#variational inference
8 papers match
Rethinking Likelihood distributions: Student's t Likelihood Boosts Bayesian Neural Network Performance
Pei-Hsuan Hsia, Lars H. Heyen, Arvid Weyrauch +4
The paper investigates using a Student's t likelihood instead of a Gaussian in Bayesian neural networks and finds it improves predictive performance and sometimes reduces training…
Variational Inference for Bird's Eye View Segmentation in Autonomous Driving
Jingyue Shi, Huaicheng Li, Junhui Zhao +1
The paper introduces a transformer-based variational flow network that uses a conditional variational autoencoder and normalizing flows to fuse multiple camera views into accurate…
Indirect Variational Inference: Applications to Earnings Dynamics
Neele Balke, Stephane Bonhomme, Thibaut Lamadon
The paper evaluates variational inference for latent-variable earnings dynamics models and proposes indirect variational inference (IVI) to correct bias from restrictive variationa…
Variational Mixture of Graph Neural Experts for Alzheimer's Disease Recognition across Frequency Bands in EEG Brain Networks
Jun-En Ding, Anna Zilverstand, Shihao Yang +2
The paper introduces VMoGE, a variational mixture-of-experts model that uses graph neural networks to analyze EEG connectivity across multiple frequency bands for distinguishing Al…
PiVoT: A Variational Solution for Real-time Large-scale Multi-object Detection and Tracking under Heavy Clutter
Runze Gan, Qing Li, Simon J. Godsill +2
PiVoT is a training‑free variational inference framework that jointly detects and tracks many objects in noisy radar point clouds, handling heavy clutter, Doppler measurements, and…
Variational Inference for Evidential Deep Learning
Jiawei Tang, Xinyan Du, Hui Liu +2
The paper introduces VI-EDL, a variational inference framework for evidential deep learning that controls evidence growth and provides theoretical guarantees for uncertainty estima…