Multi-task and Lifelong Learning of Kernels
원문 초록
We consider a problem of learning kernels for use in SVM classification in the multi-task and lifelong scenarios and provide generalization bounds on the error of a large margin classifier. Our results show that, under mild conditions on the family of kernels used for learning, solving several related tasks simultaneously is beneficial over single task learning. In particular, as the number of observed tasks grows, assuming that in the considered family of kernels there exists one that yields low approximation error on all tasks, the overhead associated with learning such a kernel vanishes and the complexity converges to that of learning when this good kernel is given to the learner.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Dynamic Mixture of Progressive Parameter-Efficient Expert Library for Lifelong Robot Learning
Learning Where to Learn: Training Distribution Selection for Provable OOD Performance
Operator Learning for Schrödinger Equation: Unitarity, Error Bounds, and Time Generalization
LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarios
UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Large Language Models
LiBOG: Lifelong Learning for Black-Box Optimizer Generation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.