Publications in Machine Learning Venues

Last updated on Jul 6, 2020

ICML

Connectivity-Optimized Representation Learning via Persistent Homology

Connectivity-Optimized Representation Learning via Persistent Homology

We study the problem of learning representations with controllable connectivity properties. This is beneficial in situations when the …
Christoph D. Hofer, Roland Kwitt, Marc Niethammer, Mandar Dixit
PDF
Dissecting Supervised Constrastive Learning

Dissecting Supervised Constrastive Learning

Minimizing cross-entropy over the softmax scores of a linear map composed with a high-capacity encoder is arguably the most popular …
Florian Graf, Christoph D. Hofer, Marc Niethammer, Roland Kwitt
PDF
Graph Filtration Learning

Graph Filtration Learning

We propose an approach to learning with graph-structured data in the problem domain of graph classification. In particular, we present …
Christoph D. Hofer, Florian Graf, Bastian Rieck, Marc Niethammer, Roland Kwitt
PDF
Topologically Densified Distributions

Topologically Densified Distributions

We study regularization in the context of small sample-size learning with over-parameterized neural networks. Specifically, we shift …
Christoph D. Hofer, Florian Graf, Marc Niethammer, Roland Kwitt
PDF

NeurIPS

A shooting formulation of deep learning

A shooting formulation of deep learning

Continuous-depth neural networks can be viewed as deep limits of discrete neural networks whose dynamics resemble a discretization of …
François-Xavier Vialard, Roland Kwitt, Susan Wei, Marc Niethammer
PDF
Deep Learning with Topological Signatures

Deep Learning with Topological Signatures

Inferring topological and geometrical information from data can offer an alternative perspective in machine learning problems. Methods …
Christoph D. Hofer, Roland Kwitt, Marc Niethammer, Andreas Uhl
PDF
Region-specific Diffeomorphic Metric Mapping

Region-specific Diffeomorphic Metric Mapping

We introduce a region-specific diffeomorphic metric mapping (RDMM) registration approach. RDMM is non-parametric, estimating …
Zhengyang Shen, François-Xavier Vialard, Marc Niethammer
PDF
Statistical Topological Data Analysis - A Kernel Perspective

Statistical Topological Data Analysis - A Kernel Perspective

We consider the problem of statistical computations with persistence diagrams, a summary representation of topological features in …
Roland Kwitt, Stefan Huber, Marc Niethammer, Weili Lin, Ulrich Bauer
PDF

AAAI

Deep Message Passing on Sets

Deep Message Passing on Sets

Modern methods for learning over graph input data have shown the fruitfulness of accounting for relationships among elements in a …
Yifeng Shi, Junier Oliva, Marc Niethammer
PDF

AISTATS

Regression Uncertainty on the Grassmannian

Regression Uncertainty on the Grassmannian

Trends in longitudinal or cross-sectional studies over time are often captured through regression models. In their simplest …
Yi Hong, Xiao Yang, Roland Kwitt, Martin Styner, Marc Niethammer
PDF

JMLR

Learning Representations of Persistence Barcodes

Learning Representations of Persistence Barcodes

We consider the problem of supervised learning with summary representations of topological features in data. In particular, we focus on …
Christoph D. Hofer, Roland Kwitt, Marc Niethammer
PDF
Admin
Admin
UNC Biomedical Image Analysis Group (UNC-biag)

UNC Biomedical Image Analysis Group (unc-biag)