# Regret Minimization on Contextual Combinatorial Bandits

Source: [Regret Minimization on Contextual Combinatorial Bandits](<https://www.sota2.com/research/sota/regret-minimization-on-contextual-combinatorial-bandits>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-27T13:03:33.344Z

Evaluation of algorithms for regret minimization specifically applied to the Contextual Combinatorial Bandits framework, focusing on adversarial and stochastic regret bounds.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Regret Minimization |
| Dataset (including any stated split) | Contextual Combinatorial Bandits |
| Metric | Stochastic Regret |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 3 of 3 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Stochastic Regret](<https://www.sota2.com/research/sota/regret-minimization-on-contextual-combinatorial-bandits.md?metric=Stochastic%20Regret>): Lower is better; unit: SCALAR.

- [Adversarial Regret](<https://www.sota2.com/research/sota/regret-minimization-on-contextual-combinatorial-bandits.md?metric=Adversarial%20Regret>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Stochastic Regret | Result date | Report paper |
| --- | --- | --- | --- |
| Kong et al. (2023) | 2 | Not recorded | 68fa7ae71e209131cea85cf7 |
| FTRL for contextual combinatorial semi-bandits | 3 | Not recorded | 68fa7ae71e209131cea85cf7 |
| Ito et al. (2022) | 3 | Not recorded | 68fa7ae71e209131cea85cf7 |

### Kong et al. (2023)

Stochastic Regret: 2. Result ID: 69c6801347f34ce924b08203.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae71e209131cea85cf7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa701d1e209131cea4920c.md>)

Recorded evaluation configuration: {"Feedback":"Linear bandit"}. This record does not assert independent reproduction.

### FTRL for contextual combinatorial semi-bandits

Stochastic Regret: 3. Result ID: 69c6801347f34ce924b08201.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae71e209131cea85cf7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ae71e209131cea85cf7.md>)

Recorded evaluation configuration: {"Feedback":"Semi-bandit"}. This record does not assert independent reproduction.

### Ito et al. (2022)

Stochastic Regret: 3. Result ID: 69c6801347f34ce924b08202.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae71e209131cea85cf7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e481e209131cea3ef6a.md>)

Recorded evaluation configuration: {"Feedback":"Graph bandit"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
