Saved in:
Bibliographic Details
Main Authors: Decugis, Juliette, Tsai, Alicia Y., Emerling, Max, Ganesh, Ashwin, Ghaoui, Laurent El
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.14430
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909262379220992
author Decugis, Juliette
Tsai, Alicia Y.
Emerling, Max
Ganesh, Ashwin
Ghaoui, Laurent El
author_facet Decugis, Juliette
Tsai, Alicia Y.
Emerling, Max
Ganesh, Ashwin
Ghaoui, Laurent El
contents In this paper, we investigate the extrapolation capabilities of implicit deep learning models in handling unobserved data, where traditional deep neural networks may falter. Implicit models, distinguished by their adaptability in layer depth and incorporation of feedback within their computational graph, are put to the test across various extrapolation scenarios: out-of-distribution, geographical, and temporal shifts. Our experiments consistently demonstrate significant performance advantage with implicit models. Unlike their non-implicit counterparts, which often rely on meticulous architectural design for each task, implicit models demonstrate the ability to learn complex model structures without the need for task-specific design, highlighting their robustness in handling unseen data.
format Preprint
id arxiv_https___arxiv_org_abs_2407_14430
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The Extrapolation Power of Implicit Models
Decugis, Juliette
Tsai, Alicia Y.
Emerling, Max
Ganesh, Ashwin
Ghaoui, Laurent El
Machine Learning
Artificial Intelligence
In this paper, we investigate the extrapolation capabilities of implicit deep learning models in handling unobserved data, where traditional deep neural networks may falter. Implicit models, distinguished by their adaptability in layer depth and incorporation of feedback within their computational graph, are put to the test across various extrapolation scenarios: out-of-distribution, geographical, and temporal shifts. Our experiments consistently demonstrate significant performance advantage with implicit models. Unlike their non-implicit counterparts, which often rely on meticulous architectural design for each task, implicit models demonstrate the ability to learn complex model structures without the need for task-specific design, highlighting their robustness in handling unseen data.
title The Extrapolation Power of Implicit Models
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2407.14430