A Unified Framework of Surrogate Loss by Refactoring and Interpolation
arXiv:2007.13870
Abstract
We introduce UniLoss, a unified framework to generate surrogate losses for training deep networks with gradient descent, reducing the amount of manual design of task-specific surrogate losses. Our key observation is that in many cases, evaluating a model with a performance metric on a batch of examples can be refactored into four steps: from input to real-valued scores, from scores to comparisons of pairs of scores, from comparisons to binary variables, and from binary variables to the final performance metric. Using this refactoring we generate differentiable approximations for each non-differentiable step through interpolation. Using UniLoss, we can optimize for different tasks and metrics using one unified framework, achieving comparable performance compared with task-specific losses. We validate the effectiveness of UniLoss on three tasks and four datasets. Code is available at https://github.com/princeton-vl/uniloss.
arXiv commentAccepted to ECCV 2020
References in corpus (6)
- Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
- Improved Image Captioning via Policy Gradient optimization of SPIDEr
- Learning to Teach with Dynamic Loss Functions
- Training Deep Neural Networks via Direct Loss Minimization
- Learning Surrogate Losses
- Learning Loss Functions for Semi-supervised Learning via Discriminative Adversarial Networks