Research map / Bandits and online learning / Online convex optimization and games
When Demands Evolve Larger and Noisier: Learning and Earning in a Growing Environment
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 |
|---|---|---|---|
| Increase growth rate of random fluctuation alpha relative to mean growth gamma (alpha in (gamma/2, gamma+1/2)) in fixed-time setting | fixed-time dynamic pricing policy · growing demand dynamic pricing (theoretical) | regret order exponent | Mixed |
| Knowing the horizon T in advance (fixed-time policy) versus not (any-time policy) | dynamic pricing with growing demand · growing demand dynamic pricing (theoretical) | optimal regret order | Helped |
| Growth rate of random fluctuation alpha > gamma+1/2 | dynamic pricing with growing demand · growing demand dynamic pricing (theoretical) | achievable sublinear regret | Hurt |
| Adding a pure-exploration phase (alternating prices l0 and u0 for T0 steps) before linear-UCB exploitation | fixed-time pricing policy (Algorithm 2) · growing demand dynamic pricing (theoretical) | regret order | Helped |
| Modifying the MAB setting with growing rewards: knowing T or not gives same regret order | multi-armed bandit in growing environment · growing MAB (theoretical) | optimal regret order | No clear effect |
Closest papers by meaning
- Low-Rank Bandit Methods for High-Dimensional Dynamic Pricing (NeurIPS 2019 · similarity 0.89)
- The Power of Menus in Dynamic Pricing: Near Optimal Regret and Equivalence Results (NeurIPS 2026 · similarity 0.89)
- Revenue Maximization Under Sequential Price Competition Via The Estimation Of $s$-Concave Demand Functions (ICLR 2026 · similarity 0.89)
- Optimal Contextual Pricing under Agnostic Non-Lipschitz Demand (NeurIPS 2026 · similarity 0.88)
- Toward Optimal Regret in Robust Pricing: Decoupling Corruption and Time (NeurIPS 2026 · similarity 0.88)
- Learning to price with resource constraints: from full information to machine-learned prices (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.