Research map / Bandits and online learning / Online convex optimization and games
Learning Resource Allocation and Pricing for Cloud Profit Maximization
Bingqian Du, Chuan Wu, Zhiyi Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add LSTM history module to DDPG for non-Markovian arrivals (ablation) | DDPG · Azure trace validation | profit: 25% more profit | Improved |
| add LSTM history module to DDPG (ablation) | DDPG · Azure trace validation | accepted users: 5% more | Improved |
| use DRL (LAPP) instead of online primal-dual pricing baselines RPD2/TI/TC | cloud pricing and placement · Azure trace validation | profit: at least 40% | Improved |
| use DRL (LAPP) instead of RPD2 | cloud pricing and placement · Azure trace, Pareto budgets | accepted users | Hurt |
| use LAPP instead of online algorithms in a worst-case request sequence | cloud pricing and placement · Worst-case scenario | profit: about 30% | Improved |
| use LAPP instead of baselines with heterogeneous servers | cloud pricing and placement · Heterogeneous servers | profit: at least 25% | Improved |
Closest papers by meaning
- Test-Time Compute Games (NeurIPS 2026 · similarity 0.82)
- Learning to price with resource constraints: from full information to machine-learned prices (NeurIPS 2025 · similarity 0.82)
- Near-Optimal Regret-Queue Length Tradeoff in Online Learning for Two-Sided Markets (NeurIPS 2025 · similarity 0.82)
- Non-Linear Pricing Restores Tractability for a Data Seller (NeurIPS 2026 · similarity 0.82)
- Compute-Optimal Scaling for Value-Based Deep RL (NeurIPS 2025 · similarity 0.81)
- Value-Based Deep RL Scales Predictably (ICML 2025 · similarity 0.81)
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.
