Hellinger-Kantorovich Gradient Flows: Global Exponential Decay of Entropy Functionals
원문 초록
We investigate a family of gradient flows of positive and probability measures, focusing on the Hellinger-Kantorovich (HK) geometry, which unifies transport mechanism of Otto-Wasserstein, and the birth-death mechanism of Hellinger (or Fisher-Rao). A central contribution is a complete characterization of global exponential decay behaviors of entropy functionals (e.g. KL, $\chi^2$) under Otto-Wasserstein and Hellinger-type gradient flows. In particular, for the more challenging analysis of HK gradient flows on positive measures -- where the typical log-Sobolev arguments fail -- we develop a specialized shape-mass decomposition that enables new analysis results. Our approach also leverages the (Polyak-)\L{}ojasiewicz-type functional inequalities and a careful extension of classical dissipation estimates. These findings provide a unified and complete theoretical framework for gradient flows and underpin applications in computational algorithms for statistical inference, optimization, and machine learning.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Brevity is the soul of sustainability: Characterizing LLM response lengths
Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints
SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL
A Survey on Inference Optimization Techniques for Mixture of Experts Models
A Temporal Linear Network for Time Series Forecasting
LLM-Rank: A Graph Theoretical Approach to Pruning Large Language Models
토론
이 논문과 연결된 포럼 글이 아직 없습니다.