Memory Augmented Optimizers for Deep Learning
arXiv:2106.10708
Abstract
Popular approaches for minimizing loss in data-driven learning often involve an abstraction or an explicit retention of the history of gradients for efficient parameter updates. The aggregated history of gradients nudges the parameter updates in the right direction even when the gradients at any given step are not informative. Although the history of gradients summarized in meta-parameters or explicitly stored in memory has been shown effective in theory and practice, the question of whether or only a subset of the gradients in the history are sufficient in deciding the parameter updates remains unanswered. In this paper, we propose a framework of memory-augmented gradient descent optimizers that retain a limited view of their gradient history in their internal memory. Such optimizers scale well to large real-life datasets, and our experiments show that the memory augmented extensions of standard optimizers enjoy accelerated convergence and improved performance on a majority of computer vision and language tasks that we considered. Additionally, we prove that the proposed class of optimizers with fixed-size memory converge under assumptions of strong convexity, regardless of which gradients are selected or how they are linearly combined to form the update step.
24 Pages. Currently under review
References in corpus (6)
- ADADELTA: An Adaptive Learning Rate Method
- A Stochastic Gradient Method with an Exponential Convergence Rate for Finite Training Sets
- Pointer Sentinel Mixture Models
- Global Convergence of Online Limited Memory BFGS
- Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves
- Correcting Momentum in Temporal Difference Learning