TY - CONF AU - Hüsing, Sven AU - Schulte, Carsten AU - Sparmann, Sören AU - Bolte, Mario ID - 52379 T2 - Proceedings of the 55th ACM Technical Symposium on Computer Science Education V. 1 TI - Using Worked Examples for Engaging in Epistemic Programming Projects ER - TY - CONF AU - Hu, Lijie AU - Habernal, Ivan AU - Shen, Lei AU - Wang, Di ED - Graham, Yvette ED - Purver, Matthew ID - 52827 T2 - Findings of the Association for Computational Linguistics: EACL 2024, St. Julian’s, Malta, March 17-22, 2024 TI - Differentially Private Natural Language Models: Recent Advances and Future Directions ER - TY - CONF AB - Neural machine translation (NMT) is a widely popular text generation task, yet there is a considerable research gap in the development of privacy-preserving NMT models, despite significant data privacy concerns for NMT systems. Differentially private stochastic gradient descent (DP-SGD) is a popular method for training machine learning models with concrete privacy guarantees; however, the implementation specifics of training a model with DP-SGD are not always clarified in existing models, with differing software libraries used and code bases not always being public, leading to reproducibility issues. To tackle this, we introduce DP-NMT, an open-source framework for carrying out research on privacy-preserving NMT with DP-SGD, bringing together numerous models, datasets, and evaluation metrics in one systematic software package. Our goal is to provide a platform for researchers to advance the development of privacy-preserving NMT systems, keeping the specific details of the DP-SGD algorithm transparent and intuitive to implement. We run a set of experiments on datasets from both general and privacy-related domains to demonstrate our framework in use. We make our framework publicly available and welcome feedback from the community. AU - Igamberdiev, Timour AU - Vu, Doan Nam Long AU - Kuennecke, Felix AU - Yu, Zhuo AU - Holmer, Jannik AU - Habernal, Ivan ED - Aletras, Nikolaos ED - De Clercq, Orphee ID - 52842 T2 - Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations TI - DP-NMT: Scalable Differentially Private Machine Translation ER - TY - CONF AU - Dann, Andreas Peter AU - Hermann, Ben AU - Bodden, Eric ID - 35083 TI - UpCy: Safely Updating Outdated Dependencies ER - TY - JOUR AB - As in almost every other branch of science, the major advances in data science and machine learning have also resulted in significant improvements regarding the modeling and simulation of nonlinear dynamical systems. It is nowadays possible to make accurate medium to long-term predictions of highly complex systems such as the weather, the dynamics within a nuclear fusion reactor, of disease models or the stock market in a very efficient manner. In many cases, predictive methods are advertised to ultimately be useful for control, as the control of high-dimensional nonlinear systems is an engineering grand challenge with huge potential in areas such as clean and efficient energy production, or the development of advanced medical devices. However, the question of how to use a predictive model for control is often left unanswered due to the associated challenges, namely a significantly higher system complexity, the requirement of much larger data sets and an increased and often problem-specific modeling effort. To solve these issues, we present a universal framework (which we call QuaSiModO: Quantization-Simulation-Modeling-Optimization) to transform arbitrary predictive models into control systems and use them for feedback control. The advantages of our approach are a linear increase in data requirements with respect to the control dimension, performance guarantees that rely exclusively on the accuracy of the predictive model, and only little prior knowledge requirements in control theory to solve complex control problems. In particular the latter point is of key importance to enable a large number of researchers and practitioners to exploit the ever increasing capabilities of predictive models for control in a straight-forward and systematic fashion. AU - Peitz, Sebastian AU - Bieker, Katharina ID - 21199 JF - Automatica TI - On the Universal Transformation of Data-Driven Models to Control Systems VL - 149 ER - TY - CONF AU - Schrader, Elena AU - Bernijazov, Ruslan AU - Foullois, Marc AU - Hillebrand, Michael AU - Kaiser, Lydia AU - Dumitrescu, Roman ID - 37553 T2 - 2022 IEEE International Symposium on Systems Engineering (ISSE) TI - Examples of AI-based Assistance Systems in context of Model-Based Systems Engineering ER - TY - CONF AU - Richter, Cedric AU - Haltermann, Jan Frederik AU - Jakobs, Marie-Christine AU - Pauck, Felix AU - Schott, Stefan AU - Wehrheim, Heike ID - 35426 T2 - 37th IEEE/ACM International Conference on Automated Software Engineering TI - Are Neural Bug Detectors Comparable to Software Developers on Variable Misuse Bugs? ER - TY - CONF AU - Schott, Stefan AU - Pauck, Felix ID - 36848 T2 - 2022 IEEE 22nd International Working Conference on Source Code Analysis and Manipulation (SCAM) TI - Benchmark Fuzzing for Android Taint Analyses ER - TY - CONF AU - Pauck, Felix ID - 35427 T2 - 37th IEEE/ACM International Conference on Automated Software Engineering TI - Scaling Arbitrary Android App Analyses ER - TY - GEN AB - We consider the data-driven approximation of the Koopman operator for stochastic differential equations on reproducing kernel Hilbert spaces (RKHS). Our focus is on the estimation error if the data are collected from long-term ergodic simulations. We derive both an exact expression for the variance of the kernel cross-covariance operator, measured in the Hilbert-Schmidt norm, and probabilistic bounds for the finite-data estimation error. Moreover, we derive a bound on the prediction error of observables in the RKHS using a finite Mercer series expansion. Further, assuming Koopman-invariance of the RKHS, we provide bounds on the full approximation error. Numerical experiments using the Ornstein-Uhlenbeck process illustrate our results. AU - Philipp, Friedrich AU - Schaller, Manuel AU - Worthmann, Karl AU - Peitz, Sebastian AU - Nüske, Feliks ID - 38031 T2 - arXiv:2301.08637 TI - Error bounds for kernel-based approximations of the Koopman operator ER -