FastPart: Over-Parameterized Stochastic Gradient Descent for Sparse optimisation on Measures
원문 초록
This paper presents a novel algorithm that leverages Stochastic Gradient Descent strategies in conjunction with Random Features to augment the scalability of Conic Particle Gradient Descent (CPGD) specifically tailored for solving sparse optimisation problems on measures. By formulating the CPGD steps within a variational framework, we provide rigorous mathematical proofs demonstrating the following key findings: (i) The total variation norms of the solution measures along the descent trajectory remain bounded, ensuring stability and preventing undesirable divergence; (ii) We establish a global convergence guarantee with a convergence rate of $\mathcal{O}(\log(K)/\sqrt{K})$ over $K$ iterations, showcasing the efficiency and effectiveness of our algorithm; (iii) Additionally, we analyze and establish local control over the first-order condition discrepancy, contributing to a deeper understanding of the algorithm's behavior and reliability in practical applications.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
StepProof: Step-by-step verification of natural language mathematical proofs
A Theoretical Analysis of Compositional Generalization in Neural Networks: A Necessary and Sufficient Condition
Hierarchical Attention Generates Better Proofs
Distance-Adaptive Quaternion Knowledge Graph Embedding with Bidirectional Rotation
Learning Rules Explaining Interactive Theorem Proving Tactic Prediction
ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian Splattings
토론
이 논문과 연결된 포럼 글이 아직 없습니다.