15 citations · 19 across the 9 of their papers we have counts for
9 papers
Anomaly Detection for Sparse and Irregular Multivariate Time Series with Latent SDEs
Martin Uray, Dominik Geng, Florian Graf +2
Multivariate time series anomaly detection (MTSAD) is critical for a wide range of application areas, such as industrial monitoring, cybersecurity, or healthcare. Real-world data i…
Learning Topological Representations of Protein Structure and Dynamics
Dominik Geng, Florian Graf, Martin Uray +1
Modern protein representation models support tasks such as enzyme design and drug discovery, but their reliance on static data such as sequence and native structure limits their ab…
The Flood Complex: Large-Scale Persistent Homology on Millions of Points
Florian Graf, Paolo Pellizzoni, Martin Uray +2
We consider the problem of computing persistent homology (PH) for large-scale Euclidean point cloud data, aimed at downstream machine learning tasks, where the exponential growth o…
Neural Persistence Dynamics
Sebastian Zeng, Florian Graf, Martin Uray +2
We consider the problem of learning the dynamics in the topology of time-evolving point clouds, the prevalent spatiotemporal model for systems exhibiting collective behavior, such…
Latent SDEs on Homogeneous Spaces
Sebastian Zeng, Florian Graf, Roland Kwitt
We consider the problem of variational Bayesian inference in a latent variable model where a (possibly complex) observed stochastic process is governed by the solution of a latent…
On Measuring Excess Capacity in Neural Networks
Florian Graf, Sebastian Zeng, Bastian Rieck +2
We study the excess capacity of deep networks in the context of supervised classification. That is, given a capacity measure of the underlying hypothesis class - in our case, empir…
Topological Attention for Time Series Forecasting
Sebastian Zeng, Florian Graf, Christoph Hofer +1
The problem of (point) forecasting time series is considered. Most approaches, ranging from traditional statistical methods to recent learning-based techniq…
Dissecting Supervised Contrastive Learning
Florian Graf, Christoph D. Hofer, Marc Niethammer +1
Minimizing cross-entropy over the softmax scores of a linear map composed with a high-capacity encoder is arguably the most popular choice for training neural networks on supervise…
Topologically Densified Distributions
Christoph D. Hofer, Florian Graf, Marc Niethammer +1
We study regularization in the context of small sample-size learning with over-parameterized neural networks. Specifically, we shift focus from architectural properties, such as no…