Bounds on Query Convergence
Barak A. Pearlmutter
Abstract
The problem of finding an optimum using noisy evaluations of a smooth cost function arises in many contexts, including economics, business, medicine, experiment design, and foraging theory. We derive an asymptotic bound E[ (xt - x*)2 ] >= O(1/sqrt(t)) on the rate of convergence of a sequence (x0, x1, >...) generated by an unbiased feedback process observing noisy evaluations of an unknown quadratic function maximised at x*. The bound is tight, as the proof leads to a simple algorithm which meets it. We further establish a bound on the total regret, E[ sumi=1..t (xi - x*)2 ] >= O(sqrt(t)) These bounds may impose practical limitations on an agent's performance, as O(eps-4) queries are made before the queries converge to x* with eps accuracy.
Create a lesson
Related papers
Understanding Evolution Strategies for LLM Reasoning: Broader Reasoning Coverage than GRPO
Yunpeng Ba, Zhi Zheng, Yue Xie et al.
Beyond Parallel Blindness: Information Floors and Model Gaps in Block Drafting
Xinwei Qiang, Xiang Fang, Chang Chen et al.
QuantumBoostNet: A Hybrid Classical-Quantum Architecture for Enhanced Accuracy in Cardiac Ultrasound View Identification
Mihai Udrescu-Milosav, Stefan-Alexandru Jura, Mihai Udrescu et al.
MM-Spectrum: Multimodal Multi-spectral Molecular Structural Elucidation with a Stable MoE Framework
Hai-tao Yu, Nan Min, Zheng Fang et al.
Making Latent Evolution Explicit: Operator-Structured Transitions for World Action Models
Xiaoxiao Lu, Yunlong Dong, Jiahao Shi et al.
Circuit Condensation: Post-Training that Concentrates a Behavior's Causal Circuit
Sai Adith Senthil Kumar