Gradient Descent-Type Methods: Background and Simple Unified Convergence Analysis
원문 초록
In this book chapter, we briefly describe the main components that constitute the gradient descent method and its accelerated and stochastic variants. We aim at explaining these components from a mathematical point of view, including theoretical and practical aspects, but at an elementary level. We will focus on basic variants of the gradient descent method and then extend our view to recent variants, especially variance-reduced stochastic gradient schemes (SGD). Our approach relies on revealing the structures presented inside the problem and the assumptions imposed on the objective function. Our convergence analysis unifies several known results and relies on a general, but elementary recursive expression. We have illustrated this analysis on several common schemes.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesis
Revisiting Deep Learning for Variable Type Recovery
Mask Detection and Classification in Thermal Face Images
TypeT5: Seq2seq Type Inference using Static Analysis
Safe-DS: A Domain Specific Language to Make Data Science Safe
Mind Reasoning Manners: Enhancing Type Perception for Generalized Zero-shot Logical Reasoning over Text
토론
이 논문과 연결된 포럼 글이 아직 없습니다.