Skip to Main Content
 

Global Search Box

 
 
 

ETD Abstract Container

Abstract Header

Learning at the Edge under Resource Constraints

Regatti, Jayanth Reddy
http://orcid.org/0000-0001-8150-2288
http://rave.ohiolink.edu/etdc/view?acc_num=osu1672937397443621

Abstract Details

2023, Doctor of Philosophy, Ohio State University, Electrical and Computer Engineering.
Recent decades saw a huge increase in the number of personal devices, wearables, edge devices, etc which led to increased data collection and increased connectivity at the edge. This collected data can be used to make insights about health, the economy, and business and help us make better decisions at the individual, organizational and global levels. With the proliferation of these devices, there are also numerous challenges associated with making use of these devices and the data to train useful models. The challenges could be due to privacy regulations or other constraints determined by the particular learning setup. These constraints make it difficult to extract the required insights from the data and the edge systems. The goal of this thesis is to understand these challenges or resource constraints and develop efficient algorithms that enable us to train models while adhering to the constraints. This thesis makes the following contributions: 1. Propose an efficient algorithm FedCMA for model heterogeneous Federated Learning under resource constraints, showed the convergence and generalization properties, and demonstrated the efficacy against state-of-the-art algorithms in the model heterogeneity setting. 2. Proposed a two-timescale aggregation algorithm that does not require the knowledge of the number of adversaries for defending against Byzantine adversaries in the distributed setup, proved the convergence of the algorithm, and demonstrated the defense against state-of-the-art attacks. 3. We highlight the challenges posed by resource constraints in the Offline Reinforcement Learning setup where the observation space during inference is different from the observation space during training. We propose a simple algorithm STPI (Simultaneous Transfer Policy Iteration) to train the agent to adapt to the changes in the observation space and demonstrated the effectiveness of the algorithm on MuJoCo environments against simple baselines.
Abhishek Gupta (Advisor)
Ness Shroff (Advisor)
205 p.
Computer Engineering; Computer Science; Electrical Engineering; Engineering
Federated Learning, Reinforcement Learning, Resource Constraints, Byzantine Learning, Byzantine Attacks, Security, Distributed Learning, offline Reinforcement Learning, Transfer Learning, Generalization, Convergence

Recommended Citations

Citations

  • Regatti, J. R. (2023). Learning at the Edge under Resource Constraints [Doctoral dissertation, Ohio State University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=osu1672937397443621

    APA Style (7th edition)

  • Regatti, Jayanth Reddy. Learning at the Edge under Resource Constraints. 2023. Ohio State University, Doctoral dissertation. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=osu1672937397443621.

    MLA Style (8th edition)

  • Regatti, Jayanth Reddy. "Learning at the Edge under Resource Constraints." Doctoral dissertation, Ohio State University, 2023. http://rave.ohiolink.edu/etdc/view?acc_num=osu1672937397443621

    Chicago Manual of Style (17th edition)

osu1672937397443621
79
© 2023, all rights reserved.
This open access ETD is published by The Ohio State University and OhioLINK.