Success of Uncertainty-Aware Deep Models Depends on Data Manifold Geometry
For responsible decision making in safety-critical settings, machine learning models must effectively detect and process edge-case data. Although existing works show that predictive uncertainty is useful for these tasks, it is not evident from literature which uncertainty-aware models are best suited for a given dataset. Thus, we compare six uncertainty-aware deep learning models on a set of edge-case tasks: robustness to adversarial attacks as well as out-of-distribution and adversarial detection. We find that the geometry of the data sub-manifold is an important factor in determining the success of various models. Our finding suggests an interesting direction in the study of uncertainty-aware deep learning models.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingDeep LearningSimilar Papers 제목 키워드 기반
Learning a Kinodynamic Trajectory Manifold for Impact-Aware Compliant Catching of Fast-Moving Objects
Fast catching of free-flying objects is difficult because of short reaction time, impact uncertainty, and kinodynamic constraints. We use reinforcement learning in simulation to collect successful catching trajectories a…
Reinforcement LearningGaussian Process Manifold Interpolation for Probabilistic Atrial Activation Maps and Uncertain Conduction Velocity
In patients with atrial fibrillation, local activation time (LAT) maps are routinely used for characterising patient pathophysiology. The gradient of LAT maps can be used to calculate conduction velocity (CV), which dire…
Gaussian ProcessesAdaptive Manipulation Potential and Haptic Estimation for Tool-Mediated Interaction
Achieving human-level dexterity in contact-rich, tool-mediated manipulation remains a significant challenge due to visual occlusion and the underdetermined nature of haptic sensing. This paper introduces a parameterized …
The Causal Uncertainty Principle: Manifold Tearing and the Topological Limits of Counterfactual Interventions
Judea Pearl's do-calculus provides a foundation for causal inference, but its translation to continuous generative models remains fraught with geometric challenges. We establish the fundamental limits of such interventio…
Causal InferenceManifoldMind: Dynamic Hyperbolic Reasoning for Trustworthy Recommendations
We introduce ManifoldMind, a probabilistic geometric recommender system for exploratory reasoning over semantic hierarchies in hyperbolic space. Unlike prior methods with fixed curvature and rigid embeddings, ManifoldMin…