Kexin Jin

6 papers · 2022–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (10)

Venues

ICML (2) JMLR (2) AISTATS (1) NeurIPS (1)

Top co-authors

Jonas Latz (3) Chenguang Liu (3) Kun Yuan (3) Wotao Yin (2) Zhang Zhang (1) Carola-Bibiane Schönlieb (1) Zhuoqing Song (1) Yifan Zhang (1) Bicheng Ying (1) xue wang (1)

Research topics

Machine Learning (6) Optimization & Theory (5) Mathematics & Optimization (3) Optimization (3) Artificial Intelligence (1) Application Areas (1) Learning Paradigms (1) Probability (1)

Keywords

wasserstein distance (1) stochastic gradient descent (1) neural network training (1) domain generalization (1) variational inference (1) bayesian inference (1) data subsampling (1) distributed learning (1) test-time adaptation (1) decentralized optimization (1) continuous optimization (1) markov chain monte carlo (1) posterior distribution (1) nearest neighbor (1) communication efficiency (1) learning rate (1) physics-informed neural network (1) gradient flow (1) model training (1) distributed stochastic gradient descent (1)

Papers

Losing Momentum in Continuous-time Stochastic Optimisation JMLR 2025 Subsampling Error in Stochastic Gradient Langevin Diffusions AISTATS 2024 A Continuous-time Stochastic Gradient Descent Method for Continuous Data JMLR 2023 AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation ICML 2023 DSGD-CECA: Decentralized SGD with Communication-Optimal Exact Consensus Algorithm ICML 2023 Communication-Efficient Topologies for Decentralized Learning with $O(1)$ Consensus Rate NeurIPS 2022