arXiv Machine Learning
Prediction-Assisted Pricing and Admission for LLM APIs with Stochastic Token Consumption
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jul 14
From Confounding to Learning: Dynamic Service Fee Pricing on Third-Party Platforms
arXiv:2512. 22749v2 Announce Type: replace Abstract: We study the pricing behavior of third-party platforms facing strategic agents.
arXiv Machine Learning
Jul 28
On Non-Stationary Dynamic Pricing: Adaptivity and Optimality
arXiv:2607. 24115v1 Announce Type: cross Abstract: We study the contextual dynamic pricing problem under non-stationarity, where a firm sells products to $T$ sequentially arriving consumers that behave according to an unknown demand model that can change over time.
arXiv AI
Jun 17
Online LLM Selection via Constrained Bandits with Time-Varying Demand
arXiv:2606. 17489v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed in edge-cloud inference systems to handle diverse user tasks with heterogeneous accuracy, latency, and cost profiles.
arXiv Machine Learning
Aug 24
Adaptive Inference for Resource-Constrained Dynamic Pricing
arXiv:2606. 03736v2 Announce Type: replace-cross Abstract: We study resource-constrained dynamic pricing when the seller seeks revenue and valid inference about demand at a price fixed before the selling season.
arXiv AI
Sep 2
Drift-Aware LLM Routing with Sparse Contexts and Shared Budgets
The paper introduces Drift‑Aware Sparse Routing (DRS), a method for routing requests in a multi‑model language service while respecting compute, latency, memory, or cost budgets. DRS estimates reward and resource use from a rolling audit window, routes using pessimistic reward and optimistic cost estimates, updates resource shadow prices online, and applies a hard meter before commitment. The authors provide theoretical regret bounds that separate control from statistics, showing how the method adapts to non‑stationary prompt distributions and model changes.
arXiv Machine Learning
Sep 29
Dynamic Regret in Online Convex Optimization with Indicator Switching Costs
arXiv:2609. 30556v1 Announce Type: new Abstract: We study dynamic regret in online convex optimization with an \emph{indicator switching cost}: a fixed penalty incurred whenever two consecutive decisions differ.