Workshop
Consequential Decisions in Dynamic Environments
Niki Kilbertus 路 Angela Zhou 路 Ashia Wilson 路 John Miller 路 Lily Hu 路 Lydia T. Liu 路 Nathan Kallus 路 Shira Mitchell
Sat 12 Dec, 8 a.m. PST
Machine learning is rapidly becoming an integral component of sociotechnical systems. Predictions are increasingly used to grant beneficial resources or withhold opportunities, and the consequences of such decisions induce complex social dynamics by changing agent outcomes and prompting individuals to proactively respond to decision rules. This introduces challenges for standard machine learning methodology. Static measurements and training sets poorly capture the complexity of dynamic interactions between algorithms and humans. Strategic adaptation to decision rules can render statistical regularities obsolete. Correlations momentarily observed in data may not be robust enough to support interventions for long-term welfaremits of traditional, static approaches to decision-making, researchers in fields ranging from public policy to computer science to economics have recently begun to view consequential decision-making through a dynamic lens. This workshop will confront the use of machine learning to make consequential decisions in dynamic environments. Work in this area sits at the nexus of several different fields, and the workshop will provide an opportunity to better understand and synthesize social and technical perspectives on these issues and catalyze conversations between researchers and practitioners working across these diverse areas.
Schedule
Sat 8:00 a.m. - 8:10 a.m.
|
Welcome and introduction
(
Live intro
)
>
|
馃敆 |
Sat 8:10 a.m. - 8:30 a.m.
|
Invited Talk 1: What do we want? And when do we want it? Alternative objectives and their implications for experimental design.
(
Prerecorded talk
)
>
link
SlidesLive Video |
Maximilian Kasy 馃敆 |
Sat 8:30 a.m. - 8:50 a.m.
|
Invited Talk 2: Country-Scale Bandit Implementation for Targeted COVID-19 Testing
(
Prerecorded talk
)
>
link
SlidesLive Video |
Hamsa Bastani 馃敆 |
Sat 8:50 a.m. - 9:00 a.m.
|
Q&A for invited talks 1&2
(
Q&A session
)
>
|
馃敆 |
Sat 9:00 a.m. - 10:00 a.m.
|
Poster Session 1
(
Poster session
)
>
|
馃敆 |
Sat 10:00 a.m. - 10:20 a.m.
|
Break 1
|
馃敆 |
Sat 10:20 a.m. - 10:30 a.m.
|
Introduction of invited speakers 3, 4
(
Live intro
)
>
|
馃敆 |
Sat 10:30 a.m. - 10:50 a.m.
|
Invited Talk 3: Modeling the Dynamics of Poverty
(
Prerecorded talk
)
>
link
SlidesLive Video |
Rediet Abebe 馃敆 |
Sat 10:50 a.m. - 11:10 a.m.
|
Invited Talk 4: From Moderate Deviations Theory to Distributionally Robust Optimization: Learning from Correlated Data
(
Prerecorded talk
)
>
link
SlidesLive Video |
Daniel Kuhn 馃敆 |
Sat 11:10 a.m. - 11:20 a.m.
|
Q&A for invited talks 3, 4
(
Q&A session
)
>
|
馃敆 |
Sat 11:20 a.m. - 11:25 a.m.
|
Contributed Talk 1: Fairness Under Partial Compliance
(
Prerecorded talk
)
>
link
SlidesLive Video |
Jessica Dai 路 Zachary Lipton 馃敆 |
Sat 11:25 a.m. - 11:30 a.m.
|
Contributed Talk 2: Better Together? How Externalities of Size Complicate Notions of Solidarity and Actuarial Fairness
(
Prerecorded talk
)
>
SlidesLive Video |
Kate Donahue 路 Solon Barocas 馃敆 |
Sat 11:30 a.m. - 11:35 a.m.
|
Contributed Talk 3: Algorithmic Recourse: from Counterfactual Explanations to Interventions
(
Prerecorded talk
)
>
link
SlidesLive Video |
Amir-Hossein Karimi 路 Bernhard Sch枚lkopf 路 Isabel Valera 馃敆 |
Sat 11:35 a.m. - 11:45 a.m.
|
Q&A for contributed talks 1,2,3
(
Q&A session
)
>
|
馃敆 |
Sat 11:45 a.m. - 12:20 p.m.
|
Break 2
|
馃敆 |
Sat 12:20 p.m. - 12:30 p.m.
|
Introduction of invited speakers 5, 6, 7
(
Live intro
)
>
|
馃敆 |
Sat 12:30 p.m. - 12:50 p.m.
|
Invited Talk 5: What are some hurdles before we can attempt machine learning? Examples from the Public and Non-Profit Sector
(
Prerecorded talk
)
>
link
SlidesLive Video |
Mitsue Iwata 馃敆 |
Sat 12:50 p.m. - 1:13 p.m.
|
Invited Talk 6: Unexpected Consequences of Algorithm-in-the-Loop Decision Making
(
Prerecorded talk
)
>
link
SlidesLive Video |
Yiling Chen 馃敆 |
Sat 1:13 p.m. - 1:35 p.m.
|
Invited Talk 7: Prediction Dynamics
(
Prerecorded talk
)
>
link
SlidesLive Video |
Moritz Hardt 馃敆 |
Sat 1:35 p.m. - 1:50 p.m.
|
Q&A for invited talks 5, 6, 7
(
Q&A session
)
>
|
馃敆 |
Sat 1:50 p.m. - 2:20 p.m.
|
Break 3
|
馃敆 |
Sat 2:20 p.m. - 2:25 p.m.
|
Contributed Talk 4: Strategic Recourse in Linear Classification
(
Prerecorded talk
)
>
link
SlidesLive Video |
Yatong Chen 路 Yang Liu 馃敆 |
Sat 2:25 p.m. - 2:30 p.m.
|
Contributed Talk 5: Performative Prediction in a Stateful World
(
Prerecorded talk
)
>
link
SlidesLive Video |
Shlomi Hod 馃敆 |
Sat 2:30 p.m. - 2:35 p.m.
|
Contributed Talk 6: Do Offline Metrics Predict Online Performance in Recommender Systems?
(
Prerecorded talk
)
>
link
SlidesLive Video |
Karl Krauth 路 Sarah Dean 路 Wenshuo Guo 路 Benjamin Recht 路 Michael Jordan 馃敆 |
Sat 2:35 p.m. - 2:45 p.m.
|
Q&A for contributed talks 4, 5, 6
(
Q&A session
)
>
|
馃敆 |
Sat 2:45 p.m. - 3:45 p.m.
|
Poster Session 2
(
Poster session
)
>
|
馃敆 |
Sat 3:45 p.m. - 3:50 p.m.
|
Wrap up
(
Live wrap up
)
>
|
馃敆 |