Publications

AI For Global Climate Cooperation 2023 Competition Proceedings
Yoshua Bengio
Prateek Arun Gupta
Lu Li
Soham R. Phade
Sunil Srinivasa
andrew williams
Tianyu Zhang
Yang Zhang
Stephan Tao Zheng
The international community must collaborate to mitigate climate change and sustain economic growth. However, collaboration is hard to achie… (see more)ve, partly because no global authority can ensure compliance with international climate agreements. Combining AI with climate-economic simulations offers a promising solution to design international frameworks, including negotiation protocols and climate agreements, that promote and incentivize collaboration. In addition, these frameworks should also have policy goals fulfillment, and sustained commitment, taking into account climate-economic dynamics and strategic behaviors. These challenges require an interdisciplinary approach across machine learning, economics, climate science, law, policy, ethics, and other fields. Towards this objective, we organized AI for Global Climate Cooperation, a Mila competition in which teams submitted proposals and analyses of international frameworks, based on (modifications of) RICE-N, an AI-driven integrated assessment model (IAM). In particular, RICE-N supports modeling regional decision-making using AI agents. Furthermore, the IAM then models the climate-economic impact of those decisions into the future. Whereas the first track focused only on performance metrics, the proposals submitted to the second track were evaluated both quantitatively and qualitatively. The quantitative evaluation focused on a combination of (i) the degree of mitigation of global temperature rise and (ii) the increase in economic productivity. On the other hand, an interdisciplinary panel of human experts in law, policy, sociology, economics and environmental science, evaluated the solutions qualitatively. In particular, the panel considered the effectiveness, simplicity, feasibility, ethics, and notions of climate justice of the protocols. In the third track, the participants were asked to critique and improve RICE-N.
2023-07-10
ArXiv (preprint)
doi.org
arxiv.org
International Institutions for Advanced AI
Lewis Ho
Joslyn N. Barnhart
Robert Frederic Trager
Yoshua Bengio
Miles Brundage
Allison Sovey Carnegie
Rumman Chowdhury
Allan Dafoe
Gillian K. Hadfield
Margaret Levi
D. Snidal
2023-07-10
ArXiv (preprint)
doi.org
arxiv.org
Robust and Versatile Bipedal Jumping Control through Reinforcement Learning
Zhongyu Li
Xue Bin Peng
Pieter Abbeel
Sergey Levine
Glen Berseth
Koushil Sreenath
2023-07-10
Robotics: Science and Systems XIX (published)
doi.org
arxiv.org
Overcoming the Technical Challenges of Coordinating Distributed Load Resources at Scale
Johanna Mathieu
Ian Hiskens
Ioannis Marios Granitsas
Oluwagbemileke Oyefeso
Gregory Ledva
Sebastian Nugroho
Salman Nazir
Scott Hinson
Suzanne Russo
Steve Mock
Rachel Jenkins
Jill Harlow
Grant Fisher
Drew Geller
Duncan Callaway
Phillippe Phanivong
Antoine Lesage-Landry
2023-07-08
(published)
doi.org
Adjusting Machine Learning Decisions for Equal Opportunity and Counterfactual Fairness
Yixin Wang
Dhanya Sridhar
David Blei
Machine learning ( ml ) methods have the potential to automate high-stakes decisions, such as bail admissions or credit lending, by analyzin… (see more)g and learning from historical data. But these algorithmic decisions may be unfair: in learning from historical data, they may replicate discriminatory practices from the past. In this paper, we propose two algorithms that adjust fitted ML predictors to produce decisions that are fair. Our methods provide post-hoc adjustments to the predictors, without requiring that they be retrained. We consider a causal model of the ML decisions, define fairness through counterfactual decisions within the model, and then form algorithmic decisions that capture the historical data as well as possible, but are provably fair. In particular, we consider two definitions of fairness. The first is “equal counterfactual opportunity,” where the counterfactual distribution of the decision is the same regardless of the protected attribute; the second is counterfactual fairness. We evaluate the algorithms, and the trade-o � between accuracy and fairness, on datasets about admissions, income, credit, and recidivism.
2023-07-07
TMLR (accepted)
openreview.net
openreview.net
Capacity Planning in Stable Matching: An Application to School Choice
Federico Bobbio
Margarida Carvalho
Andrea Lodi
Ignacio Rios
Alfredo Torrico
Centralized mechanisms are becoming the standard approach to solve several assignment problems. Examples include the allocation of students … (see more)to schools (school choice), high-school graduates to colleges, residents to hospitals and refugees to cities. In most of these markets, a desirable property of the assignment is stability, which guarantees that no pair of agents has incentive to circumvent the matching. Using school choice as our matching market application, we introduce the problem of jointly allocating a school capacity expansion and finding the best stable matching for the students in the expanded market. We analyze theoretically the problem, focusing on the trade-off behind the multiplicity of student-optimal assignments, and the problem complexity. Since the theoretical intractability of the problem precludes the adaptation of classical approaches to solve it efficiently, we generalize existent mathematical programming formulations of stability constraints to our setting. These generalizations result in integer quadratically-constrained programs, which are computationally hard to solve. In addition, we propose a novel mixed-integer linear programming formulation that is exponentially-large on the problem size. We show that the stability constraints can be separated in linear time, leading to an effective cutting-plane method. We evaluate the performance of our approaches in a detailed computational study, and we find that our cutting-plane method outperforms mixed-integer programming solvers applied to existent formulations extended to our problem setting. We also propose two heuristics that are effective for large instances of the problem. Finally, we use the Chilean school choice system data to demonstrate the impact of capacity planning under stability conditions. Our results show that each additional school seat can benefit multiple students. On the one hand, we can focus on access by prioritizing extra seats that benefit previously unassigned students; on the other hand, we can focus on merit by allocating extra seats that benefit several students via chains of improvement. These insights empower the decision-maker in tuning the matching algorithm to provide a fair application-oriented solution.
2023-07-07
Proceedings of the 24th ACM Conference on Economics and Computation (published)
doi.org
Scaling Laws Do Not Scale
Fernando Diaz
Michael Madaio
Recent work has proposed a power law relationship, referred to as ``scaling laws,'' between the performance of artificial intelligence (AI) … (see more)models and aspects of those models' design (e.g., dataset size). In other words, as the size of a dataset (or model parameters, etc) increases, the performance of a given model trained on that dataset will correspondingly increase. However, while compelling in the aggregate, this scaling law relationship overlooks the ways that metrics used to measure performance may be precarious and contested, or may not correspond with how different groups of people may perceive the quality of models' output. In this paper, we argue that as the size of datasets used to train large AI models grows, the number of distinct communities (including demographic groups) whose data is included in a given dataset is likely to grow, each of whom may have different values. As a result, there is an increased risk that communities represented in a dataset may have values or preferences not captured by (or in the worst case, at odds with) the metrics used to evaluate model performance for scaling laws. We end the paper with implications for AI scaling laws -- that models may not, in fact, continue to improve as the datasets get larger -- at least not for all people or communities impacted by those models.
2023-07-05
ArXiv (preprint)
doi.org
arxiv.org
Generative Flow Networks: a Markov Chain Perspective
Tristan Deleu
Yoshua Bengio
2023-07-04
ArXiv (preprint)
doi.org
arxiv.org
Better Training of GFlowNets with Local Credit and Incomplete Trajectories
Ling Pan
Nikolay Malkin
Dinghuai Zhang
Yoshua Bengio
Generative Flow Networks or GFlowNets are related to Monte-Carlo Markov chain methods (as they sample from a distribution specified by an en… (see more)ergy function), reinforcement learning (as they learn a policy to sample composed objects through a sequence of steps), generative models (as they learn to represent and sample from a distribution) and amortized variational methods (as they can be used to learn to approximate and sample from an otherwise intractable posterior, given a prior and a likelihood). They are trained to generate an object
2023-07-03
Proceedings of the 40th International Conference on Machine Learning (published)
doi.org
openreview.net
Bidirectional Learning for Offline Model-based Biological Sequence Design
Can Chen
Yingxue Zhang
Xue (Steve) Liu
Mark Coates
2023-07-03
Proceedings of the 40th International Conference on Machine Learning (published)
doi.org
openreview.net
Bigger, Better, Faster: Human-level Atari with human-level efficiency
Max Schwarzer
Johan Samir Obando Ceron
Aaron Courville
Marc Gendron-Bellemare
Rishabh Agarwal
Pablo Samuel Castro
We introduce a value-based RL agent, which we call BBF, that achieves super-human performance in the Atari 100K benchmark. BBF relies on sca… (see more)ling the neural networks used for value estimation, as well as a number of other design choices that enable this scaling in a sample-efficient manner. We conduct extensive analyses of these design choices and provide insights for future work. We end with a discussion about updating the goalposts for sample-efficient RL research on the ALE. We make our code and data publicly available at https://github.com/google-research/google-research/tree/master/bigger_better_faster.
2023-07-03
Proceedings of the 40th International Conference on Machine Learning (published)
doi.org
openreview.net
Bootstrapped Representations in Reinforcement Learning
Charline Le Lan
Stephen Tu
Mark Rowland
Anna Harutyunyan
Rishabh Agarwal
Marc Gendron-Bellemare
Will Dabney
In reinforcement learning (RL), state representations are key to dealing with large or continuous state spaces. While one of the promises of… (see more) deep learning algorithms is to automatically construct features well-tuned for the task they try to solve, such a representation might not emerge from end-to-end training of deep RL agents. To mitigate this issue, auxiliary objectives are often incorporated into the learning process and help shape the learnt state representation. Bootstrapping methods are today's method of choice to make these additional predictions. Yet, it is unclear which features these algorithms capture and how they relate to those from other auxiliary-task-based approaches. In this paper, we address this gap and provide a theoretical characterization of the state representation learnt by temporal difference learning (Sutton, 1988). Surprisingly, we find that this representation differs from the features learned by Monte Carlo and residual gradient algorithms for most transition structures of the environment in the policy evaluation setting. We describe the efficacy of these representations for policy evaluation, and use our theoretical analysis to design new auxiliary learning rules. We complement our theoretical results with an empirical comparison of these learning rules for different cumulant functions on classic domains such as the four-room domain (Sutton et al, 1999) and Mountain Car (Moore, 1990).
2023-07-03
Proceedings of the 40th International Conference on Machine Learning (published)
doi.org
openreview.net