This repository contains the results for the paper: "Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers"
-
Updated
Jul 17, 2021
This repository contains the results for the paper: "Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers"
Advanced Mathematical Optimization & Deep Learning Optimizers from scratch. Covers KKT duality, L-BFGS, proximal methods (ADMM, FISTA), stochastic algorithms (SVRG, Lion), and cutting-edge deep learning optimizers like K-FAC, Shampoo, Sophia, SAM, and Muon. Bridging strict convex calculus with large-scale Transformer training.
Guava Disease Classification using DenseNet-Reloaded and ADOPT optimizer. Achieves 99.73% accuracy in Anthracnose, Fruit Fly, and Healthy Guava detection.
Toy implementations of popular deep learning optimizers from scratch in JAX
Semester project on the impact of label noise on deep learning optimization
To associate your repository with the deep-learning-optimizers topic, visit your repo's landing page and select "manage topics."