SirRob1997/Crowded-Valley---Results
This repository contains the results for the paper: "Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers"
This project provides comprehensive benchmarking results for various deep learning optimizers, comparing their performance across multiple tasks and hyperparameter settings. It helps machine learning researchers or practitioners understand which optimizers work best for different scenarios, offering a data-backed alternative to anecdotal choices. The output is extensive log files and analysis, detailing optimizer effectiveness under standardized conditions.
184 stars. No commits in the last 6 months.
Use this if you are a machine learning researcher or practitioner needing empirical evidence to select or evaluate deep learning optimizers for your models.
Not ideal if you are looking for an off-the-shelf software library to automatically choose an optimizer for you without reviewing the underlying data.
Stars
184
Forks
19
Language
—
License
—
Category
Last pushed
Jul 17, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/SirRob1997/Crowded-Valley---Results"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
nschaetti/EchoTorch
A Python toolkit for Reservoir Computing and Echo State Network experimentation based on...
metaopt/torchopt
TorchOpt is an efficient library for differentiable optimization built upon PyTorch.
opthub-org/pytorch-bsf
PyTorch implementation of Bezier simplex fitting
gpauloski/kfac-pytorch
Distributed K-FAC preconditioner for PyTorch
pytorch/xla
Enabling PyTorch on XLA Devices (e.g. Google TPU)