all AI news
Leveraging Unlabeled Data to Predict Out-of-Distribution Performance. (arXiv:2201.04234v1 [cs.LG])
Jan. 13, 2022, 2:10 a.m. | Saurabh Garg, Sivaraman Balakrishnan, Zachary C. Lipton, Behnam Neyshabur, Hanie Sedghi
cs.LG updates on arXiv.org arxiv.org
Real-world machine learning deployments are characterized by mismatches
between the source (training) and target (test) distributions that may cause
performance drops. In this work, we investigate methods for predicting the
target domain accuracy using only labeled source data and unlabeled target
data. We propose Average Thresholded Confidence (ATC), a practical method that
learns a threshold on the model's confidence, predicting accuracy as the
fraction of unlabeled examples for which model confidence exceeds that
threshold. ATC outperforms previous methods across several …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Social Insights & Data Analyst (Freelance)
@ Media.Monks | Jakarta
Cloud Data Engineer
@ Arkatechture | Portland, ME, USA