Implicit, Passive-Aggressive, and aProx updates by bremen79 on June 12, 2021February 15, 2022 Read More
Perceptron is Not SGD: A Better Interpretation Through Pseudogradients by bremen79 on February 14, 2021September 9, 2022 Read More
Neural Networks (Maybe) Evolved to Make Adam The Best Optimizer by bremen79 on December 6, 2020December 6, 2020 Read More
Almost Sure Convergence of SGD on Smooth Non-Convex Functions by bremen79 on October 5, 2020December 5, 2020 Read More
Last Iterate of SGD Converges (Even in Unbounded Domains) by bremen79 on August 7, 2020September 23, 2020 Read More
Parameter-free Learning and Optimization Algorithms 