1 citations · 1 across the 7 of their papers we have counts for
5 papers · 1 filter
Continuous and Differentiable Neural Network Representations of the Surfzone Sea-Surface from Lidar Point Clouds
David R. Culver, Matthias Morzfeld, Falk Feddersen
Ocean waves are often analyzed via sea-surface observations. Multi-beam scanning lidar enables two-dimensional measurements of the water surface via sequenced point clouds…
Certification-Enhanced Generalization Bounds
Leo Elmecker-Plakolm, Matthew Wicker
We investigate the use of formal methods to provide tight and sound generalization bounds for learning algorithms. By casting the traditional notion of algorithmic stability as a s…
Hybrid Robustness Verification for Spatio-Temporal Neural Networks
Sherwin Varghese, Matthew Wicker, Alessio Lomuscio
With AI increasingly deployed in safety-critical systems, providing formal robustness guarantees for the underlying models is essential. Existing verification methods either rely o…
SafeAdapt: Provably Safe Policy Updates in Deep Reinforcement Learning
Maksim Anisimov, Francesco Belardinelli, Matthew Wicker
Safety guarantees are a prerequisite to the deployment of reinforcement learning (RL) agents in safety-critical tasks. Often, deployment environments exhibit non-stationary dynamic…
Variational Routing: A Scalable Bayesian Framework for Calibrated Mixture-of-Experts Transformers
Albus Yizhuo Li, Matthew Wicker
Foundation models are increasingly being deployed in contexts where understanding the uncertainty of their outputs is critical to ensuring responsible deployment. While Bayesian me…