Online Learning Rate Adaptation with Hypergradient Descent
Abstrak
We introduce a general method for improving the convergence rate of gradient-based optimizers that is easy to implement and works well in practice. We demonstrate the effectiveness of the method in a range of optimization problems by applying it to stochastic gradient descent, stochastic gradient descent with Nesterov momentum, and Adam, showing that it significantly reduces the need for the manual tuning of the initial learning rate for these commonly used algorithms. Our method works by dynamically updating the learning rate during optimization using the gradient with respect to the learning rate of the update rule itself. Computing this "hypergradient" needs little additional computation, requires only one extra copy of the original gradient to be stored in memory, and relies upon nothing more than what is provided by reverse-mode automatic differentiation.
Topik & Kata Kunci
Penulis (5)
A. G. Baydin
R. Cornish
David Martínez-Rubio
Mark W. Schmidt
Frank D. Wood
Akses Cepat
PDF tidak tersedia langsung
Cek di sumber asli →- Tahun Terbit
- 2017
- Bahasa
- en
- Total Sitasi
- 275×
- Sumber Database
- Semantic Scholar
- Akses
- Open Access ✓