iiinova — where your digital self keeps evolving

Rajiv Sambharya

@rajivsambharya.bsky.social

Postdoc at Penn Engineering | researching optimization, control, and machine learning | Princeton and Berkeley alumnus

Rajiv Sambharya @rajivsambharya.bsky.social · 27/10/2025

I will be presenting on this work at @informs.bsky.social in Atlanta on Tuesday, October 28, 4:15-5:30 pm, in the Machine Learning and Optimization session (Building B, Level 2, Room B208)!

030

Rajiv Sambharya @rajivsambharya.bsky.social · 27/10/2025

We learned acceleration algorithms for fast parametric convex optimization. Only 10 training instances used for each example and robustness is guaranteed with PEP! Joint work w/ Jinho Bok, Nik Matni, and George Pappas!

010

Reposted by Rajiv Sambharya

Bartolomeo Stellato @stella.to · 08/09/2025

📢 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/...

073

Rajiv Sambharya @rajivsambharya.bsky.social · 02/12/2024

We learned the hyperparameters to accelerate algorithms over a family of problems. Turns out that we only need 10 training instances in each example and learn long steps for (prox) gd! Check out this work with @stellato.io paper: arxiv.org/pdf/2411.15717 code: github.com/stellatogrp/...

050