Sparse And Efficient Models For Low Power Devices

Author(s)	Ms. Renjusha P R, Prof. Aparna A
Country	India
Abstract	Parsimony-based models, such as sparse and low-rank representations, are widely used in machine learning and signal processing. However, traditional approaches rely on iterative optimization methods that are computationally expensive and unsuitable for real-time or large-scale applications. This work introduces a process-centric approach that replaces iterative optimization with deterministic, fixed-complexity architectures inspired by proximal algorithms. The proposed method efficiently generates accurate parsimonious representations with significantly reduced computational cost. Furthermore, the framework naturally extends to discriminative learning tasks under appropriate training conditions. Experimental results on challenging image and audio processing problems demonstrate state-of-the-art performance with substantial speed improvements over conventional optimization techniques.
Keywords	Parsimonious Models , Proximal Methods , Learnable Pursuit Processes , Training Regimes
Field	Computer Applications
Published In	Volume 8, Issue 2, March-April 2026
Published On	2026-03-10

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research