The Extrapolation Power of Implicit Models

Juliette Decugis, Max Emerling, Ashwin Ganesh, Alicia Y. Tsai, Laurent El Ghaoui

Primary Area: general machine learning (i.e., none of the above)

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: deep learning, implicit models, function extrapolation, out of distribution

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Abstract: Faced with out-of-distribution data, deep neural networks may break down, even on simple tasks. In this paper, we consider the extrapolation ability of implicit deep learning models, which allow layer depth flexibility and feedback in their computational graph. We compare the out-of-sample performance of implicit and non-implicit deep learning models on both mathematical extrapolation tasks and real-world use cases in time series forecasting and earthquake location prediction. Throughout our experiments, we demonstrate a marked performance increase with implicit models. In addition, we observe that to achieve acceptable performance, the architectures of the non-implicit models must be carefully tailored to the task at hand. In contrast, implicit models do not require such task-specific architectural design, as they learn the model structure during training.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 5843