Back to search

Cornell University

Automated Machine Learning under Resource Constraints

Abstract

dc:description.abstract

Automated machine learning (AutoML) seeks to reduce the human and machine costs of finding machine learning models and hyperparameters with good predictive performance. AutoML is easy with unlimited resources: an exhaustive search across all possible solutions finds the best performing model. This dissertation studies resource-constrained AutoML, in which only limited resources (such as compute or memory) are available for model search. We present a wide variety of strategies for choosing a model under resource constraints, including meta-learning across datasets with low rank matrix and tensor decomposition and experiment design, and efficient neural architecture search (NAS) using weight sharing, reinforcement learning, and Monte Carlo sampling. We propose several AutoML frameworks that realize these ideas, and describe implementations and experimental results.

Degree

thesis:*
Name thesis:degree_name
Ph. D., Electrical and Computer Engineering
Level thesis:degree_level
Doctor of Philosophy
Discipline thesis:degree_discipline
Electrical and Computer Engineering
Grantor
Cornell University
Year dc:date.issued
2022

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Yang, Chengrun
Chair dc:contributor.chair
  • Udell, Madeleine Richards
Committee members dc:contributor.committeemember
  • Weinberger, Kilian Quirin
  • Joachims, Thorsten

Subjects

dc:subject × 6

Rights

Language dc:language.iso
en

Identifiers

dc:identifier.*
Dc Identifier Bibid
15530002
Dc Identifier Other
ProQuest Submission ID: 12986
ProQuest Publication ID: 29163496

Chain of custody

source
Harvested from
Cornell University
Base URL
ecommons.cornell.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Yang, Chengrun. Automated Machine Learning under Resource Constraints. Doctor of Philosophy thesis, Cornell University, 2022. https://hdl.handle.net/1813/111821