Optimal Adaptive and Accelerated Stochastic Gradient Descent
This work provides a theoretical foundation for improving optimization efficiency in machine learning and deep learning, though it appears incremental as it builds on existing acceleration and adaptive techniques.
The authors tackled the problem of combining acceleration and adaptive gradient methods in stochastic gradient descent (SGD) to achieve optimal convergence rates, showing that their new class of methods achieves optimal sampling and iteration complexity for smooth stochastic optimization.
Stochastic gradient descent (\textsc{Sgd}) methods are the most powerful optimization tools in training machine learning and deep learning models. Moreover, acceleration (a.k.a. momentum) methods and diagonal scaling (a.k.a. adaptive gradient) methods are the two main techniques to improve the slow convergence of \textsc{Sgd}. While empirical studies have demonstrated potential advantages of combining these two techniques, it remains unknown whether these methods can achieve the optimal rate of convergence for stochastic optimization. In this paper, we present a new class of adaptive and accelerated stochastic gradient descent methods and show that they exhibit the optimal sampling and iteration complexity for stochastic optimization. More specifically, we show that diagonal scaling, initially designed to improve vanilla stochastic gradient, can be incorporated into accelerated stochastic gradient descent to achieve the optimal rate of convergence for smooth stochastic optimization. We also show that momentum, apart from being known to speed up the convergence rate of deterministic optimization, also provides us new ways of designing non-uniform and aggressive moving average schemes in stochastic optimization. Finally, we present some heuristics that help to implement adaptive accelerated stochastic gradient descent methods and to further improve their practical performance for machine learning and deep learning.