Damped Anderson Mixing for Deep Reinforcement Learning: Acceleration, Convergence, and Stabilization

Uncovering the Law of Data Separation in Deep Learning

Recurrent Neural Networks with Mixed Hierarchical Structures and EM Algorithm for Natural Language Processing

Community Detection of Discrete-time Temporal Networks under Dynamic Stochastic Block Models

Shrinkage Estimation for Large-dimensional Factor Model with an Observed Variable Network

Estimating cell-type-specific gene co-expression networks from bulk gene expression data

Matrix-valued Network Autoregression Model with Latent Group Structure

Simple measures of uncertainty for model selection

Learning invariant representations for algorithmic fairness and domain generalization with minimax optimality

Eigencurve: Optimal Learning Rate Schedule for SGD on Quadratic Objectives with Skewed Hessian Spectrums

Statistical Inference for Decentralized Federated Learning