skip to main content
Back to Project Search

Fine-Tuning of Foundation Models via Low-Rank Adaptation and Beyond

Project

Project Details

Program
Computer Science
Field of Study
optimization, machine learning, artificial intelligence, computer science, mathematics
Division
Computer, Electrical and Mathematical Sciences and Engineering
Faculty Lab Link
https://richtarik.org/index.html

Project Description

Fine-tuning has become a popular approach to adapting large foundational models to specific tasks. As the size of models and datasets grows, parameter-efficient fine-tuning techniques are increasingly important. One of the most widely used methods is Low-Rank Adaptation (LoRA), with adaptation update expressed as the product of two low-rank matrices. While LoRA was shown to possess strong performance in fine-tuning, it often under-performs when compared to full-parameter fine-tuning (FPFT). Although many variants of LoRA have been extensively studied empirically, their theoretical optimization analysis is heavily under-explored.

About the Researcher

Peter Richtarik
Professor, Computer Science
Computer, Electrical and Mathematical Science and Engineering Division

Affiliations

Education Profile

  • PhD, Operations Research, Cornell University, 2007
  • MS, Operations Research, Cornell University, 2006
  • Mgr, Mathematics, Comenius University, 2001
  • Bc, Management Comenius University, 2001
  • Bc, Mathematics, Comenius University, 2000

Research Interests

Prof. Richtarik's research interests lie at the intersection of mathematics, computer science, machine learning, optimization, numerical linear algebra, high performance computing and applied probability. He is interested in developing zero, first, and second-order algorithms for convex and nonconvex optimization problems described by big data, with a particular focus on randomized, parallel and distributed methods. He is the co-inventor of federated learning, a Google platform for machine learning on mobile devices preserving privacy of users' data.

Selected Publications

  • R. M. Gower, D. Goldfarb and P. Richtarik. Stochastic block BFGS: squeezing more curvature out of data, Proceedings of The 33rd International Conference on Machine Learning, pp. 1869-1878, 2016
  • J. Konecny, J. Liu, P. Richtarik and M. Takac. Mini-batch semi-stochastic gradient descent in the proximal setting, IEEE Journal of Selected Topics in Signal Processing 10(2), 242a-255, 2016
  • P. Richtarik and M. Takac. Parallel coordinate descent methods for big data optimization Mathematical Programming 156(1):433a-484, 2016
  • R. M. Gower and P. Richtarik. Randomized iterative methods for linear systems, SIAM Journal on Matrix Analysis and Applications 36(4):1660-1690, 2015
  • O. Fercoq and P. Richtarik. Accelerated, parallel and proximal coordinate descent. SIAM Journal on Optimization 25(4):1997a-2023, 2015

Desired Project Deliverables

The goals of this project: - Propose and evaluate (e.g., theoretically or empirically analyze) new fine-tuning methods, improving upon LoRA and other recently proposed FPFT methods - Write a paper describing the new results, and submit it to a leading AI/ML conference, such as NeurIPS, ICML or ICLR

Recommended Student Background

Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen. LoRA
Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, Luke Zettlemoyer. QLoRA: Efficient Finetuning of Quantized LLMs,
Grigory Malinovsky, Umberto Michieli, Hasan Abed Al Kader Hammoud, Taha Ceritli, Hayder Elesedy, Mete Ozay, Pet
On this page

We are shaping the
World of Research

Be part of the journey with VSRP

Find a Project
3-6 months
Internship period
100+
Research Projects
3.5/4
Cumulative GPA
310
Interns a Year