Research map / Optimization / Optimizers
An Efficient Algorithm for Deep Stochastic Contextual Bandits
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use SSGD-SCB instead of DeepFPL | Deep stochastic contextual bandits with a VGG-11 variant · CIFAR-10, 5×10⁴ rounds | elapsed time (seconds): 21.52 ± 0.05 -> 15.25 ± 0.08 | Helped |
| Use SSGD-SCB instead of Neural Linear | Deep stochastic contextual bandits with a VGG-11 variant · CIFAR-10, 5×10⁴ rounds | elapsed time (seconds): 35.92 ± 0.11 -> 15.25 ± 0.08 | Helped |
| Use SSGD-SCB instead of DeepFPL | Deep stochastic contextual bandits with a VGG-11 variant · CIFAR-10+N, 5×10⁴ rounds | elapsed time (seconds): 33.89 ± 0.11 -> 15.25 ± 0.08 | Helped |
| Use SSGD-SCB instead of Neural Linear | Deep stochastic contextual bandits with a VGG-11 variant · CIFAR-10+N, 5×10⁴ rounds | elapsed time (seconds): 36.02 ± 0.04 -> 15.25 ± 0.08 | Helped |
| Use SSGD-SCB instead of the tested SCB baselines | Deep stochastic contextual bandits · CIFAR-10 | average cumulative regret | Helped |
| Use SSGD-SCB instead of the tested SCB baselines | Deep stochastic contextual bandits · CIFAR-10+N | average cumulative regret | Helped |
| Use SSGD-SCB instead of the tested SCB baselines | Deep stochastic contextual bandits · CIFAR-10 | out-of-sample MSE | Helped |
| Use SSGD-SCB instead of the tested SCB baselines | Deep stochastic contextual bandits · CIFAR-10+N | top-1 test accuracy | Helped |
Closest papers by meaning
- Neural Contextual Bandits with UCB-based Exploration (ICML 2020 · similarity 0.91)
- Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits (ICML 2024 · similarity 0.89)
- Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates (NeurIPS 2024 · similarity 0.88)
- Stochastic Bandits with ReLU Neural Networks (ICML 2024 · similarity 0.88)
- Neural Dueling Bandits: Preference-Based Optimization with Human Feedback (ICLR 2025 · similarity 0.88)
- An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction (NeurIPS 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.