15 citations · 24 across the 8 of their papers we have counts for
8 papers
Finite-Budget Convergence and Chaos-Aware Stopping Criteria for Time-Parallel Methods
Giancarlo Antonino Antonucci, Raphael Andreas Hauser, Debasmita Samaddar +1
Time-parallel algorithms, such as Parareal, are well understood for linear problems, but their convergence analysis for nonlinear, chaotic systems remains limited. This paper intro…
Local Convergence of Adaptively Regularized Tensor Methods
Karl Welzel, Yang Liu, Raphael A. Hauser +1
Optimization methods that make use of derivatives of the objective function up to order are called tensor methods. Among them, ones that minimize a regularized th-order…
Approximating Higher-Order Derivative Tensors Using Secant Updates
Karl Welzel, Raphael A. Hauser
Quasi-Newton methods employ an update rule that gradually improves the Hessian approximation using the already available gradient evaluations. We propose higher-order secant update…
Principled Data Completion of Network Constraints for Day Ahead Auctions in Power Markets
Ioan Alexandru Puiu, Raphael Andreas Hauser
Network constraints play a key role in the price finding mechanism for European Power Markets, but historical data is very sparse and usually insufficient for many quantitative app…
Binary Matrix Factorisation and Completion via Integer Programming
Reka A. Kovacs, Oktay Gunluk, Raphael A. Hauser
Binary matrix factorisation is an essential tool for identifying discrete patterns in binary data. In this paper we consider the rank-k binary matrix factorisation problem (k-BMF)…
Binary Matrix Factorisation via Column Generation
Reka A. Kovacs, Oktay Gunluk, Raphael A. Hauser
Identifying discrete patterns in binary data is an important dimensionality reduction tool in machine learning and data mining. In this paper, we consider the problem of low-rank b…
MOSES: A Streaming Algorithm for Linear Dimensionality Reduction
Armin Eftekhari, Raphael A. Hauser, Andreas Grammenos
This paper introduces Memory-limited Online Subspace Estimation Scheme (MOSES) for both estimating the principal components of streaming data and reducing its dimension. More speci…
PCA by Optimisation of Symmetric Functions has no Spurious Local Optima
Raphael A. Hauser, Armin Eftekhari
Principal Component Analysis (PCA) finds the best linear representation of data, and is an indispensable tool in many learning and inference tasks. Classically, principal component…