Oral
Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment
Chen Huang · Shuangfei Zhai · Walter Talbott · Miguel Bautista Martin · Shih-Yu Sun · Carlos Guestrin · Joshua M Susskind

Wed Jun 12th 04:25 -- 04:30 PM @ Hall A

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 learn- ing 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 land- scape. We verify our method in metric learning and classification scenarios, showing consider- able 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.

Author Information

Chen Huang (Apple Inc.)
Shuangfei Zhai (Apple)
Walter Talbott (Apple)
Miguel Bautista Martin (Apple Inc.)
Shih-Yu Sun (Apple)
Carlos Guestrin (Apple & Univesity of Washington)
Josh M Susskind (Apple, Inc.)

Related Events (a corresponding poster, oral, or spotlight)