81 citations · 175 across the 16 of their papers we have counts for
19 papers
Stein Variational Distributional Reinforcement Learning: Score-Guided Particles for Multivariate Return Distributions
Manuel Haußmann, Melih Kandemir
Decisions that weigh several reward signals against each other require the joint distribution of the return vector. Categorical critics scale exponentially in the reward dimension,…
Fitted Q-Iteration with Continuous Actions and Adaptive Data: Smoothed Coverage and Minimax Rates
Manuel Haußmann, Manuel Haussmann, Mustafa Mert Çelikok +1
Fitted Q-iteration (FQI) is well understood when the data come from a fixed distribution and the action set is finite, whereas value-based continuous control collects its data adap…
Uncertainty in Physics and AI: Taxonomy, Quantification, and Validation
Manuel Haußmann, Ramon Winterhalder, Maria Ubiali
Reliable uncertainty quantification is essential for the use of machine learning in physics, where scientific discoveries depend on validated probabilistic statements. We provide a…
Distributional Active Inference
Abdullah Akgül, Gulcin Baykal, Manuel Haußmann +2
Optimal control of complex environments with robotic systems faces two complementary and intertwined challenges: efficient organization of sensory state information and far-sighted…
ObjectRL: An Object-Oriented Reinforcement Learning Codebase
Gulcin Baykal, Abdullah Akgül, Manuel Haussmann +4
ObjectRL is an open-source Python codebase for deep reinforcement learning (RL), designed for research-oriented prototyping with minimal programming effort. Unlike existing codebas…
Adaptive Ensemble Aggregation for Actor-Critics
Nicklas Werge, Yi-Shan Wu, Manuel Haussmann +2
Ensembles are ubiquitous in off-policy actor-critic learning, yet their efficacy depends critically on how they are aggregated. Current methods typically rely on static rules or ta…
Deep Actor-Critics with Tight Risk Certificates
Bahareh Tasdighi, Manuel Haussmann, Yi-Shan Wu +2
Deep actor-critic algorithms have reached a level where they influence everyday life. They are a driving force behind continual improvement of large language models through user fe…
Overcoming Non-stationary Dynamics with Evidential Proximal Policy Optimization
Abdullah Akgül, Gulcin Baykal, Manuel Haußmann +1
Continuous control of non-stationary environments is a major challenge for deep reinforcement learning algorithms. The time-dependency of the state transition dynamics aggravates t…
Accurate Surrogate Amplitudes with Calibrated Uncertainties
Henning Bahl, Nina Elmer, Luigi Favaro +3
Neural networks for LHC physics have to be accurate, reliable, and controlled. Using neural surrogates for the prediction of loop amplitudes as a use case, we first show how activa…
Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning
Abdullah Akgül, Manuel Haußmann, Melih Kandemir
Current approaches to model-based offline reinforcement learning often incorporate uncertainty-based reward penalization to address the distributional shift problem. These approach…
Practical Equivariances via Relational Conditional Neural Processes
Daolang Huang, Manuel Haussmann, Ulpu Remes +5
Conditional Neural Processes (CNPs) are a class of metalearning models popular for combining the runtime efficiency of amortized inference with reliable uncertainty quantification.…
Evidential Turing Processes
Melih Kandemir, Abdullah Akgül, Manuel Haussmann +1
A probabilistic classifier with reliable predictive uncertainties i) fits successfully to the target domain data, ii) provides calibrated class probabilities in difficult regions o…
Understanding Event-Generation Networks via Uncertainties
Marco Bellagente, Manuel Haußmann, Michel Luchmann +1
Following the growing success of generative neural networks in LHC simulations, the crucial question is how to control the networks and assign uncertainties to their event output.…
Learning Partially Known Stochastic Dynamics with Empirical PAC Bayes
Manuel Haussmann, Sebastian Gerwinn, Andreas Look +2
Neural Stochastic Differential Equations model a dynamical environment with neural nets assigned to their drift and diffusion terms. The high expressive power of their nonlinearity…
Deep Active Learning with Adaptive Acquisition
Manuel Haussmann, Fred A. Hamprecht, Melih Kandemir
Model selection is treated as a standard performance boosting step in many machine learning applications. Once all other properties of a learning problem are fixed, the model is se…
Bayesian Evidential Deep Learning with PAC Regularization
Manuel Haussmann, Sebastian Gerwinn, Melih Kandemir
We propose a novel method for closed-form predictive distribution modeling with neural nets. In quantifying prediction uncertainty, we build on Evidential Deep Learning, which has…
Deep-Learning Jets with Uncertainties and More
Sven Bollweg, Manuel Haussmann, Gregor Kasieczka +3
Bayesian neural networks allow us to keep track of uncertainties, for example in top tagging, by learning a tagger output together with an error band. We illustrate the main featur…
LeMoNADe: Learned Motif and Neuronal Assembly Detection in calcium imaging videos
Elke Kirschbaum, Manuel Haußmann, Steffen Wolf +6
Neuronal assemblies, loosely defined as subsets of neurons with reoccurring spatio-temporally coordinated activation patterns, or "motifs", are thought to be building blocks of neu…
Sampling-Free Variational Inference of Bayesian Neural Networks by Variance Backpropagation
Manuel Haussmann, Fred A. Hamprecht, Melih Kandemir
We propose a new Bayesian Neural Net formulation that affords variational inference for which the evidence lower bound is analytically tractable subject to a tight approximation. W…