Lightnews — Scholar-powered news

Bartolomeo Stellato @stella.to · Sep 8

📢 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/...

3 6

Bartolomeo Stellato @stella.to · Aug 8

📢 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/...

1 9

Reposted by Bartolomeo Stellato

Paul Häusner @paulhausner.bsky.social · Aug 6

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.

1 11

Reposted by Bartolomeo Stellato

ArXiv math.OC Optimization and Control @optb0t.bsky.social · Apr 8

🔄 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

2 6

Reposted by Bartolomeo Stellato

ArXiv math.OC Optimization and Control @optb0t.bsky.social · Apr 14

📚 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

2 3

Bartolomeo Stellato @stella.to · Feb 26

🚀 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

1 6

Reposted by Bartolomeo Stellato

Jannis Kurtz @jannisku.bsky.social · Jan 20

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

1 3 15

Reposted by Bartolomeo Stellato

ArXiv math.OC Optimization and Control @optb0t.bsky.social · Dec 17

📚 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

3 9

Bartolomeo Stellato @stella.to · Dec 9

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

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

3 10

Bartolomeo Stellato @stella.to · Nov 29

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)

1

Bartolomeo Stellato @stella.to · Nov 29

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)

1 1 1

Bartolomeo Stellato @stella.to · Nov 29

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)

1 1

Bartolomeo Stellato @stella.to · Nov 29

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)

1

Bartolomeo Stellato @stella.to · Nov 29

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

1

Bartolomeo Stellato @stella.to · Nov 29

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)

1

Bartolomeo Stellato @stella.to · Nov 29

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)👇

1 7 28

Bartolomeo Stellato @stella.to · Nov 28

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

Reposted by Bartolomeo Stellato

Jason Lee @jasondeanlee.bsky.social · Nov 27

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

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

1 11 68

Reposted by Bartolomeo Stellato

ArXiv math.OC Optimization and Control @optb0t.bsky.social · Nov 26

📚 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

2 2

Bartolomeo Stellato @stella.to · Nov 22

👋👋👋

1

Bartolomeo Stellato @stella.to · Nov 22

Congratulations @atlaswang.bsky.social :)

1

Reposted by Bartolomeo Stellato

Thiago Serra @thserra.bsky.social · Nov 21

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.

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...

sites.google.com

4 16

Bartolomeo Stellato @stella.to · Nov 18

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

bsky.app/profile/arxi...

9 26

Bartolomeo Stellato @stella.to · Nov 18

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!

1 1

Bartolomeo Stellato @stella.to · Nov 18

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

1