 209k citations
  4. 4 Demis Hassabis United Kingdom 199k citations
  5. 5 Jürgen Schmidhuber Switzerland 188k citations
  6. 6 Michael I. Jordan United States 182k citations
  7. 7 Oriol Vinyals United States 177k citations
  8. 8 Kalyanmoy Deb United States 171k citations
  9. 9 David Lawrence Silver United Kingdom 168k citations
  10. 10 Koray Kavukcuoglu United States 168k citations

Ranked by citations received across their whole record, among researchers with at least three works on this topic.

What are the most cited papers in Advanced Bandit Algorithms Research?

The most cited paper in Advanced Bandit Algorithms Research is "Adam: A Method for Stochastic Optimization" (Diederik P. Kingma, Jimmy Lei Ba, 2014), with 84,625 citations. Next come "A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting" (20,713) and "No free lunch theorems for optimization" (14,318).

Most cited papers
#PaperReleasedCitations
1 Adam: A Method for Stochastic Optimization Diederik P. Kingma, Jimmy Lei Ba · arXiv (Cornell University) PreprintOpen access 22 Dec 2014 84,625
2 A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting Yoav Freund, Robert E. Schapire · Journal of Computer and System Sciences Open access Aug 1997 20,713
3 No free lunch theorems for optimization David H. Wolpert, William G. Macready · IEEE Transactions on Evolutionary Computation Apr 1997 14,318
4 Diagnosing Non-Intermittent Anomalies in Reinforcement Learning Policy Executions (Short Paper) Esper, Khalil, Spieck, Jan, Sixdenier, Pierre-Louis et al. · arXiv (Cornell University) PreprintOpen access 20 Jul 2017 11,361
5 Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions Gediminas Adomavičius, Alexander Tuzhilin · IEEE Transactions on Knowledge and Data Engineering 25 Apr 2005 10,402
All 99 most cited papers, with filters and sorting

Where is Advanced Bandit Algorithms Research research done?

The largest centres of Advanced Bandit Algorithms Research research in 2022-now are Beijing (China), Shanghai (China), Shenzhen (China) and Nanjing (China). Among places with at least 20 works in it, it is an unusually large share of all research in Sharon, Mountain View and Ithaca.

Largest cities, 2022-now

  1. 1 BeijingChina 176 works
  2. 2 ShanghaiChina 89 works
  3. 3 ShenzhenChina 63 works
  4. 4 NanjingChina 48 works
  5. 5 Hong KongChina 46 works
  6. 6 SingaporeSingapore 42 works
  7. 7 New YorkUnited States 40 works
  8. 8 SharonUnited States 39 works
  9. 9 GuangzhouChina 39 works
  10. 10 HangzhouChina 38 works

Where it is the local speciality

  1. SharonUS · 38.7 works133×
  2. Mountain ViewUS · 20.0 works14×
  3. IthacaUS · 21.7 works7.5×
  4. ShenzhenCN · 63.1 works6.7×
← less than its size predicts1×more →

Location quotient: how much more of its research is in Advanced Bandit Algorithms Research than the world average.

See Advanced Bandit Algorithms Research on the map

Where is the best place to study Advanced Bandit Algorithms Research?

Among universities, judged by research, Renmin University of China, City University of Hong Kong and University of Science and Technology of China score highest, combining excellence, specialisation, size, growth and international reach. Research strength is one signal when choosing where to study; it does not measure teaching.

0%10%20%30%mean 21.6%fractional works in this field (log) →share of work in the world top 10% →City University of H…University of Scienc…Renmin University of…Tsinghua University
above the meannear itbelow it

One dot per university in the first ten of the table below, at the default weights. The upper left is the interesting corner: small places doing unusually strong work.

Excellenceshare of its work in the world top 10%, 2022-now and all time averaged
40%
Specialisationhow much of its work is in this field, counted up to 10× the world share
10%
Sizeits output in this field, on a log scale
30%
Growthoutput growth, counted from -20% to +20%
10%
Internationalshare of its work with a co-author abroad
10%
Each slider sets a weight; the share it gets of the score is beside it.
#UniversityScoreTop 10%SpecialisationWorksGrowth
1Renmin University of ChinaChina 71.323.5%19.5×15 +462.4%
2City University of Hong KongChina 68.824.8%8.8×12 +214.0%
3University of Science and Technology of ChinaChina 67.823.8%6.6×19 +38.3%
4Tsinghua UniversityChina 66.215.8%6.0×34 +12.5%
5Nanyang Technological UniversitySingapore 59.526.4%5.8×11 -4.6%
6Northeastern UniversityChina 58.225.7%4.2×9 +194.3%
7Shanghai Jiao Tong UniversityChina 57.111.7%4.2×30 +60.0%
8University of Technology SydneyAustralia 56.426.8%8.5×9 -6.3%
9Peking UniversityChina 53.517.2%3.3×16 +48.7%
10Zhejiang UniversityChina 53.320.3%2.3×15 +103.4%

Universities only. The score blends excellence (40%), size (30%), specialisation (10%), growth (10%), international reach (10%), 2022-now; growth compares 2018-21 with 2022-25 and counts up to +20%, since a jump from a small base is mostly noise.

Every institution in Advanced Bandit Algorithms Research, country by country

Is Advanced Bandit Algorithms Research research growing?

Output in 2022-2025 was 19% higher than in 2018-2021, peaking in 2023. The fastest-growing topics are Advanced Bandit Algorithms Research.

still counting19801990200020102020
grewheldshrank

The same series as a ribbon: one cell per year, darker for more. The line above answers how much; this answers when.

Its share of all research

Growing output can still be a shrinking share: all of science grows. This is Advanced Bandit Algorithms Research as a percentage of every work published that year, 0.0097% in 2024.

still counting0.0050%0.010%0.015%Advanced Bandit Algorithms Research0.010% in 202519801990200020102020

Fractional works of Advanced Bandit Algorithms Research over all fractional works that year. How the balance of science has shifted.

How much of it reaches the world top 10%

Year by year.

still counting5%10%15%Advanced Bandit Algorithms Research10.2% in 2025200020102020

Of each year's works in it, the share that reached the world's 10% most cited for their field and year. A field is the world for its own topics, so there is no other line to hold it against.

Which topics inside it are moving

Growth and decline on one axis around a shared zero. Two lists side by side hide the thing that matters: whether the growth dwarfs the decline, or the other way round.

Discussion

Ask a question or share a note about Advanced Bandit Algorithms Research. Posts are plain text and can be reported.