@inproceedings{PetracekMaesBurgeretal.2012, author = {Petracek, Jiri and Maes, Bjorn and Burger, Sven and Luksch, Jaroslav and Kwiecien, Pavel and Richter, Ivan}, title = {Simulation of high-Q nanocavities with 1D photonic gap}, booktitle = {Transparent Optical Networks (ICTON)}, publisher = {IEEE}, doi = {10.1109/ICTON.2012.6253762}, pages = {1 -- 4}, year = {2012}, language = {en} } @inproceedings{PetracekLukschMaesetal.2012, author = {Petracek, Jiri and Luksch, Jaroslav and Maes, Bjorn and Burger, Sven and Kwiecien, Pavel and Richter, Ivan}, title = {Simulation of photonic crystal nanocavities using a bidirectional eigenmode propagation algorithm: a comparative study}, booktitle = {Micro- and nanophotonic materials and devices}, editor = {Ferrari, M. and Marciniak, M. and Righini, G. and Szoplik, T. and Varas, S.}, publisher = {IFN-CNR, Trento, Italy}, isbn = {9788377980200}, pages = {109 -- 112}, year = {2012}, language = {en} } @inproceedings{SchlosserSchothBurgeretal.2012, author = {Schlosser, Felix and Schoth, Mario and Burger, Sven and Schmidt, Frank and Knorr, Andreas and Mukamel, Shaul and Richter, Marten}, title = {Coherent Nonlinear Spectroscopy with Spatiotemporally Controlled Fields}, booktitle = {CLEO/QELS}, publisher = {Optical Society of America}, doi = {10.1364/QELS.2012.QF3D.6}, pages = {QF3D.6}, year = {2012}, language = {en} } @inproceedings{SchlosserSchothHiremathetal.2012, author = {Schlosser, Felix and Schoth, Mario and Hiremath, Kirankumar and Burger, Sven and Schmidt, Frank and Knorr, Andreas and Mukamel, Shaul and Richter, Marten}, title = {Combining nanooptical fields and coherent spectroscopy on systems with delocalized excitons}, volume = {8260}, booktitle = {Proc. SPIE}, doi = {10.1117/12.906671}, pages = {82601V}, year = {2012}, language = {en} } @inproceedings{VaitlWinklerRichteretal.2024, author = {Vaitl, Lorenz and Winkler, Ludwig and Richter, Lorenz and Kessel, Pan}, title = {Fast and unified path gradient estimators for normalizing flows}, booktitle = {International Conference on Learning Representations 2024}, arxiv = {http://arxiv.org/abs/2403.15881}, year = {2024}, abstract = {Recent work shows that path gradient estimators for normalizing flows have lower variance compared to standard estimators for variational inference, resulting in improved training. However, they are often prohibitively more expensive from a computational point of view and cannot be applied to maximum likelihood train- ing in a scalable manner, which severely hinders their widespread adoption. In this work, we overcome these crucial limitations. Specifically, we propose a fast path gradient estimator which improves computational efficiency significantly and works for all normalizing flow architectures of practical relevance. We then show that this estimator can also be applied to maximum likelihood training for which it has a regularizing effect as it can take the form of a given target energy func- tion into account. We empirically establish its superior performance and reduced variance for several natural sciences applications.}, language = {en} } @inproceedings{WinklerRichterOpper2024, author = {Winkler, Ludwig and Richter, Lorenz and Opper, Manfred}, title = {Bridging discrete and continuous state spaces: Exploring the Ehrenfest process in time-continuous diffusion models}, volume = {235}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, arxiv = {http://arxiv.org/abs/2405.03549}, pages = {53017 -- 53038}, year = {2024}, abstract = {Generative modeling via stochastic processes has led to remarkable empirical results as well as to recent advances in their theoretical understanding. In principle, both space and time of the processes can be discrete or continuous. In this work, we study time-continuous Markov jump processes on discrete state spaces and investigate their correspondence to state-continuous diffusion processes given by SDEs. In particular, we revisit the Ehrenfest process, which converges to an Ornstein-Uhlenbeck process in the infinite state space limit. Likewise, we can show that the time-reversal of the Ehrenfest process converges to the time-reversed Ornstein-Uhlenbeck process. This observation bridges discrete and continuous state spaces and allows to carry over methods from one to the respective other setting. Additionally, we suggest an algorithm for training the time-reversal of Markov jump processes which relies on conditional expectations and can thus be directly related to denoising score matching. We demonstrate our methods in multiple convincing numerical experiments.}, language = {en} } @inproceedings{RiberaBorrellRichterSchuette2025, author = {Ribera Borrell, Enric and Richter, Lorenz and Sch{\"u}tte, Christof}, title = {Reinforcement Learning with Random Time Horizons}, volume = {267}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, arxiv = {http://arxiv.org/abs/2506.00962}, pages = {5101 -- 5123}, year = {2025}, language = {en} } @inproceedings{ZinkEkteraiMartinetal.2023, author = {Zink, Christof and Ekterai, Michael and Martin, Dominik and Clemens, William and Maennel, Angela and Mundinger, Konrad and Richter, Lorenz and Crump, Paul and Knigge, Andrea}, title = {Deep-learning-based visual inspection of facets and p-sides for efficient quality control of diode lasers}, volume = {12403}, booktitle = {High-Power Diode Laser Technology XXI}, publisher = {SPIE}, doi = {10.1117/12.2648691}, pages = {94 -- 112}, year = {2023}, abstract = {The optical inspection of the surfaces of diode lasers, especially the p-sides and facets, is an essential part of the quality control in the laser fabrication procedure. With reliable, fast, and flexible optical inspection processes, it is possible to identify and eliminate defects, accelerate device selection, reduce production costs, and shorten the cycle time for product development. Due to a vast range of rapidly changing designs, structures, and coatings, however, it is impossible to realize a practical inspection with conventional software. In this work, we therefore suggest a deep learning based defect detection algorithm that builds on a Faster Regional Convolutional Neural Network (Faster R-CNN) as a core component. While for related, more general object detection problems, the application of such models is straightforward, it turns out that our task exhibits some additional challenges. On the one hand, a sophisticated pre- and postprocessing of the data has to be deployed to make the application of the deep learning model feasible. On the other hand, we find that creating labeled training data is not a trivial task in our scenario, and one has to be extra careful with model evaluation. We can demonstrate in multiple empirical assessments that our algorithm can detect defects in diode lasers accurately and reliably in most cases. We analyze the results of our production-ready pipeline in detail, discuss its limitations and provide some proposals for further improvements.}, language = {en} } @inproceedings{RichterBerner2024, author = {Richter, Lorenz and Berner, Julius}, title = {Improved sampling via learned diffusions}, booktitle = {International Conference on Learning Representations 2024}, arxiv = {http://arxiv.org/abs/2307.01198}, year = {2024}, abstract = {Recently, a series of papers proposed deep learning-based approaches to sample from unnormalized target densities using controlled diffusion processes. In this work, we identify these approaches as special cases of the Schr{\"o}dinger bridge problem, seeking the most likely stochastic evolution between a given prior distribution and the specified target. We further generalize this framework by introducing a variational formulation based on divergences between path space measures of time-reversed diffusion processes. This abstract perspective leads to practical losses that can be optimized by gradient-based algorithms and includes previous objectives as special cases. At the same time, it allows us to consider divergences other than the reverse Kullback-Leibler divergence that is known to suffer from mode collapse. In particular, we propose the so-called log-variance loss, which exhibits favorable numerical properties and leads to significantly improved performance across all considered approaches.}, language = {en} } @inproceedings{BlessingBernerRichteretal.2025, author = {Blessing, Denis and Berner, Julius and Richter, Lorenz and Neumann, Gerhard}, title = {Underdamped Diffusion Bridges with Applications to Sampling}, booktitle = {13th International Conference on Learning Representations (ICLR 2025)}, arxiv = {http://arxiv.org/abs/2503.01006}, year = {2025}, abstract = {We provide a general framework for learning diffusion bridges that transport prior to target distributions. It includes existing diffusion models for generative modeling, but also underdamped versions with degenerate diffusion matrices, where the noise only acts in certain dimensions. Extending previous findings, our framework allows to rigorously show that score matching in the underdamped case is indeed equivalent to maximizing a lower bound on the likelihood. Motivated by superior convergence properties and compatibility with sophisticated numerical integration schemes of underdamped stochastic processes, we propose \emph{underdamped diffusion bridges}, where a general density evolution is learned rather than prescribed by a fixed noising process. We apply our method to the challenging task of sampling from unnormalized densities without access to samples from the target distribution. Across a diverse range of sampling problems, our approach demonstrates state-of-the-art performance, notably outperforming alternative methods, while requiring significantly fewer discretization steps and no hyperparameter tuning.}, language = {en} } @inproceedings{ChenRichterBerneretal.2025, author = {Chen, Junhua and Richter, Lorenz and Berner, Julius and Blessing, Denis and Neumann, Gerhard and Anandkumar, Anima}, title = {Sequential Controlled Langevin Diffusions}, booktitle = {13th International Conference on Learning Representations (ICLR 2025)}, arxiv = {http://arxiv.org/abs/2412.07081}, year = {2025}, abstract = {An effective approach for sampling from unnormalized densities is based on the idea of gradually transporting samples from an easy prior to the complicated target distribution. Two popular methods are (1) Sequential Monte Carlo (SMC), where the transport is performed through successive annealed densities via prescribed Markov chains and resampling steps, and (2) recently developed diffusion-based sampling methods, where a learned dynamical transport is used. Despite the common goal, both approaches have different, often complementary, advantages and drawbacks. The resampling steps in SMC allow focusing on promising regions of the space, often leading to robust performance. While the algorithm enjoys asymptotic guarantees, the lack of flexible, learnable transitions can lead to slow convergence. On the other hand, diffusion-based samplers are learned and can potentially better adapt themselves to the target at hand, yet often suffer from training instabilities. In this work, we present a principled framework for combining SMC with diffusion-based samplers by viewing both methods in continuous time and considering measures on path space. This culminates in the new Sequential Controlled Langevin Diffusion (SCLD) sampling method, which is able to utilize the benefits of both methods and reaches improved performance on multiple benchmark problems, in many cases using only 10\% of the training budget of previous diffusion-based samplers.}, language = {en} } @inproceedings{BernerRichterUllrich2024, author = {Berner, Julius and Richter, Lorenz and Ullrich, Karen}, title = {An optimal control perspective on diffusion-based generative modeling}, booktitle = {Transactions on Machine Learning Research}, year = {2024}, abstract = {We establish a connection between stochastic optimal control and generative models based on stochastic differential equations (SDEs) such as recently developed diffusion probabilistic models. In particular, we derive a Hamilton-Jacobi-Bellman equation that governs the evolution of the log-densities of the underlying SDE marginals. This perspective allows to transfer methods from optimal control theory to generative modeling. First, we show that the evidence lower bound is a direct consequence of the well-known verification theorem from control theory. Further, we develop a novel diffusion-based method for sampling from unnormalized densities -- a problem frequently occurring in statistics and computational sciences.}, language = {en} } @inproceedings{RichterBerner2022, author = {Richter, Lorenz and Berner, Julius}, title = {Robust SDE-Based Variational Formulations for Solving Linear PDEs via Deep Learning}, volume = {162}, booktitle = {Proceedings of the 39th International Conference on Machine Learning, PMLR}, pages = {18649 -- 18666}, year = {2022}, abstract = {The combination of Monte Carlo methods and deep learning has recently led to efficient algorithms for solving partial differential equations (PDEs) in high dimensions. Related learning problems are often stated as variational formulations based on associated stochastic differential equations (SDEs), which allow the minimization of corresponding losses using gradient-based optimization methods. In respective numerical implementations it is therefore crucial to rely on adequate gradient estimators that exhibit low variance in order to reach convergence accurately and swiftly. In this article, we rigorously investigate corresponding numerical aspects that appear in the context of linear Kolmogorov PDEs. In particular, we systematically compare existing deep learning approaches and provide theoretical explanations for their performances. Subsequently, we suggest novel methods that can be shown to be more robust both theoretically and numerically, leading to substantial performance improvements.}, language = {en} }