Bartolomeo Stellato

📢 New in JMLR (w @rajivsambharya.bsky.social)! 🎉 Data-driven guarantees for classical & learned optimizers via sample bounds + PAC-Bayes theory.

📄 jmlr.org/papers/v26/2...
💻 github.com/stellatogrp/...

📢 Our paper "Verification of First-Order Methods for Parametric Quadratic Optimization" with my student Vinit Ranjan (vinitranjan1.github.io/) is accepted in Mathematical Programming! 🎉

🔗 DOI: doi.org/10.1007/s10107-025-02261-w
📄 arXiv: arxiv.org/pdf/2403.033...
💻 Code: github.com/stellatogrp/...

I’m happy to share that I’ll be spending the fall semester at Princeton as a visiting student in the Department of Operations Research and Financial Engineering (ORFE), working with @stellato.io funded through the WASP program. If you’re in the area and would like to connect, feel free to reach out.

🔄 Updated Arxiv Paper

Title: Exact Verification of First-Order Methods via Mixed-Integer Linear Programming
Authors: Vinit Ranjan, Jisun Park, Stefano Gualandi, Andrea Lodi, Bartolomeo Stellato

Read more: https://arxiv.org/abs/2412.11330

📚 New Arxiv Paper

Title: Data Compression for Fast Online Stochastic Optimization
Authors: Irina Wang, Marta Fochesato, Bartolomeo Stellato

Read more: https://arxiv.org/abs/2504.08097

🚀 Gave a talk at the EURO @euroonline.bsky.social Seminar Series on "Data-Driven Algorithm Design and Verification for Parametric Convex Optimization"!

🎥 Recording: https://euroorml.euro-online.org/

Big thanks to Dolores Romero Morales for the invitation! 🙌 #MachineLearning #Optimization #ORMS

The new season of the Robust Optimization Webinar (#ROW) starts this week. Our first presentation will take place this Friday, January 24, at 15:00 (CET).

Speaker: Peyman Mohajerin Esfahani (TU Delft)

Title: Inverse Optimization: The Role of Convexity in Learning

📚 New Arxiv Paper

Title: Exact Verification of First-Order Methods via Mixed-Integer Linear Programming
Authors: Vinit Ranjan, Stefano Gualandi, Andrea Lodi, Bartolomeo Stellato

Read more: https://arxiv.org/abs/2412.11330

What happens to the hyperparameters of learned optimizers? Turns out, we learn long steps! 🚀

👇 Check out our latest work with @rajivsambharya.bsky.social!

Clustering is a powerful tool for decision-making under uncertainty!

Work w/ my students Irina Wang (lead) and Cole Becker, in collab. w/
Bart Van Parys

🧵 (7/7)

We have several examples in the paper. Here is a sparse portfolio optimization one. Clustering barely affects the solution objective. Speedups are more than 3 orders of magnitude. 🧵 (6/7)

By varying the number of clusters K, our method bridges Robust and Distributionally Robust optimization! We also derive theoretical bounds on 1) how to adjust the Wasserstein ball radius to compensate for clustering, and 2) how to exactly quantify the effect of clustering 🧵 (5/7)

In Mean Robust Optimization, we define an uncertainty set around the cluster centroids with weights defined by the amount of samples in each cluster. 🧵 (4/7)

Our procedure: we first cluster N data points into K clusters. Then, we solve the Mean Robust Optimization problem. 🧵 (3/7)

Robust optimization is tractable but, often, very conservative. Wasserstein Distributionally Robust Optimization is less conservative but, often, computationally expensive. How can we bridge the two? 🧵 (2/7)

Our paper "Mean robust optimization" has been accepted to Mathematical Programming: https://buff.ly/3B3VpIG

📰 Arxiv (longer version): https://buff.ly/3CT4aWD
👩‍💻 Code: https://buff.ly/3ATqAXh

w/ Irina Wang, Cole Becker, and Bart van Parys

A thread 🧵 (1/7)👇

Cool! Thanks for creating this. Could you please add me? :)

Anytime Acceleration of Gradient Descent This work investigates stepsize-based acceleration of gradient descent with {\em anytime} convergence guarantees. For smooth (non-strongly) convex optimization, we propose a stepsize schedule that all...

arxiv.org/abs/2411.17668 Our postdoc zihan slays another COLT open problem! proceedings.mlr.press/v247/kornows...

📚 New Arxiv Paper

Title: Learning Algorithm Hyperparameters for Fast Parametric Convex Optimization
Authors: Rajiv Sambharya, Bartolomeo Stellato

Read more: http://arxiv.org/abs/2411.15717v1

👋👋👋

Congratulations @atlaswang.bsky.social :)

2025 ICS Conference The 18th INFORMS Computing Society (ICS) Conference welcomes you to Toronto, Canada. We invite researchers, practitioners, and innovators to come together and share insights at the cutting edge where...

We are very excited to announce that the 2025 INFORMS Computing Society (ICS) Conference will take place March 14-16, 2025, in Toronto:

sites.google.com/view/ics-2025

Submissions for contributed talks are due on December 23.

We invite talks that showcase the dynamic interface of CS, AI & #ORMS.

New #arxiv bot for #optimization and #control! 🎉

bsky.app/profile/arxi...

Thanks @tmaehara.bsky.social It looks great! I will let you know if I find anything wrong but from a brief look at the first post it looks exactly what one would expect. Thanks again!

By the way, do you consider linear optimization a technology? (if use the 1-norm Mosek gives the correct answer)

Still, some robotics companies use ADMM-based solvers for MPC. If you need only low accuracy solutions and reoptimize very often, first-order solvers can be very effective (especially with warm-starting).

You are right. For any convex solver, you can construct a nasty problem for which it fails. And if it is a first-order solver, it is quite easy to do it 🙂

Sounds great! Thanks a lot

Hey @tmaehara.bsky.social Thanks for the great work on the arxiv bots here! Any chance you could make one for arxiv math.oc (Optimization and Control)? :)

If your favorite book about algorithms is not Algorithms for Toddlers, then you haven’t read this book yet.

Today I used it to talk about greedy algorithms in my Applied Optimization #orms class (some pages below).

Here is one of the authors reading the whole book: m.youtube.com/watch?v=nnLO...