1 code implementation • 1 Jun 2023 • Lisang Ding, Kexin Jin, Bicheng Ying, Kun Yuan, Wotao Yin
Their communication, governed by the communication topology and gossip weight matrices, facilitates the exchange of model updates.
no code implementations • 23 May 2023 • Kexin Jin, ChenGuang Liu, Jonas Latz
Indeed, we introduce and study the Stochastic Gradient Langevin Diffusion (SGLDiff), a continuous-time Markov process that follows the Langevin diffusion corresponding to a data subset and switches this data subset after exponential waiting times.
1 code implementation • 25 Apr 2023 • Yi-Fan Zhang, Xue Wang, Kexin Jin, Kun Yuan, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan
In particular, when the adaptation target is a series of domains, the adaptation accuracy of AdaNPC is 50% higher than advanced TTA methods.
1 code implementation • 14 Oct 2022 • Zhuoqing Song, Weijian Li, Kexin Jin, Lei Shi, Ming Yan, Wotao Yin, Kun Yuan
In the proposed family, EquiStatic has a degree of $\Theta(\ln(n))$, where $n$ is the network size, and a series of time-dependent one-peer topologies, EquiDyn, has a constant degree of 1.
no code implementations • 8 Sep 2022 • Kexin Jin, Jonas Latz, ChenGuang Liu, Alessandro Scagliotti
This model is a piecewise-deterministic Markov process that represents the particle movement by an underdamped dynamical system and the data subsampling through a stochastic switching of the dynamical system.
no code implementations • 7 Dec 2021 • Kexin Jin, Jonas Latz, ChenGuang Liu, Carola-Bibiane Schönlieb
Optimization problems with continuous data appear in, e. g., robust machine learning, functional data analysis, and variational inference.