The Columbia University Data Science Institute’s Foundations of Data Science Center is hosting a workshop designed to foster collaboration and knowledge sharing. Through talks and posters, Columbia researchers will showcase their work in the diverse realms of data science methods and applications.


Event Registration

Tuesday, April 29, 2025 (9:30 AM – 1:00 PM ET) – In-Person Only

Location: Columbia Engineering Innovation Hub
Address: 2276 12th Ave, New York, NY 10027 – Manhattanville
Registration Deadline: If you do not have an active CUID, the deadline to register is at 12:00 PM the day before the event.

Register


Event Program

9:30 AM – 10:00 AM: Check-In, Breakfast, and Coffee

10:00 AM – 10:45 AM: Keynote

Christopher Harshaw, Assistant Professor of Statistics, Graduate School of Arts and Sciences, Columbia University

Talk Title: The Conflict Graph Design: Estimating Causal Effects Under Network Interference

Abstract: From political science and economics to public health and corporate strategy, the randomized experiment is a widely used methodological tool for estimating causal effects. In the past 15 years or so, there has been a growing interest in network experiments, where subjects are presumed to be interacting in the experiment and their interactions are of substantive interest. While the literature on interference has focused primarily on unbiased and consistent estimation, designing randomized network experiments to ensure tight rates of convergence is relatively under-explored. Not only are the optimal rates of estimation for different causal effects under interference an open question but previously proposed designs are created in an ad-hoc fashion. In this talk, I will present a new experimental design for network experiments called the “Conflict Graph Design” which, given a pre-specified causal effect of interest and the underlying network, produces a randomization over treatment assignment with the goal of increasing the precision of effect estimation. Not only does this experiment design attain improved rates of consistency for several causal effects of interest, it also provides a unifying approach to designing network experiments. We also provide consistent variance estimators and asymptotically valid confidence intervals which facilitate inference of the causal effect under investigation. Joint work with Vardis Kandiros, Charis Pipis, and Costis Daskalakis at MIT.

10:45 AM – 11:00 AM: Coffee Break

11:00 AM – 11:40 AM: Short Talks

  • Testing Causal Models with Hidden Variables in Polynomial Delay via Conditional Independencies
  • Uncertainty Quantification for LLM-Based Survey Simulations
  • Randomized Quasi-Monte Carlo Features for Kernel Approximation
  • Distributional Matrix Completion via Nearest Neighbors in the Wasserstein Space

See team member information in the list of exhibitors below.

11:40 AM – 1:00 PM: Poster Session & Lunch


List of Exhibitors & Poster Numbers

P01: Learning Interpretable Optimal Treatment Regimes Using Kolmogorov-Arnold Networks

  • Faculty Advisor: Youmi Suk, Assistant Professor, Measurement, Evaluation, and Statistics Program, Department of Human Development, Teachers College
  • Chenguang Pan, PhD Student, Human Development, Teachers College
  • Yuxuan Li, PhD Student, Human Development, Teachers College

P02: Geometric Causal Models

  • Faculty Advisor: David Blei, Professor, Statistics and Computer Science, Graduate School of Arts and Sciences and Columbia Engineering
  • Eli Weinstein, Postdoc, Data Science Institute; and Statistics, Graduate School of Arts and Sciences

P03: Fast, Accurate Manifold Denoising by Tunneling Riemannian Optimization

  • Faculty Advisor: John Wright, Associate Professor, Electrical Engineering, Columbia Engineering
  • Mariam Avagyan, PhD Student, Columbia Engineering
  • Yihan Shen, Undergraduate, Computer Science, Columbia Engineering
  • Arnaud Lamy
  • Tingran Wang, PhD Student, MIT
  • Szabolcs Márka, Professor, Physics, Graduate School of Arts and Sciences
  • Zsuzsa Márka, Associate Research Scientist, Columbia Astrophysics Laboratory, Graduate School of Arts and Sciences

P04: Scalable Computation of Causal Bounds

  • Faculty Advisor: Garud Iyengar, Professor, Industrial Engineering and Operations Research, Columbia Engineering; and Avanessians Director, Data Science Institute
  • Madhumitha Shridharan, PhD Student, Columbia Engineering

P05: Probing adaptive decision-making under uncertainty using extended Hidden Markov Models

  • Faculty Advisor: Nuttida Rungratsameetaweemana, Assistant Professor, Biomedical Engineering, Columbia Engineering
  • Rudramani Singha, Research Scientist, Biomedical Engineering, Columbia Engineering
  • Jared Winslow, MS Student, Statistics, Columbia University
  • Robert Kim, Neurology, Cedars-Sinai Medical Center
  • John T Serences, Professor, Psychology, University of California San Diego

P06: Low regret Bayesian learning for Q-functions

  • Faculty Advisor: Shipra Agrawal, Associate Professor, Industrial Engineering and Operations Research, Columbia Engineering
  • Priyank Agrawal, PhD Student, Industrial Engineering and Operations Research, Columbia Engineering

P07: ClusterSC: Advancing Synthetic Control with Donor Selection

  • Faculty Advisor: Rachel Cummings, Associate Professor, Industrial Engineering and Operations Research, Columbia Engineering
  • Faculty Advisor: Vishal Misra, Professor of Computer Science and Vice Dean Computing and AI, Columbia Engineering
  • Andrew Tang, PhD Student, Computer Science, Columbia Engineering
  • Noah Bergam, PhD Student, Computer Science, Columbia Engineering
  • Saeyoung Rho, PhD Student, Computer Science, Columbia Engineering

P08: Experiment Design for Assortment Optimization

  • Will Ma, Associate Professor, Decision, Risk, and Operations, Columbia Business School
  • DreamSports (Dream11)

P09: Adaptive and Efficient Learning with Blockwise Missing and Semi-Supervised Data

  • Faculty Advisor: Ying Wei, Professor, Biostatistics, Mailman School of Public Health
  • Molei Liu, Assistant Professor of Biostatistics, Mailman School of Public Health

P10: A real-time EEG neurofeedback platform to predict Attend level via Muse-S

  • Xiaofu He, Assistant Professor, Clinical Neurobiology, Vagelos College of Physicians and Surgeons
  • Alfredo Spagna, Lecturer, Department of Psychology

P11: Synthetic Blip Effects: Generalizing Synthetic Controls for the Dynamic Treatment Regime

  • Faculty Advisor: Anish Agarwal, Assistant Professor, Industrial Engineering and Operations Research, Columbia Engineering
  • Dwaipayan Saha, PhD Student, Industrial Engineering and Operations Research, Columbia Engineering
  • Vasilis Syrgkanis, Assistant Professor, Management Science and Engineering, Stanford University
  • Sukjin Han, Professor of Economics, University of Bristol

Poster Presenters Giving Short Talks

P12 & Short Talk: Testing Causal Models with Hidden Variables in Polynomial Delay via Conditional Independencies

  • Faculty Advisor: Elias Bareinboim, Associate Professor, Computer Science; and Director, Causal Artificial Intelligence Lab, Columbia Engineering
  • Adiba Ejaz, PhD Student, Computer Science, Columbia Engineering
  • Hyunchai Jeong, PhD Student, Computer Science, Columbia Engineering
  • Jin Tian, Visiting Professor, Computer Science, Columbia Engineering

P13 & Short Talk: Uncertainty Quantification for LLM-Based Survey Simulations

  • Kaizheng Wang, Assistant Professor, Industrial Engineering and Operations Research, Columbia Engineering
  • Chengpiao Huang, PhD Student, Industrial Engineering and Operations Research, Columbia Engineering
  • Yuhang Wu, PhD Student, Decision, Risk, and Operations Division, Columbia Business School

P14 & Short Talk: Randomized Quasi-Monte Carlo Features for Kernel Approximation

  • Faculty Advisor: Zhiliang Ying, Professor, Statistics, Graduate School of Arts and Sciences
  • Yian Huang, PhD Student, Statistics, Graduate School of Arts and Sciences
  • Zhen Huang, PhD Student, Statistics, Graduate School of Arts and Sciences

P15 & Short Talk: Distributional Matrix Completion via Nearest Neighbors in the Wasserstein Space

  • Faculty Advisor: Anish Agarwal, Assistant Professor, Industrial Engineering and Operations Research, Columbia Engineering
  • Jacob Feitelberg, PhD Student, Industrial Engineering and Operations Research, Columbia Engineering
  • Kyuseong Choi, PhD Student, Cornell University, Statistics
  • Raaz Dwivedi, Assistant Professor, Cornell University, ORIE