paper-with-me

홈 › Papers

Token Complexity of Certifying Stochastic-Oracle Reliability

2026-06-23 · Jie Wang arxiv

Wang~\cite{Wang2026} introduced the Stochastic-Oracle Turing Machine (SOTM) framework and defined token complexity as the minimum expected cost of interacting with a stochastic oracle needed to attain a specified solution quality for a task. This paper develops an analogous notion for certifying the reliability of a stochastic oracle on a given domain. Certification token complexity is the minimum expected token cost required, with controlled error probability, to distinguish oracles that meet a target reliability level from those that fall below a lower reliability threshold. We construct an SPRT-based certification SOTM that queries the oracle, computes binary correctness scores, and stops when the accumulated log-likelihood evidence crosses a decision threshold. The SOTM halts almost surely, satisfies the desired two-sided error guarantee over the reliability regions to be certified, and yields an explicit upper bound on certification token complexity in terms of the reliability thresholds, the error bound, and the expected per-turn token cost. We then establish a matching information-theoretic lower bound: even with adaptive queries, every error-bounded certification SOTM must incur the same leading-order expected token cost as the SPRT-based construction as the prescribed error bound tends to zero. Together, these bounds characterize the leading-order certification token complexity in the small-error regime.

📄 PDF Abstract BibTeX arXiv:2606.24074

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Token Complexity Theory for AI-Augmented Computing

2026-06-10 · Jie Wang arxiv

AI-augmented computing delegates natural language queries, code generation requests, and other open-ended tasks to a cluster of AI models that processes queries and generates responses. This paradigm introduces a resourc…

Natural Language QueriesCode Generation

The Complexity of Making the Gradient Small in Stochastic Convex Optimization

2019-02-13 · Dylan J. Foster, Ayush Sekhari, Ohad Shamir, Nathan Srebro 외

We give nearly matching upper and lower bounds on the oracle complexity of finding $\epsilon$-stationary points ($\| \nabla F(x) \| \leq\epsilon$) in stochastic convex optimization. We jointly analyze the oracle complexi…

Stochastic Optimization

Unified High-Probability Analysis of Stochastic Variance-Reduced Estimation

2026-05-14 · Zhankun Luo, Antesh Upadhyay, M. Berk Sahin, Sang Bin Moon 외 arxiv

Stochastic estimators are fundamental to large-scale optimization, where population quantities must be inferred from noisy oracle observations. Although influential methods such as momentum, SPIDER, STORM, and PAGE have …

Stochastic Optimization

Oracle-Efficient Algorithms for Online Linear Optimization with Bandit Feedback

2019-12-01 · NeurIPS 2019 12 · Shinji Ito, Daisuke Hatano, Hanna Sumita, Kei Takemura 외

We propose computationally efficient algorithms for \textit{online linear optimization with bandit feedback}, in which a player chooses an \textit{action vector} from a given (possibly infinite) set $\mathcal{A} \subsete…

Computational Efficiency

Optimal Algorithms for Convex Nested Stochastic Composite Optimization

2020-11-19 · Zhe Zhang, Guanghui Lan

Recently, convex nested stochastic composite optimization (NSCO) has received considerable attention for its applications in reinforcement learning and risk-averse optimization. The current NSCO algorithms have worse sto…

Stochastic Optimization