no code implementations • 11 Feb 2024 • Steffen Grünewälder, Azadeh Khaleghi
We propose methods to estimate the individual $\beta$-mixing coefficients of a real-valued geometrically ergodic Markov process from a single sample-path $X_0, X_1, \dots, X_n$.
no code implementations • 19 Apr 2022 • Steffen Grünewälder
We study approaches for compressing the empirical measure in the context of finite dimensional reproducing kernel Hilbert spaces (RKHSs). In this context, the empirical measure is contained within a natural convex set and can be approximated using convex optimization methods. Such an approximation gives under certain conditions rise to a coreset of data points.
1 code implementation • 7 Feb 2020 • Steffen Grünewälder, Azadeh Khaleghi
We derive a closed-form solution for this relaxed optimization problem and complement the result with a study of the dependencies between the newly generated features and the sensitive ones.
1 code implementation • NeurIPS 2019 • Ciara Pike-Burke, Steffen Grünewälder
We study the recovering bandits problem, a variant of the stochastic multi-armed bandit problem where the expected reward of each arm varies according to some unknown function of the time since the arm was last played.
no code implementations • 2 Nov 2018 • Stephen Page, Steffen Grünewälder
In the RKHS regression context, we choose our non-adaptive estimators to be clipped least-squares estimators constrained to lie in a ball in an RKHS.
Statistics Theory Statistics Theory
no code implementations • NeurIPS 2009 • Arno Onken, Steffen Grünewälder, Klaus Obermayer
The linear correlation coefficient is typically used to characterize and analyze dependencies of neural spike counts.
no code implementations • NeurIPS 2008 • Arno Onken, Steffen Grünewälder, Matthias Munk, Klaus Obermayer
Furthermore, copulas place a wide range of dependence structures at the disposal and can be used to analyze higher order interactions.