NIPS Proceedingsβ

Aaron Defazio

5 Papers

  • On the Curved Geometry of Accelerated Optimization (2019)
  • On the Ineffectiveness of Variance Reduced Optimization for Deep Learning (2019)
  • A Simple Practical Accelerated Method for Finite Sums (2016)
  • SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives (2014)
  • A Convex Formulation for Learning Scale-Free Networks via Submodular Relaxation (2012)