Thomas Möllenhoff

56 papers A* 12A 3B 1Journal 34Unranked 5

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	A Stein Identity for q-Gaussians with Bounded Support. CoRR Sophia Sklaviadis, Thomas Möllenhoff, André F. T. Martins, Mário A. T. Figueiredo, Mohammad Emtiyaz Khan
2025	J	`jnl`	Compact Memory for Continual Logistic Regression. CoRR Yohan Jung, Hyungi Lee, Wenlong Chen, Thomas Möllenhoff, Yingzhen Li, Juho Lee, Mohammad Emtiyaz Khan
2025	J	`jnl`	Federated ADMM from Bayesian Duality. CoRR Thomas Möllenhoff, Siddharth Swaroop, Finale Doshi-Velez, Mohammad Emtiyaz Khan
2025	J	`jnl`	Improving LoRA with Variational Learning. CoRR Bai Cong, Nico Daheim, Yuesong Shen, Rio Yokota, Mohammad Emtiyaz Khan, Thomas Möllenhoff
2025	J	`jnl`	Log-Normal Multiplicative Dynamics for Stable Low-Precision Training of Large Networks. CoRR Keigo Nishida, Eren Mehmet Kiral, Kenichi Bannai, Mohammad Emtiyaz Khan, Thomas Möllenhoff
2025	J	`jnl`	Natural Variational Annealing for Multimodal Optimization. CoRR Tâm Le Minh, Julyan Arbel, Thomas Möllenhoff, Mohammad Emtiyaz Khan, Florence Forbes
2025	J	`jnl`	Optimization Guarantees for Square-Root Natural-Gradient Variational Inference. CoRR Navish Kumar, Thomas Möllenhoff, Mohammad Emtiyaz Khan, Aurélien Lucchi
2025	J	`jnl`	Optimization Guarantees for Square-Root Natural-Gradient Variational Inference. Trans. Mach. Learn. Res. Navish Kumar, Thomas Möllenhoff, Mohammad Emtiyaz Khan, Aurélien Lucchi
2025	J	`jnl`	SVRG and Beyond via Posterior Correction. CoRR Nico Daheim, Thomas Möllenhoff, Ming Liang Ang, Mohammad Emtiyaz Khan
2025	A*	`conf`	Uncertainty-Aware Decoding with Minimum Bayes Risk. ICLR Nico Daheim, Clara Meister, Thomas Möllenhoff, Iryna Gurevych
2025	J	`jnl`	Uncertainty-Aware Decoding with Minimum Bayes Risk. CoRR Nico Daheim, Clara Meister, Thomas Möllenhoff, Iryna Gurevych
2025	J	`jnl`	Variational Learning Finds Flatter Solutions at the Edge of Stability. CoRR Avrajit Ghosh, Bai Cong, Rio Yokota, Saiprasad Ravishankar, Rongrong Wang, Molei Tao, Mohammad Emtiyaz Khan, Thomas Möllenhoff
2024	A*	`conf`	Conformal Prediction via Regression-as-Classification. ICLR Etash Kumar Guha, Shlok Natarajan, Thomas Möllenhoff, Mohammad Emtiyaz Khan, Eugène Ndiaye
2024	J	`jnl`	Conformal Prediction via Regression-as-Classification. CoRR Etash Kumar Guha, Shlok Natarajan, Thomas Möllenhoff, Mohammad Emtiyaz Khan, Eugène Ndiaye
2024	J	`jnl`	How to Weight Multitask Finetuning? Fast Previews via Bayesian Model-Merging. CoRR Hugo Monzón Maldonado, Thomas Möllenhoff, Nico Daheim, Iryna Gurevych, Mohammad Emtiyaz Khan
2024	A*	`conf`	Model Merging by Uncertainty-Based Gradient Matching. ICLR Nico Daheim, Thomas Möllenhoff, Edoardo M. Ponti, Iryna Gurevych, Mohammad Emtiyaz Khan
2024	A*	`conf`	Variational Learning is Effective for Large Deep Networks. ICML Yuesong Shen, Nico Daheim, Bai Cong, Peter Nickl, Gian Maria Marconi, Clement Bazan, Rio Yokota, Iryna Gurevych, Daniel Cremers, Mohammad Emtiyaz Khan, Thomas Möllenhoff
2024	J	`jnl`	Variational Learning is Effective for Large Deep Networks. CoRR Yuesong Shen, Nico Daheim, Bai Cong, Peter Nickl, Gian Maria Marconi, Clement Bazan, Rio Yokota, Iryna Gurevych, Daniel Cremers, Mohammad Emtiyaz Khan, Thomas Möllenhoff
2024	J	`jnl`	Variational Low-Rank Adaptation Using IVON. CoRR Bai Cong, Nico Daheim, Yuesong Shen, Daniel Cremers, Rio Yokota, Mohammad Emtiyaz Khan, Thomas Möllenhoff
2023	J	`jnl`	A Cutting-Plane Method for Sublabel-Accurate Relaxation of Problems with Product Label Spaces. Int. J. Comput. Vis. Zhenzhang Ye, Bjoern Haefner, Yvain Quéau, Thomas Möllenhoff, Daniel Cremers
2023	J	`jnl`	Model Merging by Uncertainty-Based Gradient Matching. CoRR Nico Daheim, Thomas Möllenhoff, Edoardo Maria Ponti, Iryna Gurevych, Mohammad Emtiyaz Khan
2023	A*	`conf`	SAM as an Optimal Relaxation of Bayes. ICLR Thomas Möllenhoff, Mohammad Emtiyaz Khan
2023	A	`conf`	The Lie-Group Bayesian Learning Rule. AISTATS Eren Mehmet Kiral, Thomas Möllenhoff, Mohammad Emtiyaz Khan
2023	J	`jnl`	The Lie-Group Bayesian Learning Rule. CoRR Eren Mehmet Kiral, Thomas Möllenhoff, Mohammad Emtiyaz Khan
2023	J	`jnl`	The Memory Perturbation Equation: Understanding Model's Sensitivity to Data. CoRR Peter Nickl, Lu Xu, Dharmesh Tailor, Thomas Möllenhoff, Mohammad Emtiyaz Khan
2023	A*	`conf`	The Memory-Perturbation Equation: Understanding Model's Sensitivity to Data. NeurIPS Peter Nickl, Lu Xu, Dharmesh Tailor, Thomas Möllenhoff, Mohammad Emtiyaz Khan
2022	J	`jnl`	Lifting the Convex Conjugate in Lagrangian Relaxations: A Tractable Approach for Continuous Markov Random Fields. SIAM J. Imaging Sci. Hartmut Bauermeister, Emanuel Laude, Thomas Möllenhoff, Michael Möller, Daniel Cremers
2022	B	`conf`	Non-Smooth Energy Dissipating Networks. ICIP Hannah Dröge, Thomas Möllenhoff, Michael Möller
2022	J	`jnl`	SAM as an Optimal Relaxation of Bayes. CoRR Thomas Möllenhoff, Mohammad Emtiyaz Khan
2021	J	`jnl`	Lifting the Convex Conjugate in Lagrangian Relaxations: A Tractable Approach for Continuous Markov Random Fields. CoRR Hartmut Bauermeister, Emanuel Laude, Thomas Möllenhoff, Michael Möller, Daniel Cremers
2021	—	`conf`	Sublabel-Accurate Multilabeling Meets Product Label Spaces. GCPR Zhenzhang Ye, Bjoern Haefner, Yvain Quéau, Thomas Möllenhoff, Daniel Cremers
2020	—	`—`	Efficient Lifting Methods for Variational Problems. Thomas Möllenhoff
2020	A	`conf`	Optimization of Graph Total Variation via Active-Set-based Combinatorial Reconditioning. AISTATS Zhenzhang Ye, Thomas Möllenhoff, Tao Wu, Daniel Cremers
2020	J	`jnl`	Optimization of Graph Total Variation via Active-Set-based Combinatorial Reconditioning. CoRR Zhenzhang Ye, Thomas Möllenhoff, Tao Wu, Daniel Cremers
2019	A*	`conf`	Controlling Neural Networks via Energy Dissipation. ICCV Michael Möller, Thomas Möllenhoff, Daniel Cremers
2019	J	`jnl`	Controlling Neural Networks via Energy Dissipation. CoRR Michael Möller, Thomas Möllenhoff, Daniel Cremers
2019	A*	`conf`	Flat Metric Minimization with Applications in Generative Modeling. ICML Thomas Möllenhoff, Daniel Cremers
2019	J	`jnl`	Flat Metric Minimization with Applications in Generative Modeling. CoRR Thomas Möllenhoff, Daniel Cremers
2019	J	`jnl`	Informative GANs via Structured Regularization of Optimal Transport. CoRR Pierre Bréchet, Tao Wu, Thomas Möllenhoff, Daniel Cremers
2019	A*	`conf`	Lifting Vectorial Variational Problems: A Natural Formulation Based on Geometric Measure Theory and Discrete Exterior Calculus. CVPR Thomas Möllenhoff, Daniel Cremers
2019	J	`jnl`	Lifting Vectorial Variational Problems: A Natural Formulation based on Geometric Measure Theory and Discrete Exterior Calculus. CoRR Thomas Möllenhoff, Daniel Cremers
2018	A	`conf`	Combinatorial Preconditioners for Proximal Algorithms on Graphs. AISTATS Thomas Möllenhoff, Zhenzhang Ye, Tao Wu, Daniel Cremers
2018	J	`jnl`	Combinatorial Preconditioners for Proximal Algorithms on Graphs. CoRR Thomas Möllenhoff, Zhenzhang Ye, Tao Wu, Daniel Cremers
2018	A*	`conf`	Fight Ill-Posedness With Ill-Posedness: Single-Shot Variational Depth Super-Resolution From Shading. CVPR Bjoern Haefner, Yvain Quéau, Thomas Möllenhoff, Daniel Cremers
2018	—	`conf`	Proximal Backpropagation. ICLR (Poster) Thomas Frerix, Thomas Möllenhoff, Michael Möller, Daniel Cremers
2017	J	`jnl`	Proximal Backpropagation. CoRR Thomas Frerix, Thomas Möllenhoff, Michael Möller, Daniel Cremers
2017	A*	`conf`	Sublabel-Accurate Discretization of Nonconvex Free-Discontinuity Problems. ICCV Thomas Möllenhoff, Daniel Cremers
2016	J	`jnl`	Precise Relaxation of the Mumford-Shah Functional. CoRR Thomas Möllenhoff, Daniel Cremers
2016	—	`conf`	Sublabel-Accurate Convex Relaxation of Vectorial Multilabel Energies. ECCV (1) Emanuel Laude, Thomas Möllenhoff, Michael Möller, Jan Lellmann, Daniel Cremers
2016	J	`jnl`	Sublabel-Accurate Convex Relaxation of Vectorial Multilabel Energies. CoRR Emanuel Laude, Thomas Möllenhoff, Michael Möller, Jan Lellmann, Daniel Cremers
2016	A*	`conf`	Sublabel-Accurate Relaxation of Nonconvex Energies. CVPR Thomas Möllenhoff, Emanuel Laude, Michael Möller, Jan Lellmann, Daniel Cremers
2015	J	`jnl`	Sublabel-Accurate Relaxation of Nonconvex Energies. CoRR Thomas Möllenhoff, Emanuel Laude, Michael Möller, Jan Lellmann, Daniel Cremers
2015	J	`jnl`	The Primal-Dual Hybrid Gradient Method for Semiconvex Splittings. SIAM J. Imaging Sci. Thomas Möllenhoff, Evgeny Strekalovskiy, Michael Möller, Daniel Cremers
2014	—	`conf`	Low Rank Priors for Color Image Regularization. EMMCVPR Thomas Möllenhoff, Evgeny Strekalovskiy, Michael Möller, Daniel Cremers
2014	J	`jnl`	The Primal-Dual Hybrid Gradient Method for Semiconvex Splittings. CoRR Thomas Möllenhoff, Evgeny Strekalovskiy, Michael Möller, Daniel Cremers
2013	—	`conf`	Efficient Convex Optimization for Minimal Partition Problems with Volume Constraints. EMMCVPR Thomas Möllenhoff, Claudia Nieuwenhuis, Eno Töppe, Daniel Cremers