Marius Kloft

A Unifying Review of Deep and Shallow Anomaly Detection

Sep 28, 2020
Lukas Ruff, Jacob R. Kauffmann, Robert A. Vandermeulen, Grégoire Montavon, Wojciech Samek, Marius Kloft, Thomas G. Dietterich, Klaus-Robert Müller

* 36 pages, preprint; references added

Access Paper or Ask Questions

Input Hessian Regularization of Neural Networks

Sep 14, 2020
Waleed Mustafa, Robert A. Vandermeulen, Marius Kloft

* Workshop on "Beyond first-order methods in ML systems" at the 37th International Conference on Machine Learning, Vienna, Austria, 2020

Access Paper or Ask Questions

Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Events

Aug 27, 2020
Guang Yu, Siqi Wang, Zhiping Cai, En Zhu, Chuanfu Xu, Jianping Yin, Marius Kloft

* To be published as an oral paper in Proceedings of the 28th ACM International Conference on Multimedia (ACM MM '20). 9 pages, 7 figures

Access Paper or Ask Questions

Explainable Deep One-Class Classification

Jul 03, 2020
Philipp Liznerski, Lukas Ruff, Robert A. Vandermeulen, Billy Joe Franks, Marius Kloft, Klaus-Robert Müller

* 24 pages, preprint

Access Paper or Ask Questions

How Much Can I Trust You? -- Quantifying Uncertainties in Explaining Neural Networks

Jun 16, 2020
Kirill Bykov, Marina M. -C. Höhne, Klaus-Robert Müller, Shinichi Nakajima, Marius Kloft

* 12 pages, 10 figures

Access Paper or Ask Questions

Rethinking Assumptions in Deep Anomaly Detection

May 30, 2020
Lukas Ruff, Robert A. Vandermeulen, Billy Joe Franks, Klaus-Robert Müller, Marius Kloft

* 22 pages, preprint

Access Paper or Ask Questions

Orthogonal Inductive Matrix Completion

Apr 23, 2020
Antoine Ledent, Rodrigo Alves, Marius Kloft

Access Paper or Ask Questions

Machine Learning in Thermodynamics: Prediction of Activity Coefficients by Matrix Completion

Jan 29, 2020
Fabian Jirasek, Rodrigo A. S. Alves, Julie Damay, Robert A. Vandermeulen, Robert Bamler, Michael Bortz, Stephan Mandt, Marius Kloft, Hans Hasse

* J. Phys. Chem. Lett. 11 (2020) 981-985
* Published version: J. Phys. Chem. Lett. 11 (2020) 981-985; https://pubs.acs.org/doi/full/10.1021/acs.jpclett.9b03657

Access Paper or Ask Questions

Simple and Effective Prevention of Mode Collapse in Deep One-Class Classification

Jan 28, 2020
Penny Chong, Lukas Ruff, Marius Kloft, Alexander Binder

Access Paper or Ask Questions

Two-sample Testing Using Deep Learning

Oct 14, 2019
Matthias Kirchler, Shahryar Khorasani, Marius Kloft, Christoph Lippert

Access Paper or Ask Questions

Analyzing the Variance of Policy Gradient Estimators for the Linear-Quadratic Regulator

Oct 02, 2019
James A. Preiss, Sébastien M. R. Arnold, Chen-Yu Wei, Marius Kloft

* Accepted at NeurIPS 2019 Workshop on Optimization Foundations for Reinforcement Learning. 7 pages + 6 pages appendix

Access Paper or Ask Questions

Deep Semi-Supervised Anomaly Detection

Jun 06, 2019
Lukas Ruff, Robert A. Vandermeulen, Nico Görnitz, Alexander Binder, Emmanuel Müller, Klaus-Robert Müller, Marius Kloft

* 22 pages, Under review

Access Paper or Ask Questions

Improved Generalisation Bounds for Deep Learning Through $L^\infty$ Covering Numbers

May 29, 2019
Antoine Ledent, Yunwen Lei, Marius Kloft

* 26 pages, 8 figures

Access Paper or Ask Questions

Scalable Generalized Dynamic Topic Models

Mar 21, 2018
Patrick Jähnichen, Florian Wenzel, Marius Kloft, Stephan Mandt

* Published version, International Conference on Artificial Intelligence and Statistics (AISTATS 2018)

Access Paper or Ask Questions

* accepted as conference paper at ECML-PKDD 2017

Access Paper or Ask Questions

Sparse Probit Linear Mixed Model

Jul 17, 2017
Stephan Mandt, Florian Wenzel, Shinichi Nakajima, John P. Cunningham, Christoph Lippert, Marius Kloft

* Machine Learning, 106(9), 1621-1642 (2017)
* Published version, 21 pages, 6 figures

Access Paper or Ask Questions

Local Rademacher Complexity-based Learning Guarantees for Multi-Task Learning

Feb 09, 2017
Niloofar Yousefi, Yunwen Lei, Marius Kloft, Mansooreh Mollaghasemi, Georgios Anagnostopoulos

* In this version, some arguments and results (of the previous version) have been corrected, or modified

Access Paper or Ask Questions

Distributed Optimization of Multi-Class SVMs

Dec 08, 2016
Maximilian Alber, Julian Zimmert, Urun Dogan, Marius Kloft

Access Paper or Ask Questions

Feature Importance Measure for Non-linear Learning Algorithms

Nov 22, 2016
Marina M. -C. Vidovic, Nico Görnitz, Klaus-Robert Müller, Marius Kloft

* Presented at NIPS 2016 Workshop on Interpretable Machine Learning in Complex Systems

Access Paper or Ask Questions

Localized Multiple Kernel Learning---A Convex Approach

Oct 13, 2016
Yunwen Lei, Alexander Binder, Ürün Dogan, Marius Kloft

* to appear in ACML 2016

Access Paper or Ask Questions

Framework for Multi-task Multiple Kernel Learning and Applications in Genome Analysis

Jun 30, 2015
Christian Widmer, Marius Kloft, Vipin T Sreedharan, Gunnar Rätsch

Access Paper or Ask Questions

Multi-class SVMs: From Tighter Data-Dependent Generalization Bounds to Novel Algorithms

Jun 14, 2015
Yunwen Lei, Ürün Dogan, Alexander Binder, Marius Kloft

Access Paper or Ask Questions

Probabilistic Clustering of Time-Evolving Distance Data

Apr 14, 2015
Julia E. Vogt, Marius Kloft, Stefan Stark, Sudhir S. Raman, Sandhya Prabhakaran, Volker Roth, Gunnar Rätsch

Access Paper or Ask Questions

Localized Complexities for Transductive Learning

Nov 26, 2014
Ilya Tolstikhin, Gilles Blanchard, Marius Kloft

* Appeared in Conference on Learning Theory 2014

Access Paper or Ask Questions

Insights from Classifying Visual Concepts with Multiple Kernel Learning

Dec 16, 2011
Alexander Binder, Shinichi Nakajima, Marius Kloft, Christina Müller, Wojciech Samek, Ulf Brefeld, Klaus-Robert Müller, Motoaki Kawanabe

* PLoS ONE 7(8): e38897, 2012
* 18 pages, 8 tables, 4 figures, format deviating from plos one submission format requirements for aesthetic reasons

Access Paper or Ask Questions

The Local Rademacher Complexity of Lp-Norm Multiple Kernel Learning

Mar 03, 2011
Marius Kloft, Gilles Blanchard

Access Paper or Ask Questions

Non-Sparse Regularization for Multiple Kernel Learning

Oct 26, 2010
Marius Kloft, Ulf Brefeld, Soeren Sonnenburg, Alexander Zien

Access Paper or Ask Questions

Marius Kloft

A Unifying Review of Deep and Shallow Anomaly Detection

Input Hessian Regularization of Neural Networks

Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Events

Explainable Deep One-Class Classification

How Much Can I Trust You? -- Quantifying Uncertainties in Explaining Neural Networks

Rethinking Assumptions in Deep Anomaly Detection

Orthogonal Inductive Matrix Completion

Machine Learning in Thermodynamics: Prediction of Activity Coefficients by Matrix Completion

Simple and Effective Prevention of Mode Collapse in Deep One-Class Classification

Two-sample Testing Using Deep Learning

Analyzing the Variance of Policy Gradient Estimators for the Linear-Quadratic Regulator

Deep Semi-Supervised Anomaly Detection

Improved Generalisation Bounds for Deep Learning Through $L^\infty$ Covering Numbers

Scalable Generalized Dynamic Topic Models

Efficient Gaussian Process Classification Using Polya-Gamma Data Augmentation

Data-dependent Generalization Bounds for Multi-class Classification

Bayesian Nonlinear Support Vector Machines for Big Data

Sparse Probit Linear Mixed Model

Local Rademacher Complexity-based Learning Guarantees for Multi-Task Learning

Distributed Optimization of Multi-Class SVMs

Feature Importance Measure for Non-linear Learning Algorithms

Localized Multiple Kernel Learning---A Convex Approach

Framework for Multi-task Multiple Kernel Learning and Applications in Genome Analysis

Multi-class SVMs: From Tighter Data-Dependent Generalization Bounds to Novel Algorithms

Probabilistic Clustering of Time-Evolving Distance Data

Localized Complexities for Transductive Learning

Insights from Classifying Visual Concepts with Multiple Kernel Learning

The Local Rademacher Complexity of Lp-Norm Multiple Kernel Learning

Non-Sparse Regularization for Multiple Kernel Learning