Repository logo
Log in(current)
Repository logoMIT Open ScholarshipDSpace@MIT
  1. Home
  2. MIT Libraries
  3. MIT Theses
  4. Doctoral Theses
  5. Sampling-based Algorithms for Fast and Deployable AI

Sampling-based Algorithms for Fast and Deployable AI

Thumbnail Image
Download
Name

Baykal-baykal-PhD-EECS-2021-thesis.pdf

Description
Thesis PDF
Size

6.26 MB

Format

Adobe PDF

Checksum (MD5)

69fcb7969c0c8d36640c588e18e8d903

Author(s)
Baykal, Cenk
Advisor(s)
Rus, Daniela
Date Issued
September 2021
Publisher
Massachusetts Institute of Technology
Abstract
We present sampling-based algorithms with provable guarantees to alleviate the increasingly prohibitive costs of training and deploying modern AI systems. At the core of this thesis lies importance sampling, which we use to construct representative subsets of inputs and compress machine learning models to enable fast and deployable systems. We provide theoretical guarantees on the representativeness of the generated subsamples for a variety of objectives, ranging from eliminating data redundancy for efficient training of ML models to compressing large neural networks for real-time inference. In contrast to prior work that has predominantly focused on heuristics, the algorithms presented in this thesis can be widely applied to varying scenarios to obtain provably competitive results. We conduct empirical evaluations on real-world scenarios and data sets that demonstrate the practicality and effectiveness of the presented work.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
http://rightsstatements.org/page/InC-EDU/1.0/
Copyright MIT
Persistent DSpace Link
https://hdl.handle.net/1721.1/139924
Repository logo
PrivacyPermissionsAccessibilityContact us
Repository logo
Notify us about copyright concerns.