Markov-Lipschitz Deep Learning
Li, Stan Z., Zang, Zelin, Wu, Lirong
We propose a novel framework, called Markov-Lipschitz deep learning (MLDL), to tackle geometric deterioration caused by collapse, twisting, or crossing in vector-based neural network transformations for manifold-based representation learning and manifold data generation. A prior constraint, called locally isometric smoothness (LIS), is imposed across-layers and encoded into a Markov random field (MRF)-Gibbs distribution. This leads to the best possible solutions for local geometry preservation and robustness as measured by locally geometric distortion and locally bi-Lipschitz continuity. Consequently, the layer-wise vector transformations are enhanced into well-behaved, LIS-constrained metric homeomorphisms. Extensive experiments, comparisons, and ablation study demonstrate significant advantages of MLDL for manifold learning and manifold data generation. MLDL is general enough to enhance any vector transformation-based networks. The code is available at https://github.com/westlake-cairi/Markov-Lipschitz-Deep-Learning.
Sep-30-2020
- Country:
- North America > United States
- Illinois > Cook County > Chicago (0.04)
- Asia > China
- Zhejiang Province > Hangzhou (0.04)
- North America > United States
- Genre:
- Research Report (0.64)
- Industry:
- Education (0.37)
- Technology: