A general recipe for data-adaptive anytime-valid envelopes for iterative algorithms
원문 초록
Most convergence guarantees for iterative stochastic algorithms are stated at a fixed iteration count and do not justify stopping at a data-dependent time. Recent anytime-valid envelopes do, but deterministic ones are typically too conservative for practical stopping, and existing data-adaptive ones are derived case-by-case, each concerned with a specific algorithm and a specific noise model and boundary construction. This paper provides a general recipe for sharp, data-adaptive anytime-valid envelopes for a large class of iterative algorithms. Our approach has two key steps: an optimization module derives a one-step recursion that performance measures of many such algorithms satisfy, reducing the error analysis to time-uniform concentration for predictably weighted sums of noise. Then, a statistical module ports the sub-$\psi$ condition to vector-valued processes, uniformly over predictable weights, and derives off-the-shelf boundaries via mixtures, stitching, and product betting martingales. Combining the two yields readymade envelopes for many iterative algoithms including but not limited to stochastic gradient descent (SGD), Oja's algorithm, temporal difference learning, Q-learning, and Bures-Wasserstein SGD, many with no prior data-adaptive anytime-valid guarantees. Specifically, for SGD, our framework recovers, often under weaker conditions, or significantly sharpens every existing envelope we are aware of. Our constructions come with explicit implementation details and are substantiated by numerical experiments.
제출 이력
확인된 버전만 표시합니다. 전체 제출 이력은 arXiv 원문에서 확인하세요.
- arXiv:2610.23570v2제출 시각 미확인
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
공통 태그로 연결된 공개 논문이 아직 없습니다.
토론
이 논문과 연결된 포럼 글이 아직 없습니다.