23.06.2024

Teaser image to

MCML Researchers With One Paper at COLT 2024

37th Annual Conference on Learning Theory (COLT 2024). Edmonton, Canada, 30.06.2024–03.07.2024

We are happy to announce that MCML researchers are represented with one paper at COLT 2024. Congrats to our researchers!

Main Track (1 papers)

C. M. Verdun, O. Melnyk, F. Krahmer and P. Jung.
Fast, blind, and accurate: Tuning-free sparse regression with global linear convergence.
COLT 2024 - 37th Annual Conference on Learning Theory. Edmonton, Canada, Jun 30-Jul 03, 2024. URL
Abstract

Many algorithms for high-dimensional regression problems require the calibration of regularization hyperparameters. This, in turn, often requires the knowledge of the unknown noise variance in order to produce meaningful solutions. Recent works show, however, that there exist certain estimators that are pivotal, i.e., the regularization parameter does not depend on the noise level; the most remarkable example being the square-root lasso. Such estimators have also been shown to exhibit strong connections to distributionally robust optimization. Despite the progress in the design of pivotal estimators, the resulting minimization problem is challenging as both the loss function and the regularization term are non-smooth. To date, the design of fast, robust, and scalable algorithms with strong convergence rate guarantees is still an open problem. This work addresses this problem by showing that an iteratively reweighted least squares (IRLS) algorithm exhibits global linear convergence under the weakest assumption available in the literature. We expect our findings will also have implications for multi-task learning and distributionally robust optimization.

MCML Authors
Claudio Mayrink Verdun

Claudio Mayrink Verdun

Dr.

* Former Member

Link to Profile Felix Krahmer

Felix Krahmer

Prof. Dr.

Optimization & Data Analysis


23.06.2024


Subscribe to RSS News feed

Related

Link to Satellite Insights for a Sustainable Future - with researcher Ivica Obadic

25.08.2025

Satellite Insights for a Sustainable Future - With Researcher Ivica Obadic

AI from satellite imagery helps design livable cities, improve well-being & food systems with transparent models by Ivica Obadić.

Link to Mingyang Wang receives Award at ACL 2025

18.08.2025

Mingyang Wang Receives Award at ACL 2025

MCML Junior Member Mingyang Wang wins SAC Highlights Award at ACL 2025 for research on cross-lingual consistency in language models.

Link to Digital Twins for Surgery - with researcher Azade Farshad

18.08.2025

Digital Twins for Surgery - With Researcher Azade Farshad

Azade Farshad develops patient digital twins at TUM & MCML to improve personalized treatment, surgical planning, and training.

Link to From Physics Dreams to Algorithm Discovery - with Niki Kilbertus

13.08.2025

From Physics Dreams to Algorithm Discovery - With Niki Kilbertus

Niki Kilbertus develops AI algorithms to uncover cause and effect, making science smarter and decisions in fields like medicine more reliable.

Link to AI for Dynamic Urban Mapping - with researcher Shanshan Bai

11.08.2025

AI for Dynamic Urban Mapping - With Researcher Shanshan Bai

Shanshan Bai uses geo-tagged social media and AI to map cities in real time. Part of KI Trans, funded by DATIpilot to support AI in education.