1 code implementation • 18 Apr 2024 • Masaki Adachi, Satoshi Hayakawa, Martin Jørgensen, Saad Hamid, Harald Oberhauser, Michael A. Osborne
Parallelisation in Bayesian optimisation is a common strategy but faces several challenges: the need for flexibility in acquisition functions and kernel choices, flexibility dealing with discrete and continuous variables simultaneously, model misspecification, and lastly fast massive parallelisation.
1 code implementation • 20 Nov 2023 • Csaba Toth, Harald Oberhauser, Zoltan Szabo
Tensor algebras give rise to one of the most powerful measures of similarity for sequences of arbitrary length called the signature kernel accompanied with attractive theoretical guarantees from stochastic analysis.
no code implementations • 7 Nov 2023 • Uzu Lim, Harald Oberhauser, Vidit Nanda
We introduce Hades, an unsupervised algorithm to detect singularities in data.
1 code implementation • 9 Jun 2023 • Masaki Adachi, Satoshi Hayakawa, Martin Jørgensen, Xingchen Wan, Vu Nguyen, Harald Oberhauser, Michael A. Osborne
Active learning parallelization is widely used, but typically relies on fixing the batch size throughout experimentation.
2 code implementations • 8 May 2023 • Darrick Lee, Harald Oberhauser
The signature kernel is a positive definite kernel for sequential data.
1 code implementation • 27 Jan 2023 • Masaki Adachi, Satoshi Hayakawa, Saad Hamid, Martin Jørgensen, Harald Oberhauser, Micheal A. Osborne
Batch Bayesian optimisation and Bayesian quadrature have been shown to be sample-efficient methods of performing optimisation and quadrature where expensive-to-evaluate objective functions can be queried in parallel.
1 code implementation • 23 Jan 2023 • Satoshi Hayakawa, Harald Oberhauser, Terry Lyons
We analyze the Nystr\"om approximation of a positive definite kernel associated with a probability measure.
2 code implementations • 9 Jun 2022 • Masaki Adachi, Satoshi Hayakawa, Martin Jørgensen, Harald Oberhauser, Michael A. Osborne
Empirically, we find that our approach significantly outperforms the sampling efficiency of both state-of-the-art BQ techniques and Nested Sampling in various real-world datasets, including lithium-ion battery analytics.
1 code implementation • 27 May 2022 • Csaba Toth, Darrick Lee, Celia Hacker, Harald Oberhauser
This results in a novel tensor-valued graph operator, which we call the hypo-elliptic graph Laplacian.
no code implementations • 12 Oct 2021 • Uzu Lim, Harald Oberhauser, Vidit Nanda
Consider a set of points sampled independently near a smooth compact submanifold of Euclidean space.
1 code implementation • 20 Jul 2021 • Satoshi Hayakawa, Harald Oberhauser, Terry Lyons
We study kernel quadrature rules with convex weights.
1 code implementation • 6 Feb 2021 • Patrick Kidger, James Foster, Xuechen Li, Harald Oberhauser, Terry Lyons
Stochastic differential equations (SDEs) are a staple of mathematical modelling of temporal dynamics.
1 code implementation • 4 Feb 2021 • Alexander Schell, Harald Oberhauser
We study the classical problem of recovering a multidimensional source signal from observations of nonlinear mixtures of this signal.
no code implementations • 1 Jan 2021 • Patrick Kidger, James Foster, Xuechen Li, Harald Oberhauser, Terry Lyons
Several authors have introduced \emph{Neural Stochastic Differential Equations} (Neural SDEs), often involving complex theory with various limitations.
1 code implementation • ICLR 2021 • Csaba Toth, Patric Bonnier, Harald Oberhauser
Sequential data such as time series, video, or text can be challenging to analyse as the ordered structure gives rise to complex dependencies.
Ranked #1 on Time Series Classification on KickvsPunch
1 code implementation • 2 Jun 2020 • Francesco Cosentino, Harald Oberhauser, Alessandro Abate
Various flavours of Stochastic Gradient Descent (SGD) replace the expensive summation that computes the full gradient by approximating it with a small sum over a randomly selected subsample of the data set that in turn suffers from a high variance.
1 code implementation • NeurIPS 2020 • Francesco Cosentino, Harald Oberhauser, Alessandro Abate
Given a discrete probability measure supported on $N$ atoms and a set of $n$ real-valued functions, there exists a probability measure that is supported on a subset of $n+1$ of the original $N$ atoms and has the same mean when integrated against each of the $n$ functions.
1 code implementation • ICML 2020 • Csaba Toth, Harald Oberhauser
We develop a Bayesian approach to learning from sequential data by using Gaussian processes (GPs) with so-called signature kernels as covariance functions.
Ranked #1 on Time Series Classification on DigitShapes
1 code implementation • 25 Oct 2018 • Ilya Chevyrev, Harald Oberhauser
This allows us to derive a metric of maximum mean discrepancy type for laws of stochastic processes and study the topology it induces on the space of laws of stochastic processes.
no code implementations • 1 Jun 2018 • Ilya Chevyrev, Vidit Nanda, Harald Oberhauser
We introduce a new feature map for barcodes that arise in persistent homology computation.
no code implementations • 2 Jan 2018 • Frithjof Gressmann, Franz J. Király, Bilal Mateen, Harald Oberhauser
Predictive modelling and supervised learning are central to modern data science.
no code implementations • 31 Aug 2017 • Terry Lyons, Harald Oberhauser
We introduce features for massive data streams.
no code implementations • 29 Jan 2016 • Franz J. Király, Harald Oberhauser
We present a novel framework for kernel learning with sequential data of any kind, such as time series, sequences of graphs, or strings.