event

Ph.D. Proposal Oral Exam - Riyasat Ohib

Title:  Principled Sparsity for Efficient Deep Learning Across Computational Paradigms

Committee:

Dr. Calhoun, Advisor

Dr. Plis, Co-Advisor

Dr. Anderson, Chair

Dr. Xiong

Media

No media selected

Summary

The objective of the proposed research is to develop and evaluate novel, principled sparsity-inducing techniques to enhance the computational efficiency of deep learning models across diverse applications. This work proposes methods for explicit sparse projection, the discovery of efficient task-specific subnetworks in reinforcement learning, and the design of lightweight federated learning frameworks, with the ultimate goal of enabling more scalable, adaptable, and interpretable AI systems.

Details

Tuesday
Jun 17 2025
10:00am - 12:00pm

Location: Online

In campus calendar: No

Sidebar Content

No sidebar content

Groups

Status

  • Workflow status: Published
  • Created by: Daniela Staiculescu
  • Created: 06/06/2025
  • Modified By: Daniela Staiculescu
  • Modified: 06/06/2025

Related Links

Categories

Keywords

Target Audience