704 citations · 4.8k across the 117 of their papers we have counts for
6 papers · 2 filters
Safe Adaptive Importance Sampling
Sebastian U. Stich, Anant Raj, Martin Jaggi
Importance sampling has become an indispensable strategy to speed up optimization algorithms for large-scale applications. Improved adaptive variants - using importance values defi…
Efficient Use of Limited-Memory Accelerators for Linear Learning on Heterogeneous Systems
Celestine Dünner, Thomas Parnell, Martin Jaggi
We propose a generic algorithmic building block to accelerate training of machine learning models on heterogeneous compute systems. Our scheme allows to efficiently employ compute…
Approximate Steepest Coordinate Descent
Sebastian U. Stich, Anant Raj, Martin Jaggi
We propose a new selection rule for the coordinate selection in coordinate descent methods for huge-scale optimization. The efficiency of this novel scheme is provably better than…
Greedy Algorithms for Cone Constrained Optimization with Convergence Guarantees
Francesco Locatello, Michael Tschannen, Gunnar Rätsch +1
Greedy optimization methods such as Matching Pursuit (MP) and Frank-Wolfe (FW) algorithms regained popularity in recent years due to their simplicity, effectiveness and theoretical…
Faster Coordinate Descent via Adaptive Importance Sampling
Dmytro Perekrestenko, Volkan Cevher, Martin Jaggi
Coordinate descent methods employ random partial updates of decision variables in order to solve huge-scale convex optimization problems. In this work, we introduce new adaptive ru…
A Unified Optimization View on Generalized Matching Pursuit and Frank-Wolfe
Francesco Locatello, Rajiv Khanna, Michael Tschannen +1
Two of the most fundamental prototypes of greedy optimization are the matching pursuit and Frank-Wolfe algorithms. In this paper, we take a unified view on both classes of methods,…