Revisiting Frank-Wolfe: Projection-free sparse convex optimization
M Jaggi - International conference on machine learning, 2013 - proceedings.mlr.press
We provide stronger and more general primal-dual convergence results for Frank-Wolfe-
type algorithms (aka conditional gradient) for constrained convex optimization, enabled by a …
type algorithms (aka conditional gradient) for constrained convex optimization, enabled by a …
[PDF][PDF] Sparse convex optimization methods for machine learning
M Jaggi - 2011 - infoscience.epfl.ch
Convex optimization is at the core of many of today's analysis tools for large datasets, and in
particular machine learning methods. In this thesis we will study the general setting of …
particular machine learning methods. In this thesis we will study the general setting of …
Network design for controllability metrics
In this article, we consider the problem of tuning the edge weights of a networked system
described by linear time-invariant dynamics. We assume that the topology of the underlying …
described by linear time-invariant dynamics. We assume that the topology of the underlying …
Convex optimization without projection steps
M Jaggi - arXiv preprint arXiv:1108.1170, 2011 - arxiv.org
For the general problem of minimizing a convex function over a compact convex domain, we
will investigate a simple iterative approximation algorithm based on the method by Frank & …
will investigate a simple iterative approximation algorithm based on the method by Frank & …
Atomic norm denoising-based joint channel estimation and faulty antenna detection for massive MIMO
We consider joint channel estimation and faulty antenna detection for massive multiple-input
multiple-output systems operating in time-division duplexing mode. For systems with faulty …
multiple-output systems operating in time-division duplexing mode. For systems with faulty …
Approximating concavely parameterized optimization problems
J Giesen, J Müller, S Laue… - Advances in neural …, 2012 - proceedings.neurips.cc
We consider an abstract class of optimization problems that are parameterized concavely in
a single parameter, and show that the solution path along the parameter can always be …
a single parameter, and show that the solution path along the parameter can always be …
Using Benson's algorithm for regularization parameter tracking
J Giesen, S Laue, A Lӧhne, C Schneider - Proceedings of the AAAI …, 2019 - aaai.org
Regularized loss minimization, where a statistical model is obtained from minimizing the
sum of a loss function and weighted regularization terms, is still in widespread use in …
sum of a loss function and weighted regularization terms, is still in widespread use in …
Robust and efficient kernel hyperparameter paths with guarantees
J Giesen, S Laue… - … Conference on Machine …, 2014 - proceedings.mlr.press
Algorithmically, many machine learning tasks boil down to solving parameterized
optimization problems. Finding good values for the parameters has significant influence on …
optimization problems. Finding good values for the parameters has significant influence on …
Optimizing over the growing spectrahedron
We devise a framework for computing an approximate solution path for an important class of
parameterized semidefinite problems that is guaranteed to be ε-close to the exact solution …
parameterized semidefinite problems that is guaranteed to be ε-close to the exact solution …
Efficient Line Search Method Based on Regression and Uncertainty Quantification
Unconstrained optimization problems are typically solved using iterative methods, which
often depend on line search techniques to determine optimal step lengths in each iteration …
often depend on line search techniques to determine optimal step lengths in each iteration …