default search action
Thomas Möllenhoff
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
- [c20]Nico Daheim, Thomas Möllenhoff, Edoardo M. Ponti, Iryna Gurevych, Mohammad Emtiyaz Khan:
Model Merging by Uncertainty-Based Gradient Matching. ICLR 2024 - [c19]Etash Kumar Guha, Shlok Natarajan, Thomas Möllenhoff, Mohammad Emtiyaz Khan, Eugène Ndiaye:
Conformal Prediction via Regression-as-Classification. ICLR 2024 - [c18]Yuesong Shen, Nico Daheim, Bai Cong, Peter Nickl, Gian Maria Marconi, Clement Bazan, Rio Yokota, Iryna Gurevych, Daniel Cremers, Mohammad Emtiyaz Khan, Thomas Möllenhoff:
Variational Learning is Effective for Large Deep Networks. ICML 2024 - [i18]Yuesong Shen, Nico Daheim, Bai Cong, Peter Nickl, Gian Maria Marconi, Clement Bazan, Rio Yokota, Iryna Gurevych, Daniel Cremers, Mohammad Emtiyaz Khan, Thomas Möllenhoff:
Variational Learning is Effective for Large Deep Networks. CoRR abs/2402.17641 (2024) - [i17]Etash Kumar Guha, Shlok Natarajan, Thomas Möllenhoff, Mohammad Emtiyaz Khan, Eugène Ndiaye:
Conformal Prediction via Regression-as-Classification. CoRR abs/2404.08168 (2024) - 2023
- [j3]Zhenzhang Ye, Bjoern Haefner, Yvain Quéau, Thomas Möllenhoff, Daniel Cremers:
A Cutting-Plane Method for Sublabel-Accurate Relaxation of Problems with Product Label Spaces. Int. J. Comput. Vis. 131(1): 346-362 (2023) - [c17]Eren Mehmet Kiral, Thomas Möllenhoff, Mohammad Emtiyaz Khan:
The Lie-Group Bayesian Learning Rule. AISTATS 2023: 3331-3352 - [c16]Thomas Möllenhoff, Mohammad Emtiyaz Khan:
SAM as an Optimal Relaxation of Bayes. ICLR 2023 - [c15]Peter Nickl, Lu Xu, Dharmesh Tailor, Thomas Möllenhoff, Mohammad Emtiyaz Khan:
The Memory-Perturbation Equation: Understanding Model's Sensitivity to Data. NeurIPS 2023 - [i16]Eren Mehmet Kiral, Thomas Möllenhoff, Mohammad Emtiyaz Khan:
The Lie-Group Bayesian Learning Rule. CoRR abs/2303.04397 (2023) - [i15]Nico Daheim, Thomas Möllenhoff, Edoardo Maria Ponti, Iryna Gurevych, Mohammad Emtiyaz Khan:
Model Merging by Uncertainty-Based Gradient Matching. CoRR abs/2310.12808 (2023) - [i14]Peter Nickl, Lu Xu, Dharmesh Tailor, Thomas Möllenhoff, Mohammad Emtiyaz Khan:
The Memory Perturbation Equation: Understanding Model's Sensitivity to Data. CoRR abs/2310.19273 (2023) - 2022
- [j2]Hartmut Bauermeister, Emanuel Laude, Thomas Möllenhoff, Michael Möller, Daniel Cremers:
Lifting the Convex Conjugate in Lagrangian Relaxations: A Tractable Approach for Continuous Markov Random Fields. SIAM J. Imaging Sci. 15(3): 1253-1281 (2022) - [c14]Hannah Dröge, Thomas Möllenhoff, Michael Möller:
Non-Smooth Energy Dissipating Networks. ICIP 2022: 3281-3285 - [i13]Thomas Möllenhoff, Mohammad Emtiyaz Khan:
SAM as an Optimal Relaxation of Bayes. CoRR abs/2210.01620 (2022) - 2021
- [c13]Zhenzhang Ye, Bjoern Haefner, Yvain Quéau, Thomas Möllenhoff, Daniel Cremers:
Sublabel-Accurate Multilabeling Meets Product Label Spaces. GCPR 2021: 3-17 - [i12]Hartmut Bauermeister, Emanuel Laude, Thomas Möllenhoff, Michael Möller, Daniel Cremers:
Lifting the Convex Conjugate in Lagrangian Relaxations: A Tractable Approach for Continuous Markov Random Fields. CoRR abs/2107.06028 (2021) - 2020
- [b1]Thomas Möllenhoff:
Efficient Lifting Methods for Variational Problems. Technical University of Munich, Germany, 2020 - [c12]Zhenzhang Ye, Thomas Möllenhoff, Tao Wu, Daniel Cremers:
Optimization of Graph Total Variation via Active-Set-based Combinatorial Reconditioning. AISTATS 2020: 657-668 - [i11]Zhenzhang Ye, Thomas Möllenhoff, Tao Wu, Daniel Cremers:
Optimization of Graph Total Variation via Active-Set-based Combinatorial Reconditioning. CoRR abs/2002.12236 (2020)
2010 – 2019
- 2019
- [c11]Thomas Möllenhoff, Daniel Cremers:
Lifting Vectorial Variational Problems: A Natural Formulation Based on Geometric Measure Theory and Discrete Exterior Calculus. CVPR 2019: 11117-11126 - [c10]Michael Möller, Thomas Möllenhoff, Daniel Cremers:
Controlling Neural Networks via Energy Dissipation. ICCV 2019: 3255-3264 - [c9]Thomas Möllenhoff, Daniel Cremers:
Flat Metric Minimization with Applications in Generative Modeling. ICML 2019: 4626-4635 - [i10]Michael Möller, Thomas Möllenhoff, Daniel Cremers:
Controlling Neural Networks via Energy Dissipation. CoRR abs/1904.03081 (2019) - [i9]Thomas Möllenhoff, Daniel Cremers:
Lifting Vectorial Variational Problems: A Natural Formulation based on Geometric Measure Theory and Discrete Exterior Calculus. CoRR abs/1905.00851 (2019) - [i8]Thomas Möllenhoff, Daniel Cremers:
Flat Metric Minimization with Applications in Generative Modeling. CoRR abs/1905.04730 (2019) - [i7]Pierre Bréchet, Tao Wu, Thomas Möllenhoff, Daniel Cremers:
Informative GANs via Structured Regularization of Optimal Transport. CoRR abs/1912.02160 (2019) - 2018
- [c8]Thomas Möllenhoff, Zhenzhang Ye, Tao Wu, Daniel Cremers:
Combinatorial Preconditioners for Proximal Algorithms on Graphs. AISTATS 2018: 38-47 - [c7]Bjoern Haefner, Yvain Quéau, Thomas Möllenhoff, Daniel Cremers:
Fight Ill-Posedness With Ill-Posedness: Single-Shot Variational Depth Super-Resolution From Shading. CVPR 2018: 164-174 - [c6]Thomas Frerix, Thomas Möllenhoff, Michael Möller, Daniel Cremers:
Proximal Backpropagation. ICLR (Poster) 2018 - [i6]Thomas Möllenhoff, Zhenzhang Ye, Tao Wu, Daniel Cremers:
Combinatorial Preconditioners for Proximal Algorithms on Graphs. CoRR abs/1801.05413 (2018) - 2017
- [c5]Thomas Möllenhoff, Daniel Cremers:
Sublabel-Accurate Discretization of Nonconvex Free-Discontinuity Problems. ICCV 2017: 1192-1200 - [i5]Thomas Frerix, Thomas Möllenhoff, Michael Möller, Daniel Cremers:
Proximal Backpropagation. CoRR abs/1706.04638 (2017) - 2016
- [c4]Thomas Möllenhoff, Emanuel Laude, Michael Möller, Jan Lellmann, Daniel Cremers:
Sublabel-Accurate Relaxation of Nonconvex Energies. CVPR 2016: 3948-3956 - [c3]Emanuel Laude, Thomas Möllenhoff, Michael Möller, Jan Lellmann, Daniel Cremers:
Sublabel-Accurate Convex Relaxation of Vectorial Multilabel Energies. ECCV (1) 2016: 614-627 - [i4]Emanuel Laude, Thomas Möllenhoff, Michael Möller, Jan Lellmann, Daniel Cremers:
Sublabel-Accurate Convex Relaxation of Vectorial Multilabel Energies. CoRR abs/1604.01980 (2016) - [i3]Thomas Möllenhoff, Daniel Cremers:
Precise Relaxation of the Mumford-Shah Functional. CoRR abs/1611.06987 (2016) - 2015
- [j1]Thomas Möllenhoff, Evgeny Strekalovskiy, Michael Möller, Daniel Cremers:
The Primal-Dual Hybrid Gradient Method for Semiconvex Splittings. SIAM J. Imaging Sci. 8(2): 827-857 (2015) - [i2]Thomas Möllenhoff, Emanuel Laude, Michael Möller, Jan Lellmann, Daniel Cremers:
Sublabel-Accurate Relaxation of Nonconvex Energies. CoRR abs/1512.01383 (2015) - 2014
- [c2]Thomas Möllenhoff, Evgeny Strekalovskiy, Michael Möller, Daniel Cremers:
Low Rank Priors for Color Image Regularization. EMMCVPR 2014: 126-140 - [i1]Thomas Möllenhoff, Evgeny Strekalovskiy, Michael Möller, Daniel Cremers:
The Primal-Dual Hybrid Gradient Method for Semiconvex Splittings. CoRR abs/1407.1723 (2014) - 2013
- [c1]Thomas Möllenhoff, Claudia Nieuwenhuis, Eno Töppe, Daniel Cremers:
Efficient Convex Optimization for Minimal Partition Problems with Volume Constraints. EMMCVPR 2013: 94-107
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from , , and to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-09-05 02:08 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint