A Bayesian Variational Framework for Stochastic Optimization

05/05/2019
by   Philippe Casgrain, et al.
0

This work proposes a theoretical framework for stochastic optimization algorithms, based on a continuous Bayesian variational model for algorithms. Using techniques from stochastic control with asymmetric information, the solution to this variational problem is shown to be equivalent to a system of Forward Backward Differential Equations (FBSDEs). Using an analytical approximation to the solution of these FBSDEs, we recover a variety of existing adaptive stochastic gradient descent methods. This framework establishes a direct connection between stochastic optimization algorithms and a secondary Bayesian inference problem on gradients, where the prior and assumed observation dynamics determine the resulting algorithm.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset