Lower Bounds for Linear Minimization Oracle Methods Optimizing... We consider the oracle complexity of constrained convex optimization given access to a Linear Minimization Oracle (LMO) for the constraint set and a gradient oracle for the $L$-smooth, strongly...

Also do not forget to check out the nice work by Grimmer and Liu (arxiv.org/abs/2602.22608) that shortly appeared after ours; it nicely complements our story.

The construction is unusual: instead of searching for bad initializations, we build them backward from the optimum.

With J. Halbey, D. Deza, M. Zimmer, C. Roux, B. Stellato.

📄 arxiv.org/abs/2602.04378
📝 Blog with interactive widgets: www.pokutta.com/blog/fw-low...

For a decade it was open whether Frank-Wolfe's O(1/√ε) rate on strongly convex sets is tight. We show it is: Ω(1/√ε), even for a simple quadratic on a unit ball.

SCIP Optimization Suite 10.0 is out 🎉

→ Numerically exact solving mode for rational MILPs
→ 9-20% faster on hard MINLPs
→ IIS detection for debugging infeasible models
→ Better symmetry handling
... and many more

For full details see:
www.pokutta.com/blog/resear...

#optimization

Our book on conditional gradients and Frank-Wolfe methods with Gábor Braun, @ACarderera, @CyrilleCmbt, Hamed Hassani, @aminkarbasi and Aryan Mokhtari just appeared in the MOS-SIAM Series on Optimization #ml #optimization #ai

epubs.siam.org/doi/book/10...

New blog post: committing to secrets via hashing - a short, first-principles introduction #crypto #hashing

=> www.pokutta.com/blog/hashed...