At Stability's Edge: How to Adjust Hyperparameters to Preserve Minima Selection in Asynchronous Training of Neural Networks?

Niv Giladi, Mor Shpigel Nacson, Elad Hoffer, Daniel Soudry

Keywords: generalization, gradient descent, implicit bias, learning rate, momentum, stability

Monday: Optimisation Theory

Abstract: Background: Recent developments have made it possible to accelerate neural networks training significantly using large batch sizes and data parallelism. Training in an asynchronous fashion, where delay occurs, can make training even more scalable. However, asynchronous training has its pitfalls, mainly a degradation in generalization, even after convergence of the algorithm. This gap remains not well understood, as theoretical analysis so far mainly focused on the convergence rate of asynchronous methods. Contributions: We examine asynchronous training from the perspective of dynamical stability. We find that the degree of delay interacts with the learning rate, to change the set of minima accessible by an asynchronous stochastic gradient descent algorithm. We derive closed-form rules on how the learning rate could be changed, while keeping the accessible set the same. Specifically, for high delay values, we find that the learning rate should be kept inversely proportional to the delay. We then extend this analysis to include momentum. We find momentum should be either turned off, or modified to improve training stability. We provide empirical experiments to validate our theoretical findings.

Similar Papers

Escaping Saddle Points Faster with Stochastic Momentum
Jun-Kun Wang, Chi-Heng Lin, Jacob Abernethy,
Gap-Aware Mitigation of Gradient Staleness
Saar Barkai, Ido Hakimi, Assaf Schuster,