Distributed Learning via Filtered Hyperinterpolation on Manifolds
원문 초록
Learning mappings of data on manifolds is an important topic in contemporary machine learning, with applications in astrophysics, geophysics, statistical physics, medical diagnosis, biochemistry, 3D object analysis. This paper studies the problem of learning real-valued functions on manifolds through filtered hyperinterpolation of input-output data pairs where the inputs may be sampled deterministically or at random and the outputs may be clean or noisy. Motivated by the problem of handling large data sets, it presents a parallel data processing approach which distributes the data-fitting task among multiple servers and synthesizes the fitted sub-models into a global estimator. We prove quantitative relations between the approximation quality of the learned function over the entire manifold, the type of target function, the number of servers, and the number and type of available samples. We obtain the approximation rates of convergence for distributed and non-distributed approaches. For the non-distributed case, the approximation order is optimal.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
AI-Driven Cytomorphology Image Synthesis for Medical Diagnostics
MAM: Modular Multi-Agent Framework for Multi-Modal Medical Diagnosis via Role-Specialized Collaboration
AMQA: An Adversarial Dataset for Benchmarking Bias of LLMs in Medicine and Healthcare
Backward Conformal Prediction
Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum
MedCaseReasoning: Evaluating and learning diagnostic reasoning from clinical case reports
토론
이 논문과 연결된 포럼 글이 아직 없습니다.