Workshop
Responsible Decision Making in Dynamic Environments
Virginie Do · Thorsten Joachims · Alessandro Lazaric · Joelle Pineau · Matteo Pirotta · Harsh Satija · Nicolas Usunier
Ballroom 1
Sat 23 Jul, 6 a.m. PDT
Algorithmic decision-making systems are increasingly used in sensitive applications such as advertising, resume reviewing, employment, credit lending, policing, criminal justice, and beyond. The long-term promise of these approaches is to automate, augment and/or eventually improve on the human decisions which can be biased or unfair, by leveraging the potential of machine learning to make decisions supported by historical data. Unfortunately, there is a growing body of evidence showing that the current machine learning technology is vulnerable to privacy or security attacks, lacks interpretability, or reproduces (and even exacerbates) historical biases or discriminatory behaviors against certain social groups.
Most of the literature on building socially responsible algorithmic decision-making systems focus on a static scenario where algorithmic decisions do not change the data distribution. However, real-world applications involve nonstationarities and feedback loops that must be taken into account to measure and mitigate fairness in the long-term. These feedback loops involve the learning process which may be biased because of insufficient exploration, or changes in the environment's dynamics due to strategic responses of the various stakeholders. From a machine learning perspective, these sequential processes are primarily studied through counterfactual analysis and reinforcement learning.
The purpose of this workshop is to bring together researchers from both industry and academia working on the full spectrum of responsible decision-making in dynamic environments, from theory to practice. In particular, we encourage submissions on the following topics: fairness, privacy and security, robustness, conservative and safe algorithms, explainability and interpretability.
Schedule
Sat 6:00 a.m. - 2:30 p.m.
|
Please visit the workshop website for the full program ( Program ) > link | 🔗 |
Sat 6:00 a.m. - 6:10 a.m.
|
Introduction and opening remarks
(
Intro
)
>
SlidesLive Video |
🔗 |
Sat 6:10 a.m. - 6:40 a.m.
|
Responsible Decision-Making in Batch RL Settings
(
Keynote
)
>
SlidesLive Video |
Finale Doshi-Velez 🔗 |
Sat 6:40 a.m. - 8:00 a.m.
|
Poster session (in-person only, with coffee break)
(
Poster session
)
>
|
🔗 |
Sat 8:00 a.m. - 8:30 a.m.
|
Robust Multivalid Uncertainty Quantification
(
Keynote
)
>
SlidesLive Video |
Aaron Roth 🔗 |
Sat 8:30 a.m. - 8:45 a.m.
|
Individually Fair Learning with One-Sided Feedback
(
Contributed talk
)
>
SlidesLive Video |
Yahav Bechavod 🔗 |
Sat 8:45 a.m. - 9:00 a.m.
|
Reward Reports for Reinforcement Learning
(
Contributed talk
)
>
SlidesLive Video |
Nathan Lambert 🔗 |
Sat 11:00 a.m. - 11:30 a.m.
|
Dimension Reduction Tools and Their Use in Responsible Data Understanding in Dynamic Environments
(
Keynote
)
>
SlidesLive Video |
Cynthia Rudin 🔗 |
Sat 11:30 a.m. - 12:00 p.m.
|
Explanations in Whose Interests?
(
Keynote
)
>
SlidesLive Video |
🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
Poster session (in-person only, with coffee break)
(
Poster session
)
>
|
🔗 |
Sat 1:00 p.m. - 1:30 p.m.
|
Exposure-Aware Recommendation using Contextual Bandits
(
Keynote
)
>
SlidesLive Video |
🔗 |
Sat 1:30 p.m. - 2:00 p.m.
|
Modeling Recommender Ecosystems - Some Considerations
(
Keynote
)
>
SlidesLive Video |
Craig Boutilier 🔗 |
Sat 2:00 p.m. - 2:15 p.m.
|
Optimal Rates of (Locally) Differentially Private Heavy-tailed Multi-Armed Bandits
(
Contributed talk
)
>
SlidesLive Video |
Yulian Wu 🔗 |
Sat 2:15 p.m. - 2:30 p.m.
|
A Game-Theoretic Perspective on Trust in Recommendation
(
Contributed talk
)
>
SlidesLive Video |
Sarah Cen 🔗 |
-
|
Combining Counterfactuals With Shapley Values To Explain Image Models
(
Poster
)
>
|
Aditya Lahiri · Kamran Alipour · Ehsan Adeli · Babak Salimi 🔗 |
-
|
Perspectives on Incorporating Expert Feedback into Model Updates
(
Poster
)
>
|
Valerie Chen · Umang Bhatt · Hoda Heidari · Adrian Weller · Ameet Talwalkar 🔗 |
-
|
Individually Fair Learning with One-Sided Feedback
(
Poster
)
>
|
Yahav Bechavod · Aaron Roth 🔗 |
-
|
Robust Reinforcement Learning with Distributional Risk-averse formulation
(
Poster
)
>
|
Pierre Clavier · Stephanie Allassonniere · Erwann LE PENNEC 🔗 |
-
|
Optimal Dynamic Regret in LQR Control
(
Poster
)
>
|
Dheeraj Baby · Yu-Xiang Wang 🔗 |
-
|
Optimal Rates of (Locally) Differentially Private Heavy-tailed Multi-Armed Bandits
(
Poster
)
>
|
Yulian Wu · Youming Tao · Peng Zhao · Di Wang 🔗 |
-
|
RISE: Robust Individualized Decision Learning with Sensitive Variables
(
Poster
)
>
|
Xiaoqing (Ellen) Tan · Zhengling Qi · Christopher Seymour · Lu Tang 🔗 |
-
|
Adversarial Cheap Talk
(
Poster
)
>
|
Christopher Lu · Timon Willi · Alistair Letcher · Jakob Foerster 🔗 |
-
|
Acting Optimistically in Choosing Safe Actions
(
Poster
)
>
|
Tianrui Chen · Aditya Gangrade · Venkatesh Saligrama 🔗 |
-
|
Dynamic Positive Reinforcement For Long-Term Fairness
(
Poster
)
>
|
Bhagyashree Puranik · Upamanyu Madhow · Ramtin Pedarsani 🔗 |
-
|
An Investigation into the Open World Survival Game Crafter
(
Poster
)
>
|
Aleksandar Stanic · Yujin Tang · David Ha · Jürgen Schmidhuber 🔗 |
-
|
Equity and Equality in Fair Federated Learning
(
Poster
)
>
|
Hamid Mozaffari · Amir Houmansadr 🔗 |
-
|
Certifiably Robust Multi-Agent Reinforcement Learning against Adversarial Communication
(
Poster
)
>
|
Yanchao Sun · Ruijie Zheng · Parisa Hassanzadeh · Yongyuan Liang · Soheil Feizi · Sumitra Ganesh · Furong Huang 🔗 |
-
|
Prisoners of Their Own Devices: How Models Induce Data Bias in Performative Prediction
(
Poster
)
>
|
José Maria Pombal · Pedro Saleiro · Mario Figueiredo · Pedro Bizarro 🔗 |
-
|
A Decision Metric for the Use of a Deep Reinforcement Learning Policy
(
Poster
)
>
|
Christina Selby · Edward Staley 🔗 |
-
|
Safe and Robust Experience Sharing for Deterministic Policy Gradient Algorithms
(
Poster
)
>
|
Baturay Sağlam · Dogan Can Cicek · Furkan Burak Mutlu · Suleyman Kozat 🔗 |
-
|
Planning to Fairly Allocate: Probabilistic Fairness in the Restless Bandit Setting
(
Poster
)
>
|
Christine Herlihy · Aviva Prins · Aravind Srinivasan · John P Dickerson 🔗 |
-
|
Exposing Algorithmic Bias through Inverse Design
(
Poster
)
>
|
Carmen Mazijn · Carina Prunkl · Andres Algaba · Jan Danckaert · Vincent Ginis 🔗 |
-
|
Reward Reports for Reinforcement Learning
(
Poster
)
>
|
Thomas Krendl Gilbert · Sarah Dean · Nathan Lambert · Tom Zick · Aaron Snoswell 🔗 |
-
|
Rashomon Capacity: Measuring Predictive Multiplicity in Probabilistic Classification
(
Poster
)
>
|
Hsiang Hsu · Flavio Calmon 🔗 |
-
|
Counterfactual Metrics for Auditing Black-Box Recommender Systems for Ethical Concerns
(
Poster
)
>
|
Nil-Jana Akpinar · Liu Leqi · Dylan Hadfield-Menell · Zachary Lipton 🔗 |
-
|
Adaptive Data Debiasing Through Bounded Exploration
(
Poster
)
>
|
Yifan Yang · Yang Liu · Parinaz Naghizadeh 🔗 |
-
|
Fairness Over Utilities Via Multi-Objective Rewards
(
Poster
)
>
|
Jack Blandin · Ian Kash 🔗 |
-
|
Defining and Characterizing Reward Gaming
(
Poster
)
>
|
Joar Skalse · Nikolaus Howe · Dmitrii Krasheninnikov · David Krueger 🔗 |
-
|
End-to-end Auditing of Decision Pipelines
(
Poster
)
>
|
Benjamin Laufer · Emma Pierson · Nikhil Garg 🔗 |
-
|
Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning
(
Poster
)
>
|
Yongyuan Liang · Yanchao Sun · Ruijie Zheng · Furong Huang 🔗 |
-
|
Engineering a Safer Recommender System
(
Poster
)
>
|
Liu Leqi · Sarah Dean 🔗 |
-
|
RiskyZoo: A Library for Risk-Sensitive Supervised Learning
(
Poster
)
>
|
William Wong · Audrey Huang · Liu Leqi · Kamyar Azizzadenesheli · Zachary Lipton 🔗 |
-
|
Open Problems in (Un)fairness of the Retail Food Safety Inspection Process
(
Poster
)
>
|
Tanya Berger-Wolf · Allison Howell · Chris Kanich · Ian Kash · Barbara Kowalcyk · Gina Nicholson Kramer · Andrew Perrault · Shubham Singh 🔗 |
-
|
From Soft Trees to Hard Trees: Gains and Losses
(
Poster
)
>
|
Xin Zeng · Jiayu Yao · Finale Doshi-Velez · Weiwei Pan 🔗 |
-
|
Success of Uncertainty-Aware Deep Models Depends on Data Manifold Geometry
(
Poster
)
>
|
Mark Penrod · Harrison Termotto · Varshini Reddy · Jiayu Yao · Finale Doshi-Velez · Weiwei Pan 🔗 |
-
|
Long Term Fairness for Minority Groups via Performative Distributionally Robust Optimization
(
Poster
)
>
|
Liam Peet-Pare · Alona Fyshe · Nidhi Hegde 🔗 |
-
|
A Game-Theoretic Perspective on Trust in Recommendation
(
Poster
)
>
|
Sarah Cen · Andrew Ilyas · Aleksander Madry 🔗 |
-
|
Optimizing Personalized Assortment Decisions in the Presence of Platform Disengagement
(
Poster
)
>
|
Mika Sumida · Angela Zhou 🔗 |
-
|
Machine Learning Explainability & Fairness: Insights from Consumer Lending
(
Poster
)
>
|
Sormeh Yazdi · Laura Blattner · Duncan McElfresh · P-R Stark · Jann Spiess · Georgy Kalashnov 🔗 |
-
|
Policy Fairness in Sequential Allocations under Bias Dynamics
(
Poster
)
>
|
Meirav Segal · Anne-Marie George · Christos Dimitrakakis 🔗 |
-
|
A law of adversarial risk, interpolation, and label noise
(
Poster
)
>
|
Daniel Paleka · Amartya Sanyal 🔗 |
-
|
LPI: Learned Positional Invariances for Transfer of Task Structure and Zero-shot Planning
(
Poster
)
>
|
Tamas Madarasz 🔗 |
-
|
The Backfire Effects of Fairness Constraints
(
Poster
)
>
|
Yi Sun · Alfredo Cuesta Infante · Kalyan Veeramachaneni 🔗 |
-
|
Beyond Adult and COMPAS: Fairness in Multi-Class Prediction
(
Poster
)
>
|
Wael Alghamdi · Hsiang Hsu · Haewon Jeong · Hao Wang · Peter Winston Michalak · Shahab Asoodeh · Flavio Calmon 🔗 |