PUBLICATIONS
For the publication list of the group members: People
2019 | 2018 | 2017 | 2016 | 2015 | 2014 | 2013 | 2012 | 2011 | 2010 | 2009 | 2008 | 2007 | 2006 | 2005 | 2004 | 2003
2019
- D. Stutz, M. Hein, B. Schiele
Confidence-Calibrated Adversarial Training: Towards Robust Models Generalizing Beyond the Attack Used During Training
preprint, available at arxiv. - A. Meinke, M. Hein
Towards neural networks that provably know when they don't know
preprint, available at arxiv - M. Andriushchenko, M. Hein
Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks
accepted at NeurIPS, pre-final version at arxiv - P. Mercado, F. Tudisco, M. Hein
Generalized Matrix Means for Semi-Supervised Learning with Multilayer Graphs
accepted at NeurIPS, paper available soon - F. Croce, M. Hein
Sparse and imperceivable adversarial attacks
accepted at ICCV, final version at arxiv and code is available here - N. Garcia Trillos, M. Gerlach, M. Hein, D. Slepcev
Error estimates for spectral convergence of the graph Laplacian on random geometric graphs towards the Laplace--Beltrami operator
accepted at Foundations of Computational Mathematics (FOCM), available at arxiv. - F. Croce, M. Hein
Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack
preprint, available on arxiv and code is available here - A. Gautier, F. Tudisco, M. Hein
A unifying Perron-Frobenius theorem for nonnegative tensors via multi-homogeneous maps
accepted at SIAM J. Matrix Analysis (SIMAX), pre-final version available at arxiv. - A. Gautier, F. Tudisco, M. Hein
The Perron-Frobenius theorem for multi-homogeneous mappings
accepted at SIAM J. Matrix Analysis (SIMAX), pre-final version available at arxiv. - F. Croce, M. Hein
Provable robustness against all adversarial l_p-perturbations for p>=1
preprint, available on arxiv - F. Croce, J. Rauber, M. Hein
Scaling up the randomized gradient-free adversarial attack reveals overestimation of robustness using established attacks
accepted at International Journal of Computer Vision (IJCV), pre-final version available on arxiv - P. Mercado, F. Tudisco, M. Hein
Spectral Clustering of Signed Graphs via Matrix Power Means
ICML 2019, download PDF - M. Hein, M. Andriushchenko, J. Bitterwolf
Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem
CVPR 2019 (oral presentation), available on arxiv. - D. Stutz, M. Hein, B. Schiele
Disentangling Adversarial Robustness and Generalization
CVPR 2019, available on arxiv. - F. Croce, M. Andriushchenko, M. Hein
Provable Robustness of ReLU networks via Maximization of Linear Regions
AISTATS 2019, available on arxiv. - Q. Nguyen, M. Mukkamala, M. Hein
On the loss landscape of a class of deep neural networks with no bad local valleys
ICLR 2019, download PDF at arxiv .
2018
- M. Mosbach, M. Andriushchenko, T. Trost, M. Hein, D. Klakow
Logit Pairing Methods Can Fool Gradient-Based Attacks
NeurIPS 2018 Workshop on Security in Machine Learning, available on arxiv. - F. Croce, M. Hein
A randomized gradient-free attack on ReLU networks
GCPR, 2018, available on arxiv. - F. Tudisco, P. Mercado, M. Hein
Community Detection in Networks via Nonlinear Modularity Eigenvectors
SIAM Journal of Applied Mathematics, 78(5): 2393--2419, 2018, preprint available at arxiv. - M. Lapin, M. Hein, B. Schiele
Analysis and Optimization of Loss Functions for Multiclass, Top-k, and Multilabel Classification
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 40(7):1533-1554, 2018, available here or at arxiv. - F. Tudisco, M. Hein
A nodal domain theorem and a higher-order Cheeger inequality for the graph p-Laplacian
Journal of Spectral Theory, 8(3): 883-908, 2018, preprint available at arxiv. - Q. Nguyen, M. Hein
Optimization Landscape and Expressivity of Deep CNNs
ICML 2018, PDF (long version including proofs: PDF ). - Q. Nguyen, M. Mukkamala, M. Hein
Neural networks should be wide enough to learn disconnected decision regions
ICML 2018, PDF (long version including proofs: PDF ). - N. Garcia Trillos, M. Gerlach, M. Hein, D. Slepcev
Error estimates for spectral convergence of the graph Laplacian on random geometric graphs towards the Laplace--Beltrami operator
preprint, available at arxiv. - A. Gautier, F. Tudisco, M. Hein
A unifying Perron-Frobenius theorem for nonnegative tensors via multi-homogeneous maps
preprint, available at arxiv. - A. Gautier, F. Tudisco, M. Hein
The Perron-Frobenius theorem for multi-homogeneous mappings
preprint, available at arxiv. - P. Mercado, A. Gautier, F. Tudisco, M. Hein
The Power Mean Laplacian for Multilayer Graph Clustering
AISTATS 2018, PDF (Appendix containing the proofs: PDF and code is available here)
2017
- Q. Nguyen, M. Hein
The loss surface and expressivity of deep convolutional neural networks
preprint, download PDF or on arxiv. - M. Hein, M. Andriushchenko
Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation
NeurIPS 2017, PDF (Long Version including proofs: PDF , code is avalaible here). - M. C. Mukkamala, M. Hein
Variants of RMSProp and Adagrad with Logarithmic Regret Bounds
ICML 2017, PDF (Long Version including proofs: PDF , code is avalaible here). - Q. Nguyen, M. Hein
The loss surface of deep and wide neural networks
ICML 2017, PDF (Long Version including proofs: PDF ). - A. Khoreva, R. Beneson, J. Hosang, M. Hein and B. Schiele
Simple does it: Weakly Supervised Instance and Semantic Segmentation
CVPR 2017, PDF - A. Gautier, F. Tudisco, M. Hein
The Perron-Frobenius Theorem for Multi-homogeneous Maps
preprint, available at arxiv. - P. Lutsik, M. Slawski, G. Gasparoni, N. Vedeneev, M. Hein, J. Walter
MeDeCom: discovery and quantification of latent components of heterogeneous methylomes
Genome Biology, 18:55, 2017, Link to article (open access), code is avalaible here
2016
- M. Lapin, M. Hein, B. Schiele
Analysis and Optimization of Loss Functions for Multiclass, Top-k, and Multilabel Classification
preprint, available at arxiv. - A. Gautier, Q. Nguyen Ngoc, M. Hein
Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods
NeurIPS 2016. PDF (Supplementary material (Long version): PDF ) (download matlab code) - P. Mercado, F. Tudisco, M. Hein
Clustering Signed Networks with the Geometric Mean of Laplacians
NeurIPS 2016. PDF (Supplementary material (Long version): PDF ) (code is available here) - A. Gautier and M. Hein
Tensor norm and maximal singular vectors of non-negative tensors - a Perron-Frobenius theorem, a Collatz-Wielandt characterization and a generalized power method
Linear Algebra and its Applications, 505:313–343, 2016, Link to article, preprint available at arxiv. (project page)
- F. Tudisco, M. Hein
A nodal domain theorem and a higher-order Cheeger inequality for the graph p-Laplacian
preprint, available at arxiv. - Q. Ngoc, F. Tudisco, A. Gautier, M. Hein
An Efficient Multilinear Optimization Framework for Hypergraph Matching
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 39(6):1054-1075, 2017, Link, preprint available at arxiv (download code - M. Lapin, M. Hein and B. Schiele
Loss Functions for Top-k Error: Analysis and Insights
CVPR 2016. PDF (Long version: PDF ) (code at github) - Y. Xian, Z. Akata, G. Sharma, Q. Ngoc, M. Hein and B. Schiele
Latent Embeddings for Zero-shot Classification
CVPR 2016 (spotlight). PDF (Long version: PDF ) (project page) - A. Khoreva, R. Beneson, M. Omran, M. Hein and B. Schiele
Weakly Supervised Object Boundaries
CVPR 2016 (spotlight). PDF (Long version: PDF ) (project page)
2015
- M. Lapin, M. Hein and B. Schiele
Top-k Multiclass SVM
spotlight at NeurIPS 2015. PDF (Supplementary material (Long version): PDF ) (Code available - here) - P. Jawanpuria, M. Lapin, M. Hein and B. Schiele
Efficient Output Kernel Learning for Multiple Tasks
NeurIPS 2015. PDF (Supplementary material (Long version): PDF ) (download code) - M. Slawski, P. Li and M. Hein
Regularization-Free Estimation in Trace Regression with Symmetric Positive Semidefinite Matrices
NeurIPS 2015. PDF (Supplementary material (Long version): PDF ) - A. Gautier and M. Hein
Tensor norm and maximal singular vectors of non-negative tensors - a Perron-Frobenius theorem, a Collatz-Wielandt characterization and a generalized power method
preprint, available at arxiv. (project page) - Q. Ngoc, A. Gautier and M. Hein
A Flexible Tensor Block Coordinate Ascent Scheme for Hypergraph Matching
CVPR 2015 (oral presentation). PDF (Supplementary material: PDF ) (project page) - A. Khoreva, F. Galasso, M. Hein and B. Schiele
Classifier Based Graph Construction for Video Segmentation
CVPR 2015. PDF (Supplementary material: ZIP ). (project page). - S. Bhadra and M. Hein
Correction of Noisy Labels via Mutual Consistency Check
Neurocomputing, 160: 34-52, 2015, PDF (you can find the code here)
- M. Slawski, M. Hein,
Estimation of positive definite M-matrices and structure learning for attractive Gaussian Markov Random fields
Linear Algebra and its Applications, 473: 145-179 (Special Issue on Statistics). Long version can be found here: Link
2014
- S. Rangapuram, P. K. Mudrakarta and M. Hein
Tight continuous relaxation of the balanced k-cut problem
NeurIPS 2014. PDF (Supplementary material (Long version): PDF ) (code ) - L. Jost, S. Setzer and M. Hein
Nonlinear Eigenproblems in Data Analysis - Balanced Graph Cuts and the RatioDCA-Prox
in "Extraction of Quantifiable Information from Complex Systems",
S. Dahlke, W. Dahmen, M. Griebel, W. Hackbusch, K. Ritter, R. Schneider, C. Schwab, H. Yserentant (Eds.)
Link to arxiv version - A. Podosinnikova, S. Setzer and M. Hein
Robust PCA: Optimization of the Robust Reconstruction Error on the Stiefel Manifold
GCPR 2014, PDF (Supplementary material: PDF ) - code is available on our code page - A. Khoreva, F. Galasso, M. Hein and B. Schiele,
Learning Must-Link Constraints for Video Segmentation based on Spectral Clustering
GCPR 2014, PDF and project page - M. Slawski and M. Hein,
Sparse Recovery for Protein Mass Spectrometry Data
in "Practical Applications of Sparse Modeling", edited by I. Rish, G. Cecchi, A. Lozano, A. Niculescu-Mizil, MIT press. PDF - U. von Luxburg, A. Radl and M. Hein,
Hitting and Commute Times in Large Random Neighborhood Graphs,
Journal of Machine Learning Research, 15: 1751-1798, 2014, PDF - M. Lapin, M. Hein and B. Schiele,
Scalable Multitask Representation Learning for Scene Classification
CVPR 2014, PDF and project page - M. Lapin, M. Hein and B. Schiele,
Learning Using Privileged Information: SVM+ and Weighted SVM
Neural Networks, 53: 95-108, 2014, PDF
2013
- M. Slawski, M. Hein,
Non-negative least squares for high-dimensional linear models: consistency and sparse recovery without regularization
Electronic Journal of Statistics, 7(0):3004-3056, 2013. Link - M. Hein, S. Setzer, L. Jost, and S. Rangapuram,
The Total Variation on Hypergraphs - Learning on Hypergraphs Revisited
spotlight at NeurIPS 2013 (acceptance rate < 5%), PDF (Supplementary material: PDF ) - M. Slawski, M. Hein, and P. Lutsik,
Matrix Factorization with Binary Components
spotlight at NeurIPS 2013 (acceptance rate < 5%), PDF (Supplementary material: PDF ) - S. Rangapuram, T. Buehler, and M. Hein,
Towards Realistic Team Formation in Social Networks based on Densest Subgraphs
WWW 2013, 1077-1088. PDF - T. Buehler, S. Rangapuram, S. Setzer and M. Hein,
Constrained fractional set programs and their application in local clustering and community detection
ICML 2013, 624-632. PDF (Supplementary material: PDF ) - M. Maier, U. von Luxburg and M. Hein,
How the result of graph clustering methods depends on the construction of the graph,
ESAIM: Probability and Statistics, 17: 370-418, 2013. Link
2012
- M. Slawski, R. Hussong, A. Tholey, T. Jakoby, B. Gregorius, A. Hildebrandt, M. Hein
Isotope pattern deconvolution for peptide mass spectrometry by non-negative least squares/least absolute deviation template matching,
BMC Bioinformatics 2012, 13:291 (8 November 2012). PDF - C. Backes, A. Rurainski, G.W. Klau, O. Müller, D. Stöckel, A. Gerasch, J. Küntzer, D. Maisel, N. Ludwig, M. Hein, A. Keller, H. Burtscher, M. Kaufmann, E. Meese, H.-P. Lenhof,
An integer linear programming approach for finding deregulated subgraphs in regulatory networks,
Nucleic Acids Research, 40(6):e43. PDF - S. Rangapuram and M. Hein,
Constrained 1-Spectral Clustering,
AISTATS 2012, JMLR W&CP 22: 1143-1151, PDF (Supplementary material: PDF )
2011
- M. Slawski and M. Hein,
Sparse recovery by thresholded non-negative least squares,
In Advances in Neural Information Processing Systems 24 (NeurIPS 2011), 1926--1934, 2011. PDF (Supplementary material: PDF ) - M. Hein and S. Setzer,
Beyond Spectral Clustering - Tight Relaxations of Balanced Graph Cuts,
In Advances in Neural Information Processing Systems 24 (NeurIPS 2011), 2366--2374, 2011. PDF (Supplementary material (Long version): PDF ) - M. Slawski and M. Hein,
Robust sparse recovery with non-negativity constraints,
In Workshop on Signal Processing with Adaptive Sparse Structured Representations (SPARS), 2011. PDF
2010
- M. Slawski and M. Hein,
Sparse Recovery for Protein Mass Spectrometry Data,
In NeurIPS Workshop "Practical Application of Sparse Modeling: Open Issues and New Directions", 2010. PDF - M. Hein and T. Buehler,
An inverse power method for nonlinear eigenproblems with applications in 1-spectral clustering and sparse PCA,
In Advances in Neural Information Processing Systems 23 (NeurIPS 2010), 847-855, 2010. PDF (Supplementary material: PDF ) - U. von Luxburg, A. Radl and M. Hein,
Getting lost in space: Large sample analysis of the commute distance,
In Advances in Neural Information Processing Systems 23 (NeurIPS 2010), 2622-2630, 2010. PDF (Supplementary material: PDF ) - F. Steinke, M. Hein, B. Schoelkopf.
Non-parametric regression between general Riemannian manifolds,
SIAM Journal on Imaging Sciences, 3:527-563, 2010. PDF - U. von Luxburg, A. Radl, M. Hein.
Hitting times, commute distances and the spectral gap for large random geometric graphs,
arXiv:1003.1266v1 Link - M. Slawski, W. zu Castell, G. Tutz.
Feature Selection Guided by Structural Information,
Annals of Applied Statistics, 4:1056-1080, 2010. Link
2009
- M. Hein,
Robust Nonparametric Regression with Metric-Space valued Output,
In Y. Bengio and D. Schuurmans and J. Lafferty and C. K. I. Williams and A. Culotta, editors, Advances in Neural Information Processing Systems 22 (NeurIPS 2009), 718-726, MIT Press, Cambridge, MA, 2010, PDF (Supplementary material: PDF ) - K.I. Kim, F. Steinke and M. Hein,
Semi-supervised Regression using Hessian energy with an application to semi-supervised dimensionality reduction,
In Y. Bengio and D. Schuurmans and J. Lafferty and C. K. I. Williams and A. Culotta, editors, Advances in Neural Information Processing Systems 22 (NeurIPS 2009), 979-987, MIT Press, Cambridge, MA, 2010, PDF (Supplementary material: PDF ) - A. Keller, N. Ludwig, S. Heisel, P. Leidinger, C. Andres, W.-I. Steudel, H. Huwer, B. Burgeth, M. Hein, J. Weickert, E. Meese und H.-P. Lenhof.
Large-scale antibody profiling of human blood sera: The future of molecular diagnosis,
Informatik-Spektrum, 32:332-338, 2009. Link - T. Buehler, M. Hein,
Spectral Clustering based on the graph p-Laplacian,
In Leon Bottou and Michael Littman, editors, Proceedings of the 26th International Conference on Machine Learning (ICML 2009), 81-88, Omnipress, 2009, PDF (Supplementary material: PDF - Errata of Supp. Mat.: PDF ) - M. Maier, M. Hein, U. von Luxburg.
Optimal construction of k-nearest neighbor graphs for identifying noisy clusters,
Theoretical Computer Science, 410:1749-1764, 2009. PDF
2008
- F. Steinke, M. Hein,
Non-parametric Regression between Manifolds,
In D. Koller and D. Schuurmans and Y. Bengio and L. Bottou, editors, Advances in Neural Information Processing Systems 21 (NeurIPS 2008), 1561 - 1568, MIT Press, Cambridge, MA, 2009, PDF - M. Maier, U. von Luxburg, M. Hein,
Influence of Graph Construction on Graph-based Clustering Measures,
In D. Koller and D. Schuurmans and Y. Bengio and L. Bottou, editors, Advances in Neural Information Processing Systems 21 (NeurIPS 2008), 1025 - 1032, MIT Press, Cambridge, MA, 2009, PDF
Markus Maier obtained for this paper the Outstanding Student Paper Award at NeurIPS 2008. - M. Hein, F. Steinke, B. Schoelkopf.
Nonparametric regression between manifolds,
Oberwolfach Report 30:34-35, 2008.
- P. Didyk, R. Mantiuk, M. Hein, H. P. Seidel.
Enhancement of Bright Video Features for HDR Displays,
Computer Graphics Forum, 27:1265-1274, 2008. (Proceedings of Eurographics Symposium on Rendering 2008). - F. Steinke, M. Hein, J. Peters, B. Schoelkopf.
Manifold-valued Thin-Plate Splines with Applications in Computer Graphics,
Computer Graphics Forum, 27:437-448, 2008. PDF (Proceedings of EUROGRAPHICS 2008). - M. Hein.
Binary Classification under Sample Selection Bias,
in J. Quinonero Candela, M. Sugiyama, A. Schwaighofer, N. D. Lawrence (editors), "Dataset Shift", 2008. PDF - M. Hein, F. Steinke, B. Schoelkopf.
Energy functionals for manifold-valued mappings and their properties,
Technical Report 167, Max Planck Institute for Biological Cybernetics, January 2008. PDF
2007
- M. Hein, J.-Y. Audibert, U. von Luxburg.
Convergence of graph Laplacians on random neighborhood graphs,
Journal of Machine Learning Research, 8:1325-1370, 2007. PDF - M. Maier, M. Hein, U. von Luxburg.
Cluster Identification in neighborhood graphs,
In M. Hutter, R. Servedio, and E. Takimoto, editors, Proceedings of the 18th International Confererence on Algorithmic Learning Theory (ALT 2007), 196 - 210, Springer, New York, 2007, PDF
Markus Maier obtained for this paper the E. M. Gold Award (best student paper) at ALT 2007.
Corresponding technical report:
M. Maier, M. Hein, U. von Luxburg.
Cluster identification in nearest-neighbor graphs,
Technical Report 163, Max Planck Institute for Biological Cybernetics, May 2007. PDF - M. Hein, M. Maier.
Manifold Denoising for finding natural representations of data,
Proceedings of the 22nd AAAI Conference on Artificial Intelligence (AAAI-07), 1646-1649, AAAI Press, PDF
2006
- M. Hein, M. Maier.
Manifold Denoising,
In B. Schoelkopf, J. Platt, and T. Hofmann, editors, Advances in Neural Information Processing Systems 19 (NeurIPS 2006), 561 - 568, MIT Press, Cambridge, MA, 2007, PDF - M. Hein.
Uniform convergence of adaptive graph-based regularization,
In G. Lugosi and H. U. Simon, editors, Proceedings of the 19th Annual Conference on Learning Theory (COLT 2006), 50-64, Springer, New York, 2006, PDF
2005
- M. Hein, O. Bousquet, B. Schoelkopf.
Maximal margin classification for metric spaces,
Journal of Computer and System Sciences, 71:333-359, 2005. PDF - M. Hein, J.-Y. Audibert.
Intrinsic dimensionality estimation of submanifolds in Euclidean space,
In L. de Raedt and S. Wrobel, editors, Proceedings of the 22nd International Conference on Machine Learning (ICML 2005), 289 - 296, ACM press, 2005, PDF - M. Hein, J.-Y. Audibert, U. von Luxburg.
From graphs to manifolds - weak and strong pointwise consistency of graph Laplacians,
In R. Meir and P. Auer, editors, Proceedings of the 18th Conference on Learning Theory (COLT 2005), 470-485, Springer, New York, 2005, PDF
This paper has won a best student paper award at COLT 2005. - M. Hein and O. Bousquet.
Hilbertian metrics and positive definite kernels on probability measures,
In Z. Ghahramani and R. Cowell, editors, Proceedings of the 10th International Workshop on Artificial Intelligence and Statistics (AISTATS). Society for Artificial Intelligence and Statistics, 2005. PDF
2004
- M. Hein, T. N. Lal, O. Bousquet.
Hilbertian metrics on probability measures and their application in SVMs,
In C. E. Rasmussen, H. H. Buelthoff, M. Giese, and B. Schoelkopf, editors, Proceedings of the 26th DAGM Symposium, 270-277, Springer, Berlin, 2004, PDFCorresponding technical report:
M. Hein, O. Bousquet.
Hilbertian metrics and positive definite kernels on probability measures,
Technical Report 126, Max Planck Institute for Biological Cybernetics, July 2004. PDF - M. Hein, O. Bousquet.
Kernels, associated structures and generalizations,
Technical Report 127, Max Planck Institute for Biological Cybernetics, July 2004. PDF
2003
- O. Bousquet, O. Chapelle, and M. Hein.
Measure based regularization,
In S. Thrun, L. Saul, and B. Schoelkopf, editors, Advances in Neural Information Processing Systems 16 (NeurIPS 2003), MIT Press, Cambridge, MA, 2004, PDF - M. Hein and O. Bousquet.
Maximal margin classification for metric spaces,
In B. Schoelkopf and M. K. Warmuth, editors, 16th Annual Conference on Learning Theory (COLT 2003), Berlin, 2003. Springer. PDF