Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Adaptive stochastic optimization via trajectory cues

Hinder, Oliver (2022) Adaptive stochastic optimization via trajectory cues. In: Pitt Momentum Fund 2022.

Download (161kB) | Preview


Training machine learning models requires users to select many tuning parameters. For example, a popular training method, stochastic gradient descent, requires users to select a value for the learning rate. These tuning parameters are hard to select and users often resort to time consuming trial-and-error process to find a good set of parameters. This project aims to automate the selection of these tuning parameters by using information inferred from training algorithm trajectories. This will reduce the time spent training machine learning models, and make machine learning more user-friendly.


Social Networking:
Share |


Item Type: Conference or Workshop Item (Other)
CreatorsEmailPitt UsernameORCID
Hinder, Oliverohinder@pitt.edu0000-0002-5077-0359
Centers: Other Centers, Institutes, Offices, or Units > Office of Sponsored Research > Pitt Momentum Fund
Date: 2022
Event Title: Pitt Momentum Fund 2022
Event Type: Other
DOI or Unique Handle: 10.18117/yf90-qp63
Schools and Programs: Swanson School of Engineering > Industrial Engineering
Refereed: No
Uncontrolled Keywords: Seeding Grants - Engineering, Technology, Natural Sciences, and Mathematical Sciences
Other ID: 5083
Date Deposited: 07 Mar 2022 19:57
Last Modified: 17 Feb 2023 21:29


Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item