Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
2
0
3
2
Student's t likelihood significantly boosts Bayesian neural network performance, outperforming Gaussian distributions across diverse datasets and architectures.
Sampling parallelism unlocks faster Bayesian learning by strategically distributing sample evaluations across GPUs, achieving near-perfect scaling and boosting augmentation diversity for quicker convergence.