Distributed and error resilient convex optimization formulations in machine learning
Abstract/Contents
- Abstract
- Neural networks have been very successful across many domains in machine learning. Training neural networks typically requires minimizing a high-dimensional non-convex function. Stochastic gradient descent and variants are often used in practice for training neural networks. In this thesis, we describe convex optimization formulations for optimally training neural networks with polynomial activation functions. More specifically, we present semidefinite programming formulations for training neural networks with second degree polynomial activations and show that its solution provides a globally optimal solution to the original non-convex training problem. We then extend this strategy to train quantized neural networks with integer weights. We show that we can globally optimize the training loss with respect to integer weights in polynomial time via semidefinite relaxations and randomized rounding. In the second part of the thesis, we describe a distributed computing and optimization framework to train models, including our convex neural networks. The proposed second order optimization methods in this part rely on approximating the Hessian matrix via random projections. In particular, we describe how to employ randomized sketches in reducing the problem dimensions as well as preserving privacy and improving straggler resilience in asynchronous distributed systems. We present novel approximation guarantees as well as closed-form expressions for debiasing the update directions of the optimization algorithm. Finally, we establish a novel connection between randomized sketching and coded computation. The proposed approach builds on polar codes for straggler-resilient distributed computing.
Description
Type of resource | text |
---|---|
Form | electronic resource; remote; computer; online resource |
Extent | 1 online resource. |
Place | California |
Place | [Stanford, California] |
Publisher | [Stanford University] |
Copyright date | 2022; ©2022 |
Publication date | 2022; 2022 |
Issuance | monographic |
Language | English |
Creators/Contributors
Author | Bartan, Burak |
---|---|
Degree supervisor | Pilanci, Mert |
Thesis advisor | Pilanci, Mert |
Thesis advisor | Lall, Sanjay |
Thesis advisor | Wootters, Mary |
Degree committee member | Lall, Sanjay |
Degree committee member | Wootters, Mary |
Associated with | Stanford University, Department of Electrical Engineering |
Subjects
Genre | Theses |
---|---|
Genre | Text |
Bibliographic information
Statement of responsibility | Burak Bartan. |
---|---|
Note | Submitted to the Department of Electrical Engineering. |
Thesis | Thesis Ph.D. Stanford University 2022. |
Location | https://purl.stanford.edu/st635tm1500 |
Access conditions
- Copyright
- © 2022 by Burak Bartan
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...