Learning with Random Learning Rates
cs.LG, cs.NE, stat.ML
Submitted: 2018-10-02
Updated: 2019-01-29
Code: https://github.com/kuangliu/pytorch-cifar
Terminology
Sources
- Designing Neural Network Architectures using Reinforcement Learning
- Stronger Baselines for Trustable Results in Neural Machine Translation
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
- Three Factors Influencing Minima in SGD
- Exploring the Limits of Language Modeling
- Improving Generalization Performance by Switching from Adam to SGD
- Combining Expert Advice Efficiently
- One weird trick for parallelizing convolutional neural networks
- Measuring the Intrinsic Dimension of Objective Landscapes
- Continuous control with deep reinforcement learning
- Progressive Neural Architecture Search
- DARTS: Differentiable Architecture Search
- Speed learning on the fly
- Large-Scale Evolution of Image Classifiers
- Compression of Neural Machine Translation Models via Pruning
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Neural Architecture Search with Reinforcement Learning
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning