Dynamic Game Theoretic Neural Optimizer

by   Guan-Horng Liu, et al.

The connection between training deep neural networks (DNNs) and optimal control theory (OCT) has attracted considerable attention as a principled tool of algorithmic design. Despite few attempts being made, they have been limited to architectures where the layer propagation resembles a Markovian dynamical system. This casts doubts on their flexibility to modern networks that heavily rely on non-Markovian dependencies between layers (e.g. skip connections in residual networks). In this work, we propose a novel dynamic game perspective by viewing each layer as a player in a dynamic game characterized by the DNN itself. Through this lens, different classes of optimizers can be seen as matching different types of Nash equilibria, depending on the implicit information structure of each (p)layer. The resulting method, called Dynamic Game Theoretic Neural Optimizer (DGNOpt), not only generalizes OCT-inspired optimizers to richer network class; it also motivates a new training principle by solving a multi-player cooperative game. DGNOpt shows convergence improvements over existing methods on image classification datasets with residual and inception networks. Our work marries strengths from both OCT and game theory, paving ways to new algorithmic opportunities from robust optimal control and bandit-based optimization.


page 1

page 2

page 3

page 4


A Differential Game Theoretic Neural Optimizer for Training Residual Networks

Connections between Deep Neural Networks (DNNs) training and optimal con...

Differential Dynamic Programming Neural Optimizer

Interpretation of Deep Neural Networks (DNNs) training as an optimal con...

Review: Ordinary Differential Equations For Deep Learning

To better understand and improve the behavior of neural networks, a rece...

On a Connection between Differential Games, Optimal Control, and Energy-based Models for Multi-Agent Interactions

Game theory offers an interpretable mathematical framework for modeling ...

On the Turnpike to Design of Deep Neural Nets: Explicit Depth Bounds

It is well-known that the training of Deep Neural Networks (DNN) can be ...

Nash Neural Networks : Inferring Utilities from Optimal Behaviour

We propose Nash Neural Networks (N^3) as a new type of Physics Informed ...

Please sign up or login with your details

Forgot password? Click here to reset