CompSust-2023

2023 NeurIPS Workshop on
Computational Sustainability:
Pitfalls and Promises from
Theory to Deployment

December 15, 2023
New Orleans, Louisiana

2023 NeurIPS Workshop on Computational Sustainability: Pitfalls and Promises from Theory to Deployment

December 15th, New Orleans, Louisiana
Contact: neurips-workshop2023@compsust.net

Computational sustainability (CompSust) is an interdisciplinary research area that uses computational methods to help address the 17 United Nations Sustainable Development Goals (UN SDGs), including but not limited to hunger and poverty reduction, infrastructure development, and environmental conservation. Computational sustainability is a two-way street: sustainability domains benefit from computational tools and methods and computational research areas benefit from the unique challenges that arise in attempting to address sustainability problems, including noisy and biased data, complex multi-agent systems, and multi-objective problems. Previous computational sustainability problems have led to new approaches in computer vision, reinforcement learning, multi-agent systems, and decision-focused learning. While computational sustainability problems span many domains, they share common challenges.

The Computational Sustainability Workshop @ NeurIPS 2023 (CompSust 2023) focuses on computational methods for balancing environmental, economic, and societal needs for a sustainable future. The theme of this workshop is “Promises and Pitfalls from Theory to Deployment.” This workshop will bring the community together to focus on two topics:

• The path from theory to deployment: While a goal of computational sustainability is to achieve broader impacts, many challenges arise on the path from theory to deployment. This workshop will help researchers navigate this path by bringing together participants and speakers from academia, industry, and non-profits, highlighting successes going from theory to deployment, and facilitating collaboration.
• Promises and pitfalls: Advances on ML benchmarks do not always translate to improvements in computational sustainability problems, with contributing factors including low-signal-to-noise ratios, ever changing conditions, and biased or imbalanced data. However, due to the difficulties of publishing negative results, these findings rarely reach the community leading to duplicated effort and obscuring important gaps in existing methods.

The goals of this workshop are to (i) identify pathways from theory to deployment, including best-practices and measures to quantify success, (ii) facilitate discussion and collaboration between participants with diverse backgrounds, including academia, industry, and the non-profit sector, and (iii) identify common failure modes and high-impact research directions, including “moonshot’’ challenges.

Speakers and Panelists

Hannah Kerner ASU, NASA Harvest	Grant Van Horn UMass, Cornell Lab of Ornithology	David Dao ETH Zurich, GainForest	David Rolnick McGill, MILA	Sara Beery MIT
Carla Gomes Cornell	Emily Aiken UC Berkeley	Caleb Robinson Microsoft AI for Good	Eric Orenstein MBARI

Call for Papers

We invite submission of 4 pages (excluding references, submission anonymized) on topics related to deploying computational sustainability methods. Submission reviews will be double-blind. Supplementary appendices are allowed but will be read at the discretion of the reviewers. The purpose of this workshop is not specifically as a venue for publication so much as a place to gather together those in the community working on or interested in computational sustainability, particularly around deploying models in the wild. The workshop does not publish proceedings, and submissions are non-archival. Submission to this workshop does not preclude future publication. Submissions of work which has been previously published, including papers accepted to the main NeurIPS 2023 conference are allowed this year. We will also consider submissions where work on the same topic has been submitted to other NeurIPS workshops. However, submissions should not be identical.

While the goal of computational sustainability is to create positive impacts, the potential for broad social impacts makes it important to consider ethical concerns and potential unintended consequences, including but not limited to issues around security, bias, and fairness. We encourage participants to follow the NeurIPS code of ethics and include a statement of potential ethical considerations in their submission.

Papers should be submitted through OpenReview and use the workshop template based on the NeurIPS style file. The LaTeX version of the workshop template is available for download or as an Overleaf template. While we strongly encourage LaTeX submission, a Microsoft Word template is available upon request. A single PDF should be submitted with any supplementary material included in appendices after the main submission.

Papers accepted to the workshop will be allowed an extra page for a total of 5 pages for the camera-ready submission.

Important dates
Deadline for Submission:	October 3, 2023
Notification of acceptance:	October 21, 2023
Camera Ready Deadline:	November 15, 2023
Workshop:	December 15, 2023

Collaborathon

Following in the tradition of previous CompSust DCs, our workshop will include a 90-minute “collaborathon", to facilitate collaboration and identify high-impact research directions. Focused discussion groups will be led by 5-10 volunteers, chosen from participants and members of the organizing team, to identify key challenges in specific sustainability domains, and each discussion group will be invited to give a short 5-minute pitch of their ideas at the end of the session. This structured networking and collaboration session has proven successful at previous CompSust DCs, where collaborathon ideas have later developed into paper and thesis topics.

Past Events

• CompSust-2022 Doctoral Consortium on Computational Sustainability, March 11–12, 2022, Virtual
• CompSust-2020 Doctoral Consortium on Computational Sustainability, October 17–18, 2020, Virtual
• CompSust-2019 Doctoral Consortium on Computational Sustainability, October 18–20, 2019, Carnegie Mellon University, Pittsburgh, PA
• CompSust-2018 Doctoral Consortium on Computational Sustainability, September 14–16, 2018, Cornell University, Ithaca, NY
• CompSust-2017 Doctoral Consortium on Computational Sustainability, July 13–14, 2017, University of Southern California, Los Angeles, CA
• CompSust-2016 Conference, July 6–8, 2016, Cornell University, Ithaca, NY, U.S.A.
• Conference on Conservation, Computation, & Criminology (C4) June 29–30, 2015, Washington DC, U.S.A.
• CompSust'12 Conference, July 4–6, 2012, Copenhagen, Denmark
• CompSust'10 Conference, June 28–30, 2010, Boston MA, U.S.A.
• CompSust09 Conference, June 8–11, Ithaca NY, U.S.A.