Nando Fioretto

Thank you, Christian! Here they are: @michaelcardei.bsky.social, @jacobchristopher.bsky.social, (Jinhao is not on bsky)

Grateful to the organizers and DARPA for recognizing our work!

with my students: Jacob Christopher, Michael Cardei, and Jinhao Liang

🔗: neus-2025.github.io/files/papers...:

Excited to share that our work "Neuro-Symbolic Generative Diffusion Models" received a DARPA Disruptive Idea Award at NeuS 2025! 🌟

This work pushes toward integrating symbolic reasoning and generative modeling to meet the safety and robustness demands of scientific applications.

If you are at #NAACL2025 check out our oral: 🔥
"Speculative Diffusion Decoding: Accelerating Language generation through diffusion"

We use discrete diffusion as a drafting model to speed up #LLM inference---up to 7.2x faster over standard generation 🚀

tiny.cc/xt0i001

We are experiencing an assault on science unparalleled by anything I’ve seen in my life. It’s not one issue or another anymore, the entire institution is under attack by the most powerful individuals in the country.

This Friday, where will you be?

standupforscience2025.org

The Privacy Preserving AI workshop is back! And is happening on Monday.

I am excited about our program and lineup of invited speakers!

Check out the program here: ppai-workshop.github.io

disparate effects in downstream decisions (like large-scale allocations) and the surprising role of differential privacy in this setting.

🖇️ arxiv.org/pdf/2408.08471 (2/2)

If you are at #AAAI2025 come and see our oral presentation today in Room 122A at 11:15AM.

The paper "Fairness Issues and Mitigations in (Differentially Private) Socio-demographic Data Processes" shows how sampling errors in survey data can introduce (1/2)

Learning To Solve Differential Equation Constrained Optimization Problems Differential equations (DE) constrained optimization plays a critical role in numerous scientific and engineering fields, including energy systems, aerospace engineering, ecology, and finance, where o...

We apply them to complex energy optimization and financial applications.

🖇️ arxiv.org/abs/2410.01786

Learning To Solve Differential Equation Constrained Optimization Problems Differential equations (DE) constrained optimization plays a critical role in numerous scientific and engineering fields, including energy systems, aerospace engineering, ecology, and finance, where o...

Learning to Solve Differential Equation Constrained Optimization Problems was awarded a spotlight at ICLR 2025 ✨

Congrats to my student Vincenzo Di Vito!

We show how to build neural surrogates to solve constrained optimization problems coupled with system dynamics.

I just want to scream at my LaTeX compiler today! 😭

What are your biggest takes from attending #NeurIPS24? Where do you think the field is moving/should move?

Is there a Machine Learning floor in my hotel?

Tomorrow (Dec 12) poster #2503! Come talk with us about our #NeurIPS work on constrained diffusion models!

I'll be at #NeurIPS from Thursday to Saturday. DM me I'd you like to chat about generative ML for science or responsible AI broadly!

Huge congratulations to James Kotary on defending his dissertation with flying colors!! 👏🔥🎉

Title of his dissertation: "Integrating Constrained Optimization with Machine Learning to Enhance Data-Driven Decision Making"
j-kota.github.io

Receiving reviews on Thanksgiving day is brutal! Should you be thankful for the reviews received? 🤔

🆘Help needed!

Are you working on Privacy (from a Technical (e.g., Differential Privacy), Policy, or Law perspective)?

Please give your availability to review for PPAI (ppai-workshop.github.io) if you can!
We'd highly appreciate it! 🙏

forms.gle/dqjVsBsR2y81...

very nice!

You ask and PPAI listens! We have extended the submission deadline of a few days, now papers are accepted until **November 29**!

The AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI-25) (ppai-workshop.github.io) looks forward to receive your best work!

Excited to share our #NeurIPS2024 work on combining diffusion models with constrained optimization to generate data adhering to constraints and physical principles (with guarantees!) will be a spotlight at the workshop on AI for Accelerated Materials Design!

🔗 arxiv.org/abs/2402.03559

Thank you! ✨

Differential Privacy Researchers Join the conversation

#DifferentialPrivacy starter pack by @thegautamkamath.bsky.social

Nice! Would love to be added! We work on diffusion models for scientific and engineering applications

Would love to be added

Would love to be added

I am not too surprised. Anchoring is really powerful

Joonhyuk Ko, Juba Ziani, Saswat Das, Matt Williams, Ferdinando Fioretto
Fairness Issues and Mitigations in (Differentially Private) Socio-demographic Data Processes
https://arxiv.org/abs/2408.08471

Differential Privacy Overview and Fundamental Techniques This chapter is meant to be part of the book "Differential Privacy in Artificial Intelligence: From Theory to Practice" and provides an introduction to Differential Privacy. It starts by illustrating ...

Going to advertise this here too, but we have a new book on differential privacy led by Nando Fioretto and Pascal Van Hentenryck!

I was asked to contribute to the first, intro chapter, available here: arxiv.org/abs/2411.04710

Full book available soon!

If you are on the job market, and work on the kinds of topics that might be published in FORC ("Foundations of Responsible Computing"), fill out this form and get on the job list. This covers mathematical research on privacy, fairness, and related topics.