NeurIPS 2025 Workshop on Constrained Optimization for Machine Learning

About the Workshop

As AI systems are increasingly deployed in safety-critical domains—including credit scoring, medical diagnosis, and autonomous systems—there is a growing demand to ensure their fairness, safety, robustness, and interpretability, alongside stronger calls for regulation. Constrained optimization offers an accountable framework for enforcing these requirements by embedding them directly into the training process, steering models to satisfy explicit constraints. This framework facilitates compliance with regulatory, industry, or ethical standards, which can be easily verified by checking constraint satisfaction.

This workshop explores constrained optimization as a principled method for enforcing desirable properties in machine learning models. It brings together experts in optimization, machine learning, and trustworthy AI to address the algorithmic and practical challenges of scaling constrained methods to modern deep learning settings, which are often large-scale, non-convex, and stochastic.

We invite contributions that advance the state of the art in Constrained Learning. For details, see the Call for Contributions.

News

• We are accepting extended abstracts for oral and poster presentations. See the Call for Contributions for more details.
• If you are interested in reviewing for the workshop, please fill out the reviewer nomination form by August 21st.
• Submit questions for our panelists here.

Dates & Deadlines

• Extended abstract submission deadline: Aug 21, 2025 Aug 28, 2025 (AOE)
• Author notification: Sep 22, 2025
• NeurIPS early registration deadline: Oct 11, 2025 (AOE)
• Camera-ready version: Oct 31, 2025 (AOE)
• NeurIPS financial assistance application deadline: TBA

Speakers

Luiz Chamon

Hi! Paris & École Polytechnique

Frank E. Curtis

Lehigh University

Emily Ruth Diana

Carnegie Mellon University

Ferdinando Fioretto

University of Virginia

FAQ

• Can I attend virtually?

  All talks will be live-streamed, so you can follow them online. However, the poster session is in-person only, and we strongly encourage everyone to attend in person if possible to get the most out of the experience

• What does non-archival mean?

  Non-archival means that your submission will not be published in formal proceedings or indexed in academic databases. You still retain the right to publish the same work elsewhere.

• Can I submit work that was already accepted at another conference?

  No. Following NeurIPS 2025 workshop guidelines, we only accept work that has not been previously published (see the Call for Contributions for details). We encourage submissions of work in progress, early-stage ideas, or research not yet published elsewhere. The goal is to foster discussion and feedback on developing work.

• Does the workshop provide financial aid?

  Please note that we are unable to provide financial support for travel or accommodation. If you require assistance to attend the workshop, we encourage you to check the NeurIPS financial assistance page.

Questions?