Contact:

About:

My research interests are broadly at the intersection of algorithms, theoretical machine learning, and the foundations of data science, including:

• online learning, bandits, decision making, and games
• distributed algorithms, opinion dynamics, and computation in multi-agent settings
• differentially private statistics and optimization

News:

• December 2023: will be attending OPT2023 @ NeurIPS to present our work on decentralized learning dynamics.
• August 2023: presented at the Yale Theory Student Seminar.
• August 2023: gave a short talk and poster at WOLA 2023.
• During the Winter/Spring 2023 semester, I was a visitor at IST Austria hosted by Dan Alistarh.
• In Summer 2022, I interned with the privacy-preserving machine learning research group at Meta in NYC, where I collaborated with Sen Yuan and Huanyu Zhang.

Publications:

• Dan Alistarh, Krishnendu Chatterjee, Mehrdad Karrabi, and John Lazarsfeld
  Game Dynamics and Equilibrium Computation in the Population Protocol Model
  February 2024 -- preprint; to appear in PODC 2024
  [ArXiv]
• John Lazarsfeld and Dan Alistarh
  The Power of Populations in Decentralized Bandits
  June 2023 -- preprint; preliminary version appeared in OPT workshop at NeurIPS 2023
  [ArXiv]
• Talley Amir, James Aspnes, Petra Berenbrink, Felix Biermeier, Christopher Hahn, Dominik Kaaser, and John Lazarsfeld
  Fast Convergence of k-Opinion Undecided State Dynamics in the Population Protocol Model
  PODC 2023
  [ArXiv] [Proceedings]
• John Lazarsfeld, Aaron Johnson, and Emmanuel Adeniran
  Differentially Private Maximal Information Coefficients
  ICML 2022
  [ArXiv] [Proceedings]
• John Lazarsfeld and Aaron Johnson
  Consistency of the Maximal Information Coefficient Estimator
  July 2021 -- corrects an error in previous work of Reshef et al. (JMLR, 2016)
  [ArXiv]
• Talley Amir, James Aspnes, and John Lazarsfeld
  Approximate Majority With Catalytic Inputs
  OPODIS 2020
  [ArXiv] [Proceedings]
• John Lazarsfeld, Jonathan Rodríguez, Mert Erden, Yuelin Liu, and Lenore Cowen
  Majority Vote Cascading: A Semi-Supervised Framework for Improving Protein Function Prediction
  ACM BCB 2019 - Companion poster named Best Poster
  [Conf. Proceedings] [Code and Data]

Teaching:

• Yale CPSC 569: Randomized Algorithms
  Graduate Teaching Fellow
  Spring 2024
• Yale CPSC 565: Distributed Algorithms
  Graduate Teaching Fellow
  Fall 2023, Fall 2022
• Yale CPSC 365: Introduction to Algorithms
  Graduate Teaching Fellow
  Spring 2022, Spring 2021
• Yale CPSC 202: Mathematical Tools for Computer Science
  Graduate Teaching Fellow
  Fall 2021, Fall 2020
• Tufts COMP 160: Introduction to Algorithms
  Graduate Teaching Assistant
  Spring 2019; Summer 2019

Other: