papers AI Learner
The Github is limit! Click to go to the new site.

Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment

2019-05-15
Chen Huang, Shuangfei Zhai, Walter Talbott, Miguel Angel Bautista, Shih-Yu Sun, Carlos Guestrin, Josh Susskind

Abstract

In most machine learning training paradigms a fixed, often handcrafted, loss function is assumed to be a good proxy for an underlying evaluation metric. In this work we assess this assumption by meta-learning an adaptive loss function to directly optimize the evaluation metric. We propose a sample efficient reinforcement learning approach for adapting the loss dynamically during training. We empirically show how this formulation improves performance by simultaneously optimizing the evaluation metric and smoothing the loss landscape. We verify our method in metric learning and classification scenarios, showing considerable improvements over the state-of-the-art on a diverse set of tasks. Importantly, our method is applicable to a wide range of loss functions and evaluation metrics. Furthermore, the learned policies are transferable across tasks and data, demonstrating the versatility of the method.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.05895

PDF

http://arxiv.org/pdf/1905.05895


Similar Posts

Comments