Optimization
Coordinate Linear Variance Reduction for Generalized Linear Programming
For better scalability, stochastic counterparts of these methods have been proposed.
Benchmark_Sample_Efficiency_neurips_data
Despite the exciting progress in the field and the abundance of new methods proposed, how these algorithms compare against each other remains unclear.
WoodFisher: Efficient Second-Order Approximation for Neural Network Compression
Second-order information, in the form of Hessian-or Inverse-Hessian-vector products, is a fundamental tool for solving optimization problems.
Semi-Infinitely Constrained Markov Decision Processes
We also devise a reinforcement learning algorithm for SICMDPs that we call SI-CRL.
Stochastic L null-convex Function Minimization
We develop the first polynomial-time algorithms that return a near-optimal solution with high probability.
