8 citations · 32 across the 13 of their papers we have counts for
5 papers · 1 filter
Unsupervised Co-Learning on -Manifolds Across Irreducible Representations
Yifeng Fan, Tingran Gao, Zhizhen Zhao
We introduce a novel co-learning paradigm for manifolds naturally equipped with a group action, motivated by recent developments on learning a manifold from attached fibre bundle s…
Representation Theoretic Patterns in Multi-Frequency Class Averaging for Three-Dimensional Cryo-Electron Microscopy
Yifeng Fan, Tingran Gao, Zhizhen Zhao
We develop in this paper a novel intrinsic classification algorithm -- multi-frequency class averaging (MFCA) -- for classifying noisy projection images obtained from three-dimensi…
SelectNet: Learning to Sample from the Wild for Imbalanced Data Training
Yunru Liu, Tingran Gao, Haizhao Yang
Supervised learning from training data with imbalanced class sizes, a commonly encountered scenario in real applications such as anomaly/fraud detection, has long been considered a…
Uniform-in-Time Weak Error Analysis for Stochastic Gradient Descent Algorithms via Diffusion Approximation
Yuanyuan Feng, Tingran Gao, Lei Li +2
Diffusion approximation provides weak approximation for stochastic gradient descent algorithms in a finite time horizon. In this paper, we introduce new tools motivated by the back…
Multi-Frequency Phase Synchronization
Tingran Gao, Zhizhen Zhao
We propose a novel formulation for phase synchronization -- the statistical problem of jointly estimating alignment angles from noisy pairwise comparisons -- as a nonconvex optimiz…