Cong Fang

Latest

• Task-Robust Pre-Training for Worst-Case Downstream Adaptation
• On the Lower Bound of Minimizing Polyak-Łojasiewicz Functions
• Zeroth-order Optimization with Weak Dimension Dependency
• Alternating Direction Method of Multipliers for Machine Learning
• Training Neural Networks by Lifted Proximal Operator Machines
• Decentralized Accelerated Gradient Methods With Increasing Penalty Parameters
• Accelerated First-Order Optimization Algorithms for Machine Learning
• Accelerated Optimization for Machine Learning: First-Order Algorithms
• Lifted Proximal Operator Machines
• Sharp Analysis for Nonconvex SGD Escaping from Saddle Points
• SPIDER Near-Optimal Non-Convex Optimization via Stochastic Path-Integrated Differential Estimator
• Faster and Non-ergodic O(1/K) Stochastic Alternating Direction Method of Multipliers
• Feature Learning via Partial Differential Equation with Applications to Face Recognition
• Parallel Asynchronous Stochastic Variance Reduction for Nonconvex Optimization
• A Robust Hybrid Method for Text Detection in Natural Scenes by Learning-based Partial Differential Equations