ADADELTA: An Adaptive Learning Rate Method

Code

• github.com/arobey1/mbrdl
  pytorch★ 16
• github.com/harshraj11584/Paper-Implementation-Overview-Gradient-Descent-Optimization-Sebastian-Ruder
  none★ 0
• github.com/mohamedameen93/German-Traffic-Sign-Classification-Using-TensorFlow
  tf★ 0
• github.com/harshraj11584/Paper-Implementation-Overview-Gradient-Descent-Optimization-Algorithms
  none★ 0
• github.com/rahulsonone1234/Traffic-Sign-Recognition
  tf★ 0
• github.com/nyatadecocoa/Machine_Learning_Midterm_Assignment_2019
  tf★ 0
• github.com/rahulsonone1234/traffic-sign-
  tf★ 0
• github.com/bratao/PySeqLab
  none★ 0
• github.com/Arko98/Gradient-Descent-Algorithms
  none★ 0
• github.com/hx123123/optimization
  none★ 0

Abstract

We present a novel per-dimension learning rate method for gradient descent called ADADELTA. The method dynamically adapts over time using only first order information and has minimal computational overhead beyond vanilla stochastic gradient descent. The method requires no manual tuning of a learning rate and appears robust to noisy gradient information, different model architecture choices, various data modalities and selection of hyperparameters. We show promising results compared to other methods on the MNIST digit classification task using a single machine and on a large scale voice dataset in a distributed cluster environment.

Tasks

Reproductions