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!

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

27.02.2025

MCML Researchers With Six Papers at WACV 2025

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025). Tucson, AZ, USA, 28.02.2025 - 04.03.2024

Link to

24.02.2025

MCML Researchers With Seven Papers at AAAI 2025

39th Conference on Artificial Intelligence (AAAI 2025). Philadelphia, PA, USA, 25.02.2025 - 04.03.2024

Link to

01.01.2025

MCML Researchers With 39 Papers in Highly-Ranked Journals

Link to

05.12.2024

MCML Researchers With 28 Papers at NeurIPS 2024

38th Conference on Neural Information Processing Systems (NeurIPS 2024). Vancouver, Canada, 10.12.2024 - 15.12.2024

Link to

06.11.2024

MCML Researchers With 22 Papers at EMNLP 2024

Conference on Empirical Methods in Natural Language Processing (EMNLP 2024). Miami, FL, USA, 12.11.2024 - 16.11.2024