4 citations · 10 across the 14 of their papers we have counts for
12 papers · 1 filter
Training Mixed-Monotone Neural Networks for Verification Without Set Propagation
Jonas Fingerhut, Lukas Koller, Matthias Althoff
Most formal verification approaches for neural networks conservatively enclose the output set of the neural network. However, computing a tight output enclosure is in general compu…
The Misery of Mechanistic Interpretability: A Formal Perspective
Tobias Ladner, Matthias Althoff
Mechanistic interpretability has become the dominant lens for understanding frontier language models, as their inner workings are complex and inherently black boxes. To gain insigh…
Provably Explaining Neural Additive Models
Shahaf Bassan, Yizhak Yisrael Elboher, Tobias Ladner +4
Despite significant progress in post-hoc explanation methods for neural networks, many remain heuristic and lack provable guarantees. A key approach for obtaining explanations with…
BSAT: B-Spline Adaptive Tokenizer for Long-Term Time Series Forecasting
Maximilian Reinwardt, Michael Eichelbeck, Matthias Althoff
Long-term time series forecasting using transformers is hampered by the quadratic complexity of self-attention and the rigidity of uniform patching, which may be misaligned with th…
Improving Stochastic Action-Constrained Reinforcement Learning via Truncated Distributions
Roland Stolz, Michael Eichelbeck, Matthias Althoff
In reinforcement learning (RL), it is often advantageous to consider additional constraints on the action space to ensure safety or action relevance. Existing work on such action-c…
Zono-Conformal Prediction: Zonotope-Based Uncertainty Quantification for Regression and Classification Tasks
Laura Lützow, Michael Eichelbeck, Mykel J. Kochenderfer +1
Conformal prediction is a popular uncertainty quantification method that augments a base predictor to return sets of predictions with statistically valid coverage guarantees. Howev…
Explaining, Fast and Slow: Abstraction and Refinement of Provable Explanations
Shahaf Bassan, Yizhak Yisrael Elboher, Tobias Ladner +2
Despite significant advancements in post-hoc explainability techniques for neural networks, many current methods rely on heuristics and do not provide formally provable guarantees…
PyTupli: A Scalable Infrastructure for Collaborative Offline Reinforcement Learning Projects
Hannah Markgraf, Michael Eichelbeck, Daria Cappey +3
Offline reinforcement learning (RL) has gained traction as a powerful paradigm for learning control policies from pre-collected data, eliminating the need for costly or risky onlin…
Out of the Shadows: Exploring a Latent Space for Neural Network Verification
Lukas Koller, Tobias Ladner, Matthias Althoff
Neural networks are ubiquitous. However, they are often sensitive to small input changes. Hence, to prevent unexpected behavior in safety-critical applications, their formal verifi…
Training Verifiably Robust Agents Using Set-Based Reinforcement Learning
Manuel Wendl, Lukas Koller, Tobias Ladner +1
Reinforcement learning policies parametrized by deep neural networks have achieved strong performance for continuous control, yet even small input perturbations may lead to unpredi…
Formal Verification of Graph Convolutional Networks with Uncertain Node Features and Uncertain Graph Structure
Tobias Ladner, Michael Eichelbeck, Matthias Althoff
Graph neural networks are becoming increasingly popular in the field of machine learning due to their unique ability to process data structured in graphs. They have also been appli…
Set-Based Training for Neural Network Verification
Lukas Koller, Tobias Ladner, Matthias Althoff
Neural networks are vulnerable to adversarial attacks, i.e., small input perturbations can significantly affect the outputs of a neural network. Therefore, to ensure safety of neur…