callowbird / Harmonica
Code repository for the paper "Hyperparameter Optimization: A Spectral Approach" by Elad Hazan, Adam Klivans, Yang Yuan.
☆174Updated 6 years ago
Alternatives and similar repositories for Harmonica:
Users that are interested in Harmonica are comparing it to the libraries listed below
- auto-tuning momentum SGD optimizer☆422Updated 7 years ago
- auto-tuning momentum SGD optimizer☆286Updated 6 years ago
- Exploring differentiation with respect to hyperparameters☆294Updated 9 years ago
- Efficient Architecture Search by Network Transformation, in AAAI 2018☆169Updated 5 years ago
- Deep learning system course☆218Updated 6 years ago
- Compare SELUs (scaled exponential linear units) with other activations on MNIST, CIFAR10, etc.☆375Updated 7 years ago
- Standalone TensorBoard for visualizing in deep learning☆369Updated 5 years ago
- ☆254Updated 3 years ago
- ☆251Updated 8 years ago
- https://2017.icml.cc/Conferences/2017/Schedule☆72Updated 7 years ago
- Fully differentiable deep-neural decision forest in tensorflow☆229Updated 7 years ago
- 2.86% and 15.85% on CIFAR-10 and CIFAR-100☆296Updated 6 years ago
- Hyperparameter optimization with approximate gradient☆66Updated 4 years ago
- DeepArchitect: Automatically Designing and Training Deep Architectures☆144Updated 5 years ago
- DrMAD☆107Updated 7 years ago
- Code to reproduce some of the figures in the paper "On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima"☆139Updated 7 years ago
- ☆137Updated 7 years ago
- Implements pytorch code for the Accelerated SGD algorithm.☆215Updated 7 years ago
- MultiGPU enabled image generative models (GAN and DCGAN)☆207Updated 4 years ago
- Tensorflow implementation of SGD with Coupled Adaptive Batch Size (CABS)☆43Updated 8 years ago
- Forward-mode Automatic Differentiation for TensorFlow☆140Updated 7 years ago
- Reference caffe implementation of LSUV initialization☆113Updated 7 years ago
- Code used to generate the results appearing in "Train longer, generalize better: closing the generalization gap in large batch training o…☆149Updated 7 years ago
- An experimental technique for efficiently exploring neural architectures.☆490Updated 7 years ago
- Code for paper "L4: Practical loss-based stepsize adaptation for deep learning"☆125Updated 5 years ago
- Simple Tensorflow implementation of "On the Convergence of Adam and Beyond" (ICLR 2018)☆104Updated 6 years ago
- 🏃 Implementation of Using Fast Weights to Attend to the Recent Past.☆268Updated 6 years ago
- Sublinear memory optimization for deep learning, reduce GPU memory cost to train deeper nets☆308Updated 7 years ago
- Implementation of Appendix A (Neural Architecture Search with Reinforcement Learning: https://arxiv.org/abs/1611.01578) by chainer☆55Updated 6 years ago
- An example of data parallelism and async updates of parameter in tensorflow.☆121Updated 6 years ago