43 citations · 64 across the 10 of their papers we have counts for
Showing 2026 · stat.MLShow all
2 papers · 2 filters
stat.ML2026
Bayesian Neural Networks via Dirichlet Process Priors on the Data-Generating Distribution for Randomized Value Functions in Deep Reinforcement Learning
Sumit Vashishtha
Bayesian neural networks (BNNs) offer a principled framework for quantifying epistemic uncertainty. However, standard weight-space priors yield complex, high-dimensional neural net…
stat.ML2026
Dimension-Free PAC-Bayes Generalization for Deep Neural Networks via Dirichlet Processes
Sumit Vashishtha
Classical PAC-Bayesian generalization theory places prior distributions over Euclidean parameter space , causing relative entropy to scale with network dim…