Statistical Learning
Depth is More Powerful than Width with Prediction Concatenation in Deep Forest
The prediction concatenation (PreConc) operation is crucial for the multi-layer feature transformation in deep forest, though little has been known about its theoretical property.
Manifold Interpolating Optimal-Transport Flows for Trajectory Inference
Data from naturalistic systems are often modeled as generated from an underlying low dimensional manifold embedded in a high dimensional measurement space.
Unsupervised Visual Representation Learning via Mutual Information Regularized Assignment
We derive a fixed-point iteration method and prove its convergence to the optimal solution.