Try   HackMD

Raghu Meka

HOME RESEARCH TEACHING

My main interests are in complexity theory, learning theory, algorithm design. More generally, I like probability and combinatorics related things. The best resource for up to date publications really is to look up my profile on Google scholar.

You can find a description of some of my recent research work in Quanta article, Science News and in this
video highlight.

Publications

  • Learning Neural Networks with Sparse Activations
    COLT 2024
    Pranjal Awasthi, Nishant Dikkala, Pritish Kamath, Raghu Meka
  • On Convex Optimization with Semi-Sensitive Features
    COLT 2024
    Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Raghu Meka, Chiyuan Zhang
  • Extractors and Secret Sharing Against Bounded Collusion Protocols
    FOCS 2020. (Merger of these two)
    Eshan Chattopadhyay, Jesse Goodman, Vipul Goyal, Ashutosh Kumar, Xin Li, Raghu Meka, David Zuckerman
  • Learning Functions of Halfspaces using Prefix Covers
    COLT 2012
    Parikshit Gopalan, Adam Klivans, Raghu Meka
  • Almost Optimal Explicit Johnson-Lindenstrauss Transformations
    Random 2011
    Daniel Kane, Raghu Meka and Jelani Nelson
Last changed by 
 
Raghu Meka
0
16272

Read more

Algorithmic Machine Learning Spring 2025

In this course we will look at a handful of ubiquitous algorithms in machine learning. We will cover several classical tools in machine learning but more emphasis will be given to recent advances and developing efficient and provable algorithms for learning tasks. A tentative syllabus/schedule can be found below; the topics may change based on student interests as well. You can also check last year's course notes for a more details about what's to come.

Apr 2, 2025
Raghu Meka

raghum@cs.ucla.***, Engineering VI 463.

Apr 1, 2025
Teaching

Here are the courses I have taught or will in the future.

Feb 28, 2025
Algorithmic Machine Learning

In this course we will look at a handful of ubiquitous algorithms in machine learning. We will cover several classical tools in machine learning but more emphasis will be given to recent advances and developing efficient and provable algorithms for learning tasks. A tentative syllabus/schedule can be found below; the topics may change based on student interests as well. You can also check last year's course notes for a more details about what's to come.

May 20, 2024
Read more from Raghu Meka
Published on HackMD