Workshop
Causal Inference Challenges in Sequential Decision Making: Bridging Theory and Practice
Aurelien Bibaut · Maria Dimakopoulou · Nathan Kallus · Xinkun Nie · Masatoshi Uehara · Kelly Zhang
Tue 14 Dec, 10:50 a.m. PST
Sequential decision-making problems appear in settings as varied as healthcare, e-commerce, operations management, and policymaking, and depending on the context these can have very varied features that make each problem unique. Problems can involve online learning or offline data, known cost structures or unknown counterfactuals, continuous actions with or without constraints or finite or combinatorial actions, stationary environments or environments with dynamic agents, utilitarian considerations or fairness or equity considerations. More and more, causal inference and discovery and adjacent statistical theories have come to bear on such problems, from the early work on longitudinal causal inference from the last millenium up to recent developments in bandit algorithms and inference, dynamic treatment regimes, both online and offline reinforcement learning, interventions in general causal graphs and discovery thereof, and more. While the interaction between these theories has grown, expertise is spread across many different disciplines, including CS/ML, (bio)statistics, econometrics, ethics/law, and operations research.
The primary purpose of this workshop is to convene both experts, practitioners, and interested young researchers from a wide range of backgrounds to discuss recent developments around causal inference in sequential decision making and the avenues forward on the topic, especially ones that bring together ideas from different fields. The all-virtual nature of this year's NeurIPS workshop makes it particularly felicitous to such an assembly. The workshop will combine invited talks and panels by a diverse group of researchers and practitioners from both academia and industry together with contributed talks and town-hall Q\&A that will particularly seek to draw from younger individuals new to the area.
Schedule
Tue 10:50 a.m. - 11:00 a.m.
|
Opening Remarks
(
Opening Remarks
)
>
SlidesLive Video |
🔗 |
Tue 11:00 a.m. - 11:30 a.m.
|
TBD (Elias Bareibnboim)
(
Live Talk and Q&A
)
>
SlidesLive Video |
Elias Bareinboim 🔗 |
Tue 11:30 a.m. - 12:00 p.m.
|
Sequential Adaptive Designs for Learning Optimal Individualized Treatment Rules with Formal Inference (Mark van der Laan)
(
Live Talk and Q&A
)
>
SlidesLive Video |
Mark van der Laan 🔗 |
Tue 12:00 p.m. - 12:30 p.m.
|
Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting (Claire Vernade)
(
Live Talk and Q&A
)
>
SlidesLive Video |
Claire Vernade 🔗 |
Tue 12:30 p.m. - 1:10 p.m.
|
Panel Discussion
(
Discussion Panel
)
>
SlidesLive Video |
Elias Bareinboim · Mark van der Laan · Claire Vernade 🔗 |
Tue 1:20 p.m. - 2:20 p.m.
|
Poster Presentation ( Poster Presentation ) > link | 🔗 |
Tue 2:20 p.m. - 2:40 p.m.
|
Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning (Guy Tennenholtz)
(
Oral Presentation
)
>
SlidesLive Video |
Guy Tennenholtz 🔗 |
Tue 2:40 p.m. - 3:00 p.m.
|
MAGNET: Multi-Agent Graph Cooperative Bandits (Hengrui Cai)
(
Oral Presentation
)
>
SlidesLive Video |
Hengrui Cai 🔗 |
Tue 3:00 p.m. - 3:30 p.m.
|
(un)fairness in sequential decision making as a challenge (Razieh Nabi)
(
Live Talk and Q&A
)
>
SlidesLive Video |
Razieh Nabi 🔗 |
Tue 3:30 p.m. - 4:00 p.m.
|
Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process (Rui Song)
(
Live Talk and Q&A
)
>
SlidesLive Video |
Rui Song 🔗 |
Tue 4:00 p.m. - 4:30 p.m.
|
TALK (Susan Athey)
(
Live Talk and Q&A
)
>
SlidesLive Video |
Susan Athey 🔗 |
Tue 4:30 p.m. - 5:10 p.m.
|
Panel Discussion
(
Panel Discussion
)
>
SlidesLive Video |
Susan Athey · Rui Song · Razieh Nabi 🔗 |
Tue 5:30 p.m. - 5:50 p.m.
|
What Would the Expert $do(\cdot)$?: Causal Imitation Learning (Gokul Swamy)
(
Oral Presentation
)
>
SlidesLive Video |
Gokul Swamy 🔗 |
Tue 5:50 p.m. - 6:10 p.m.
|
The Limits to Learning a Diffusion Model (Andy Zheng)
(
Oral Presentation
)
>
SlidesLive Video |
Andrew Zheng 🔗 |
Tue 6:10 p.m. - 6:30 p.m.
|
Deviation-Based Learning (Komiyama Junpei)
(
Oral Presentation
)
>
SlidesLive Video |
Junpei Komiyama 🔗 |
Tue 6:30 p.m. - 6:40 p.m.
|
Closing Remarks
(
Remarks
)
>
|
🔗 |
Tue 6:40 p.m. - 7:30 p.m.
|
Poster Presentation ( Poster Presentation ) > link | 🔗 |
-
|
Bandits with Partially Observable Confounded Data
(
Poster
)
>
|
Guy Tennenholtz · Uri Shalit · Shie Mannor · Yonathan Efroni 🔗 |
-
|
Deviation-Based Learning
(
Poster
)
>
|
Junpei Komiyama · Shunya Noda 🔗 |
-
|
MAGNET: Multi-Agent Graph Cooperative Bandits
(
Poster
)
>
|
Hengrui Cai · Rui Song 🔗 |
-
|
On Adaptivity and Confounding in Contextual Bandit Experiments
(
Poster
)
>
|
Chao Qin · Daniel Russo 🔗 |
-
|
Doubly robust confidence sequences
(
Poster
)
>
|
Ian Waudby-Smith · David Arbour · Ritwik Sinha · Edward Kennedy · Aaditya Ramdas 🔗 |
-
|
A Causality-based Graphical Test to obtain an Optimal Blocking Set for Randomized Experiments
(
Poster
)
>
|
Abhishek Kumar Umrawal 🔗 |
-
|
Kernel Methods for Multistage Causal Inference: Mediation Analysis and Dynamic Treatment Effects
(
Poster
)
>
|
Rahul Singh · Ritsugen Jo · Arthur Gretton 🔗 |
-
|
Reinforcement Learning in Reward-Mixing MDPs
(
Poster
)
>
|
Jeongyeol Kwon · Yonathan Efroni · Constantine Caramanis · Shie Mannor 🔗 |
-
|
Chronological Causal Bandit
(
Poster
)
>
|
Neil Dhir 🔗 |
-
|
Causal Multi-Agent Reinforcement Learning: Review and Open Problems
(
Poster
)
>
|
St John Grimbly · Jonathan Shock · Arnu Pretorius 🔗 |
-
|
Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning
(
Poster
)
>
|
Guy Tennenholtz · Assaf Hallak · Gal Dalal · Shie Mannor · Gal Chechik · Uri Shalit 🔗 |
-
|
Multiple imputation via state space model for missing data in non-stationary multivariate time series
(
Poster
)
>
|
Xiaoxuan Cai · Linda Valeri 🔗 |
-
|
Practical Policy Optimization with PersonalizedExperimentation
(
Poster
)
>
|
Mia Garrard · Hanson Wang · Ben Letham · Zehui Wang · Yin Huang · Yichun Hu · Chad Zhou · Norm Zhou · Eytan Bakshy 🔗 |
-
|
Dynamic Causal Discovery in Imitation Learning
(
Poster
)
>
|
Wenchao Yu 🔗 |
-
|
A Validation Tool for Designing Reinforcement Learning Environments
(
Poster
)
>
|
RUIYANG XU · Zhengxing Chen 🔗 |
-
|
What Would the Expert $do(\cdot)$?: Causal Imitation Learning
(
Poster
)
>
|
Gokul Swamy · Sanjiban Choudhury · James Bagnell · Steven Wu 🔗 |
-
|
Learning Treatment Effects in Panels with General Intervention Patterns
(
Poster
)
>
|
Vivek Farias · Andrew Li · Tianyi Peng 🔗 |
-
|
Partition-based Local Independence Discovery
(
Poster
)
>
|
Inwoo Hwang · Byoung-Tak Zhang · Sanghack Lee 🔗 |
-
|
Understanding User Podcast Consumption Using Sequential Treatment Effect Estimation
(
Poster
)
>
|
Vishwali Mhasawade · Praveen Chandar · Ghazal Fazelnia · Benjamin Carterette 🔗 |
-
|
A Variational Information Bottleneck Principle for Recurrent Neural Networks
(
Poster
)
>
|
ADRIAN TOVAR · Varun Jog 🔗 |
-
|
Off-Policy Evaluation with Embedded Spaces
(
Poster
)
>
|
Jaron Jia Rong Lee · David Arbour · Georgios Theocharous 🔗 |
-
|
Algorithms for Adaptive Experiments that Trade-off Statistical Analysis with Reward: Combining Uniform Random Assignment and Reward Maximization
(
Poster
)
>
|
Jacob Nogas · Arghavan Modiri · · Sofia Villar · Audrey Durand · Anna Rafferty · Joseph Williams 🔗 |
-
|
The Limits to Learning a Diffusion Model
(
Poster
)
>
|
Jackie Baek · Vivek Farias · ANDREEA GEORGESCU · Retsef Levi · Tianyi Peng · Joshua Wilde · Andrew Zheng 🔗 |
-
|
Beyond Ads: Sequential Decision-Making Algorithmsin Public Policy
(
Poster
)
>
|
Peter Henderson · Brandon Anderson · Daniel Ho 🔗 |
-
|
Double/Debiased Machine Learning for Dynamic Treatment Effects via $g$-Estimation
(
Poster
)
>
|
Greg Lewis · Vasilis Syrgkanis 🔗 |
-
|
Estimating the Long-Term Effects of Novel Treatments
(
Poster
)
>
|
Keith Battocchi · Maggie Hei · Greg Lewis · Miruna Oprescu · Vasilis Syrgkanis 🔗 |
-
|
Deviation-Based Learning
(
Oral
)
>
|
Junpei Komiyama · Shunya Noda 🔗 |
-
|
MAGNET: Multi-Agent Graph Cooperative Bandits
(
Oral
)
>
|
Hengrui Cai · Rui Song 🔗 |
-
|
Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning
(
Oral
)
>
|
Guy Tennenholtz · Assaf Hallak · Gal Dalal · Shie Mannor · Gal Chechik · Uri Shalit 🔗 |
-
|
What Would the Expert $do(\cdot)$?: Causal Imitation Learning
(
Oral
)
>
|
Gokul Swamy · Sanjiban Choudhury · James Bagnell · Steven Wu 🔗 |
-
|
The Limits to Learning a Diffusion Model
(
Oral
)
>
|
Jackie Baek · Vivek Farias · ANDREEA GEORGESCU · Retsef Levi · Tianyi Peng · Joshua Wilde · Andrew Zheng 🔗 |