Analysis of gradient descent methods with non-diminishing, bounded errors

by   Arunselvan Ramaswamy, et al.

The main aim of this paper is to provide an analysis of gradient descent (GD) algorithms with gradient errors that do not necessarily vanish, asymptotically. In particular, sufficient conditions are presented for both stability (almost sure boundedness of the iterates) and convergence of GD with bounded, (possibly) non-diminishing gradient errors. In addition to ensuring stability, such an algorithm is shown to converge to a small neighborhood of the minimum set, which depends on the gradient errors. It is worth noting that the main result of this paper can be used to show that GD with asymptotically vanishing errors indeed converges to the minimum set. The results presented herein are not only more general when compared to previous results, but our analysis of GD with errors is new to the literature to the best of our knowledge. Our work extends the contributions of Mangasarian & Solodov, Bertsekas & Tsitsiklis and Tadic & Doucet. Using our framework, a simple yet effective implementation of GD using simultaneous perturbation stochastic approximations (SP SA), with constant sensitivity parameters, is presented. Another important improvement over many previous results is that there are no `additional' restrictions imposed on the step-sizes. In machine learning applications where step-sizes are related to learning rates, our assumptions, unlike those of other papers, do not affect these learning rates. Finally, we present experimental results to validate our theory.


page 1

page 2

page 3

page 4


Asynchronous stochastic approximations with asymptotically biased errors and deep multi-agent learning

Asynchronous stochastic approximations are an important class of model-f...

Linear Convergence and Implicit Regularization of Generalized Mirror Descent with Time-Dependent Mirrors

The following questions are fundamental to understanding the properties ...

Stability and Generalization of Stochastic Compositional Gradient Descent Algorithms

Many machine learning tasks can be formulated as a stochastic compositio...

Backtracking Gradient Descent allowing unbounded learning rates

In unconstrained optimisation on an Euclidean space, to prove convergenc...

Geometrically Convergent Distributed Optimization with Uncoordinated Step-Sizes

A recent algorithmic family for distributed optimization, DIGing's, have...

Errors-in-variables models with dependent measurements

Suppose that we observe y ∈R^n and X ∈R^n × m in the following errors-in...

Please sign up or login with your details

Forgot password? Click here to reset