Research map / Bandits and online learning / Online convex optimization and games
Robust Budget Pacing with a Single Sample
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 |
|---|---|---|---|
| Dual FTRL with target rate estimated from one sample per distribution (instead of T log T samples) | budget pacing / online allocation with time-varying distributions · theoretical regret analysis, Wasserstein-shifted sampling distributions | regret | Helped |
| Learning the empirical optimal dual and directly bidding with it (Algorithm 1) instead of tracking a target via Dual FTRL (ablation) | dual-based bidding with one sample per distribution · Example with Wasserstein-shifted sampling distributions (W ≤ 3ε) | regret | Hurt |
| Using Dual FTRL to track the empirical target consumption sequence instead of the naive dual price | Dual FTRL budget pacing · theoretical regret with sum of Wasserstein distances | regret | Helped |
Closest papers by meaning
- Dynamic Budget Throttling in Repeated Second-Price Auctions (AAAI 2024 · similarity 0.89)
- Interference Among First-Price Pacing Equilibria: A Bias and Variance Analysis (ICLR 2025 · similarity 0.87)
- Online Resource Allocation With General Constraints (NeurIPS 2026 · similarity 0.86)
- Percentile Risk-Constrained Budget Pacing for Guaranteed Display Advertising in Online Optimization (AAAI 2024 · similarity 0.85)
- Toward Optimal Regret in Robust Pricing: Decoupling Corruption and Time (NeurIPS 2026 · similarity 0.85)
- Non-stochastic Budgeted Online Pricing with Semi-Bandit Feedback (AAAI 2025 · similarity 0.84)
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.