PIVEN: A Deep Neural Network for Prediction Intervals with Specific Value Prediction.

Eli Simhayev, Gilad Katz, Lior Rokach

Research output: Working paper/PreprintPreprint

Abstract

Improving the robustness of neural nets in regression tasks is key to their application in multiple domains. Deep learning-based approaches aim to achieve this goal either by improving their prediction of specific values (i.e., point prediction), or by producing prediction intervals (PIs) that quantify uncertainty. We present PIVEN, a deep neural network for producing both a PI and a prediction of specific values. Unlike previous studies, PIVEN makes no assumptions regarding data distribution inside the PI, making its point prediction more effective for various real-world problems. Benchmark experiments show that our approach produces tighter uncertainty bounds than the current state-of-the-art approach for producing PIs, while maintaining comparable performance to the state-of-the-art approach for specific value-prediction. Additional evaluation on large image datasets further support our conclusions.
Original languageEnglish
Volumeabs/2006.05139
StatePublished - 2020

Publication series

NameArxiV cs.ML

Fingerprint

Dive into the research topics of 'PIVEN: A Deep Neural Network for Prediction Intervals with Specific Value Prediction.'. Together they form a unique fingerprint.

Cite this