A Probabilistically Motivated Learning Rate Adaptation for Stochastic Optimization
arXiv:2102.10880
Abstract
Machine learning practitioners invest significant manual and computational resources in finding suitable learning rates for optimization algorithms. We provide a probabilistic motivation, in terms of Gaussian inference, for popular stochastic first-order methods. As an important special case, it recovers the Polyak step with a general metric. The inference allows us to relate the learning rate to a dimensionless quantity that can be automatically adapted during training by a control algorithm. The resulting meta-algorithm is shown to adapt learning rates in a robust manner across a large range of initial values when applied to deep learning benchmark problems.
References in corpus (8)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- ADADELTA: An Adaptive Learning Rate Method
- An overview of gradient descent optimization algorithms
- No More Pesky Learning Rates
- On the Noisy Gradient Descent that Generalizes as SGD
- Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence
- Training Neural Networks for and by Interpolation
- Active Probabilistic Inference on Matrices for Pre-Conditioning in Stochastic Optimization