2024 Shanghai Workshop on Robustness Meets Causality:
Theory and Applications

Shanghai Qi Zhi Institute, Shanghai, China
Time: July 22 - July 25, 2024


This workshop aims to bring together researchers from the realms of robust statistics (interpreted in its broadest sense), causal inference, and applied scientists from related fields. Over the past decade, there has been growing interest in exploring the interplay between these two disciplines. Robust statistics has had a pervasive influence on the evolution of causal inference, most recently through advances in conformal prediction and distribution-free tests, for example. Meanwhile, the development of causal inference has also exerted a profound influence on robust statistics, notably seen in areas such as invariant prediction. Beyond these, there are also many other research topics that are shared by both fields; some famous examples include double robustness and higher-order influence functions. These topics are not only actively studied by statistical scientists from both disciplines, but have also garnered significant attention from fields such as economics, epidemiology, and computer science.

The central goal of this workshop is to foster new collaborations, exchange new ideas, discover unexplored research topics and discuss their transformative potential in practical applications.


Organizing Committee


July 22 9:45-17:15
Time Speaker Report Topic
9:45 - 10:15 Registration
10:15 - 11:00 Yang Feng
New York University
Design-Based Causal Inference with Missing Outcomes: Missingness Mechanisms,
Imputation-Assisted Randomization Test, and Covariate Adjustment
11:00 - 11:30 Break
11:30 - 12:15 Peng Ding
UC Berkeley
Flexible sensitivity analysis for causal inference in observational studies
subject to unmeasured confounding
12:15 - 13:45 Lunch
13:45 - 14:30 Linbo Wang
The University of Toronto
The synthetic instrument
14:30 - 15:15 Tom Berrett
The University of Warwick
Nonparametric tests of Missing Completely At Random
15:15 - 15:45 Break
15:45 - 16:30 Lihua Lei
Stanford Univerisity
Model-Agnostic Covariate-Assisted Inference on Partially Identified Causal Effects
16:30 - 17:15 Richard Guo
The University of Washington
Hunt, test and aggregate: a flexible framework for testing complex hypotheses

July 23 9:15-20:00
Time Speaker Report Topic
9:15 - 10:00 Jinchi Lv
The University of Southern California
SOFARI: High-dimensional manifold-based inference
10:00 - 10:45 Tengyao Wang
London School of Economics
Residual permutation test for high-dimensional regression coefficient testing
10:45 - 11:15 Break
11:15 - 12:00 Hongyuan Cao
Florida State University
Heritability: a counterfactual perspective
12:00 - 12:45 Oliver Dukes
Ghent University
On nonparametric doubly robust inference
12:45 - 14:15 Lunch
14:15 - 15:00 Lin Liu
Shanghai Jiao Tong University
Nuisance Function Tuning for Optimal Doubly Robust Estimation
15:00 - 15:45 Tim Canning
The University of Edinburgh
Nonparametric classification with missing data
15:45 - 16:15 Break
16:15 - 17:00 Mona Azadkia
London School of Economics and Political Science
A simple measure of conditional dependence
18:00 - 20:00 Banquet

July 24 9:15-20:00
Time Speaker Report Topic
9:15 - 10:00 Fan Li
Duke University
Covariate adjustment in randomized experiments with missing outcomes and covariates
10:00 - 10:45 Zijian Guo
Rutgers University
Adversarially robust learning: identification, estimation, and uncertainty quantification
10:45 - 11:15 Break
11:15 - 12:00 Xiaojie Mao
Tsinghua University
Long-term causal inference under persistent confo unding via data combination
12:00 - 12:45 Dominik Rothenhäusler
Stanford University
Out-of-distribution generalization under random, dense distributional shifts
12:45 - 13:45 Lunch
14:00 - 20:00 Tour

July 25 9:15-14:15
Time Speaker Report Topic
9:15 - 10:00 José Zubizarreta
Harvard University
Anatomy of event studies: hypothetical experiments, exact decomposition,
and robust estimation
10:00 - 10:45 Mingli Chen
The University of Warwick
Nonlinear latent factor models for counterfactual prediction
10:45 - 11:15 Break
11:15 - 12:00 Anqi Zhao
Duke University
A unified look at rerandomization based on p-values from covariate balance tests
12:00 - 12:45 Nicole Pashley
Rutgers University
Design-based causal inference for balanced incomplete block
12:45 - 14:15 Lunch