Implementation and comparison of zero order vs first order method on the AdaMM (aka AMSGrad) optimizer: analysis of convergence rates and minima shape
python
machine-learning
deep-learning
pytorch
cosine-similarity
t-sne
optimization-algorithms
first-order-methods
amsgrad
optimizers
convergence-analysis
convergence-rate
cnn-filters
zero-order-methods
zero-order-adammm
first-order-adamm
minima-analysis
zo-sgd
-
Updated
Sep 25, 2022 - Jupyter Notebook