callowbird / Harmonica
Code repository for the paper "Hyperparameter Optimization: A Spectral Approach" by Elad Hazan, Adam Klivans, Yang Yuan.
☆174Updated 5 years ago
Related projects ⓘ
Alternatives and complementary repositories for Harmonica
- auto-tuning momentum SGD optimizer☆423Updated 6 years ago
- auto-tuning momentum SGD optimizer☆287Updated 5 years ago
- Exploring differentiation with respect to hyperparameters☆297Updated 8 years ago
- DeepArchitect: Automatically Designing and Training Deep Architectures☆144Updated 5 years ago
- 2.86% and 15.85% on CIFAR-10 and CIFAR-100☆295Updated 6 years ago
- Hyperparameter optimization with approximate gradient☆66Updated 3 years ago
- ☆250Updated 7 years ago
- Implements pytorch code for the Accelerated SGD algorithm.☆214Updated 6 years ago
- Efficient Architecture Search by Network Transformation, in AAAI 2018☆170Updated 5 years ago
- MultiGPU enabled image generative models (GAN and DCGAN)☆209Updated 4 years ago
- https://2017.icml.cc/Conferences/2017/Schedule☆72Updated 7 years ago
- ☆132Updated 7 years ago
- Standalone TensorBoard for visualizing in deep learning☆370Updated 4 years ago
- Implementation of Appendix A (Neural Architecture Search with Reinforcement Learning: https://arxiv.org/abs/1611.01578) by chainer☆55Updated 6 years ago
- DrMAD☆108Updated 6 years ago
- Functional ANOVA☆122Updated 7 months ago
- Reference caffe implementation of LSUV initialization☆112Updated 7 years ago
- Tensorflow implementation of SGD with Coupled Adaptive Batch Size (CABS)☆43Updated 7 years ago
- Forward-mode Automatic Differentiation for TensorFlow☆140Updated 6 years ago
- Implementation of Progressive Neural Architecture Search in Keras and Tensorflow☆120Updated 5 years ago
- predicting learning curves in python☆42Updated 7 years ago
- An implementation of KFAC for TensorFlow☆197Updated 2 years ago
- Sublinear memory optimization for deep learning, reduce GPU memory cost to train deeper nets☆308Updated 7 years ago
- ☆90Updated 7 years ago
- ☆137Updated 7 years ago
- An example of data parallelism and async updates of parameter in tensorflow.☆121Updated 6 years ago
- Code used to generate the results appearing in "Train longer, generalize better: closing the generalization gap in large batch training o…☆148Updated 7 years ago
- Neural Architecture Search with Bayesian Optimisation and Optimal Transport☆133Updated 5 years ago
- Path-Level Network Transformation for Efficient Architecture Search, in ICML 2018.☆113Updated 6 years ago