PyTorchKR Papers

최신 논문

총 2편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2607.06367v1math.ST

정규 평균 추정에서 수축-임계값 규칙에 대한 근사 위험 최소화

Approximate Risk Minimization Over Shrinking-Thresholding Rules in Normal Mean Estimation

정규 평균 추정에서 James-Stein형과 lasso형 규칙을 통합하는 일반 수축-임계값 추정량 클래스(GEST)를 도입하고, 오라클 위험을 사용할 수 없을 때 관측 데이터 기반의 근사 위험 기준을 최소화하는 추정량 NOMAD를 제안한다. 이 프레임워크는 표준 및 상관 다변량 정규 평균 추정과 선형 회귀에 걸쳐 수축, 임계값 처리, 정규화를 통합하며, 일관성 및 근사 위험 부등식 이론을 수립한다.

arXiv:2511.22823v2cs.LG

A Unified and Stable Risk Minimization Framework for Weakly Supervised Learning with Theoretical Guarantees

Weakly supervised learning has emerged as a practical alternative to fully supervised learning when complete and accurate labels are costly or infeasible to acquire. However, many existing methods are tailored to specific supervision patterns -- such as positive-unlabeled (PU), unlabeled-unlabeled (UU), complementary-label (CLL), partial-label (PLL), or similarity-unlabeled annotations -- and rely on post-hoc corrections to mitigate instability induced by indirect supervision. We propose a principled, unified framework that bypasses such post-hoc adjustments by directly formulating a stable surrogate risk grounded in the structure of weakly supervised data. The formulation naturally subsumes diverse settings -- including PU, UU, CLL, PLL, multi-class unlabeled, and tuple-based learning -- under a single optimization objective. We further establish a non-asymptotic generalization bound via Rademacher complexity that clarifies how supervision structure, model capacity, and sample size jointly govern performance. Beyond this, we analyze the effect of class-prior misspecification on the bound, deriving explicit terms that quantify its impact, and we study identifiability, giving sufficient conditions -- most notably via supervision stratification across groups -- under which the target risk is recoverable. Extensive experiments show consistent gains across class priors, dataset scales, and class counts -- without heuristic stabilization -- while exhibiting robustness to overfitting.