Improved Training Speed, Accuracy, and Data Utilization Through Loss Function Optimization

As the complexity of neural network models has grown, it has become increasingly important to optimize their design automatically through metalearning. Methods for discovering hyperparameters, topologies, and learning rate schedules have lead to significant increases in performance. This paper shows that loss functions can be optimized with metalearning as well, and result in similar improvements. The method, Genetic Lossfunction Optimization (GLO), discovers loss functions de novo, and optimizes them for a target task. Leveraging techniques from genetic programming, GLO builds loss functions hierarchically from a set of operators and leaf nodes. These functions are repeatedly recombined and mutated to find an optimal structure, and then a covariance-matrix adaptation evolutionary strategy (CMA-ES) is used to find optimal coefficients. Networks trained with GLO loss functions are found to outperform the standard cross-entropy loss on standard image classification tasks. Training with these new loss functions requires fewer steps, results in lower test error, and allows for smaller datasets to be used. Loss function optimization thus provides a new dimension of metalearning, and constitutes an important step towards AutoML.

I. Introduction

Much of the power of modern neural networks originates from their complexity, i.e., number of parameters, hyperparameters, and topology. This complexity is often beyond human ability to optimize, and automated methods are needed. An entire field of metalearning has emerged recently to address this issue, based on various methods such as gradient descent, simulated annealing, reinforcement learning, Bayesian optimization, and evolutionary computation (EC) [1].