$\left( β, \varpi \right)$-stability for cross-validation and the choice of the number of folds
원문 초록
In this paper, we introduce a new concept of stability for cross-validation, called the $\left( \beta, \varpi \right)$-stability, and use it as a new perspective to build the general theory for cross-validation. The $\left( \beta, \varpi \right)$-stability mathematically connects the generalization ability and the stability of the cross-validated model via the Rademacher complexity. Our result reveals mathematically the effect of cross-validation from two sides: on one hand, cross-validation picks the model with the best empirical generalization ability by validating all the alternatives on test sets; on the other hand, cross-validation may compromise the stability of the model selection by causing subsampling error. Moreover, the difference between training and test errors in q\textsuperscript{th} round, sometimes referred to as the generalization error, might be autocorrelated on q. Guided by the ideas above, the $\left( \beta, \varpi \right)$-stability help us derivd a new class of Rademacher bounds, referred to as the one-round/convoluted Rademacher bounds, for the stability of cross-validation in both the i.i.d.\ and non-i.i.d.\ cases. For both light-tail and heavy-tail losses, the new bounds quantify the stability of the one-round/average test error of the cross-validated model in terms of its one-round/average training error, the sample sizes $n$, number of folds $K$, the tail property of the loss (encoded as Orlicz-$\Psi_\nu$ norms) and the Rademacher complexity of the model class $\Lambda$. The new class of bounds not only quantitatively reveals the stability of the generalization ability of the cross-validated model, it also shows empirically the optimal choice for number of folds $K$, at which the upper bound of the one-round/average test error is lowest, or, to put it in another way, where the test error is most stable.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
완전 오프라인 강화학습
Fully Offline Reinforcement Learning
오프라인 강화학습(ORL)은 안전하고 샘플 효율적인 배포를 약속하지만, 기존 방법들은 하이퍼파라미터 튜닝을 위해 문서화되지 않은 온라인 상호작용에 의존하며 초기 온라인 성능에 대한 신뢰할 수 있는 완전 오프라인 추정치가 부족하다. 우리는 동역학에 대한 사후분포를 학습하고, 예측 불확실성을 통해 정책 가치를 추정하며, 완전한 오프라인 하이퍼파라미터 선택을 가능하게 하는 완전 오프라인 베이지안 모델 기반 강화학습 방법 SOReL을 제안한다. 또한 이 튜닝 프레임워크를 임의의 모델-프리 및 모델 기반 ORL 알고리즘으로 확장하는 TOReL을 제안한다. 표준 정규성 조건 하에서 베이지안 오프라인 강화학습이 minimax-최적 파라미터적 수렴률을 달성함을 보이는 후회(regret) 분석을 제공한다. 이를 통해 우리의 방법들은 완전 오프라인 강화학습을 위한 실용적이고 이론적으로 근거 있는 프레임워크를 확립한다.
mTSBench: Benchmarking Multivariate Time Series Anomaly Detection and Model Selection at Scale
Leveraging Predictive Equivalence in Decision Trees
The use of cross validation in the analysis of designed experiments
Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning
Tuning the Right Foundation Models is What you Need for Partial Label Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.