Author

Sumit Vashishtha

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Bayesian Neural Networks via Dirichlet Process Priors on the Data-Generating Distribution for Randomized Value Functions in Deep Reinforcement Learning

Bayesian neural networks (BNNs) offer a principled framework for quantifying epistemic uncertainty. However, standard weight-space priors yield complex, high-dimensional neural network posteriors that are computationally prohibitive to sample from, and popular approximate inference schemes often fail to capture epistem...

Sumit Vashishtha · 1 citation

#machine learning Preprint Oct 2026

Dimension-Free PAC-Bayes Generalization for Deep Neural Networks via Dirichlet Processes

Classical PAC-Bayesian generalization theory places prior distributions over Euclidean parameter space $\Theta \subseteq \mathbb{R}^D$, causing relative entropy to scale with network dimension $D$. For modern overparameterized neural networks where $D \gg n$, this parameter-counting dependency yields vacuous generaliza...

Sumit Vashishtha · 0 citations