paper-with-me

홈 › Papers

Success of Uncertainty-Aware Deep Models Depends on Data Manifold Geometry

2022-08-02 · Mark Penrod, Harrison Termotto, Varshini Reddy, Jiayu Yao, Finale Doshi-Velez, Weiwei Pan

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.

📄 PDF Abstract BibTeX arXiv:2208.01705

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingDeep Learning

Similar Papers 제목 키워드 기반

Learning a Kinodynamic Trajectory Manifold for Impact-Aware Compliant Catching of Fast-Moving Objects

2026-05-27 · Guorui Pei, Mengshi Zhang, Xi Chen, Jinsong Wu 외 arxiv

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 Learning

Gaussian Process Manifold Interpolation for Probabilistic Atrial Activation Maps and Uncertain Conduction Velocity

2020-04-22 · Sam Coveney, Cesare Corrado, Caroline H Roney, Daniel O'Hare 외

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 Processes

Adaptive Manipulation Potential and Haptic Estimation for Tool-Mediated Interaction

2026-03-11 · Lin Yang, Anirvan Dutta, Yuan Ji, Yanxin Zhou 외 arxiv

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

2026-03-18 · Rui Wu, Hong Xie, Yongjun Li arxiv

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 Inference

ManifoldMind: Dynamic Hyperbolic Reasoning for Trustworthy Recommendations

2025-07-02 · Anoushka Harit, Zhongtian Sun, Suncica Hadzidedic arxiv

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…