Timezone: »
Manifold learning is a fundamental problem in machine learning with numerous applications. Most of the existing methods directly learn the low-dimensional embedding of the data in some high-dimensional space, and usually lack the flexibility of being directly applicable to down-stream applications. In this paper, we propose the concept of implicit manifold learning, where manifold information is implicitly obtained by learning the associated heat kernel. A heat kernel is the solution of the corresponding heat equation, which describes how ``heat'' transfers on the manifold, thus containing ample geometric information of the manifold. We provide both practical algorithm and theoretical analysis of our framework. The learned heat kernel can be applied to various kernel-based machine learning models, including deep generative models (DGM) for data generation and Stein Variational Gradient Descent for Bayesian inference. Extensive experiments show that our framework can achieve the state-of-the-art results compared to existing methods for the two tasks.
Author Information
Yufan Zhou (University at Buffalo)
Changyou Chen (University at Buffalo)
Jinhui Xu (SUNY at Buffalo)
More from the Same Authors
-
2023 Poster: Linear Time Algorithms for k-means with Multi-Swap Local Search »
Junyu Huang · Qilong Feng · Ziyun Huang · Jinhui Xu · Jianxin Wang -
2020 Poster: Bayesian Multi-type Mean Field Multi-agent Imitation Learning »
Fan Yang · Alina Vereshchaka · Changyou Chen · Wen Dong -
2020 Spotlight: Bayesian Multi-type Mean Field Multi-agent Imitation Learning »
Fan Yang · Alina Vereshchaka · Changyou Chen · Wen Dong -
2018 Poster: Empirical Risk Minimization in Non-interactive Local Differential Privacy Revisited »
Di Wang · Marco Gaboardi · Jinhui Xu -
2017 Poster: Differentially Private Empirical Risk Minimization Revisited: Faster and More General »
Di Wang · Minwei Ye · Jinhui Xu -
2013 Poster: k-Prototype Learning for 3D Rigid Structures »
Hu Ding · Ronald Berezney · Jinhui Xu