A Tunable Loss Function for Robust Classification: Calibration, Landscape, and Generalization-Reference-Cited by-同舟云学术

A Tunable Loss Function for Robust Classification: Calibration, Landscape, and Generalization

Author:

Sypherd Tyler¹^ORCID,Diaz Mario²^ORCID,Cava John Kevin³,Dasarathy Gautam¹^ORCID,Kairouz Peter⁴,Sankar Lalitha¹^ORCID

Affiliation:

1. School of Electrical, Computer and Energy Engineering (ECEE), Arizona State University, Tempe, AZ, USA

2. Instituto de Investigaciones en Matemáticas Aplicadas y Sistemas, Universidad Nacional Autónoma de México, Coyoacán, Mexico

3. School of Computing and Augmented Intelligence (SCAI), Arizona State University, Tempe, AZ, USA

4. Google, Menlo Park, CA, USA

Funder

NSF

Programa de Apoyo a Proyectos de Investigación e Innovación Tecnológica

Office of Naval Research

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Library and Information Sciences,Computer Science Applications,Information Systems

Link

Reference80 articles.

1. Theoretically principled trade-off between robustness and accuracy;zhang;Proc Int Conf Mach Learn,2019

2. Stiffness: A new perspective on generalization in neural networks;fort;arXiv 1901 09491,2019

3. Pytorch: An imperative style, high-performance deep learning library;paszke;Proc Adv Neural Inf Process Syst,2019

4. Censored and fair universal representations using generative adversarial models;kairouz;arXiv 1910 00411,2019

Cited by 5 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

4. A Momentum Loss Reweighting Method for Improving Recall;Proceedings of the 32nd ACM International Conference on Information and Knowledge Management;2023-10-21

5. (α_D, α_G)-GANs: Addressing GAN Training Instabilities via Dual Objectives;2023 IEEE International Symposium on Information Theory (ISIT);2023-06-25