the archive

#automatic differentiation

5 results

stat.CO2019

Functional probabilistic programming for scalable Bayesian modelling

Jonathan Law, Darren Wilkinson

The paper presents a functional probabilistic programming approach that lets users define Bayesian models in a domain-specific language and perform inference with generic algorithm…

#probabilistic programming#bayesian inference#functional programming#hamiltonian monte carlo

cs.LG2019

SVGD: A Virtual Gradients Descent Method for Stochastic Optimization

Zheng Li, Shi Shu

The paper introduces Stochastic Virtual Gradient Descent (SVGD), a memory‑efficient stochastic optimization algorithm that defines gradients via computational graphs and automatic…

#stochastic optimization#gradient descent#automatic differentiation#computational graph

stat.ML2019

Posterior inference unchained with EL_2O

Uros Seljak, Byeonghee Yu

The paper proposes EL_2O, a noise‑free optimization of the L2 distance between an approximate log posterior and the true un‑normalized log posterior, offering faster and more accur…

#posterior inference#variational inference#mcmc#automatic differentiation

math.ST2019

A Higher-Order Swiss Army Infinitesimal Jackknife

Ryan Giordano, Michael I. Jordan, Tamara Broderick

The paper introduces higher-order infinitesimal jackknife (HOIJ) methods that use Taylor expansions to approximate cross‑validation and bootstrap re‑weightings, providing recursive…

#cross-validation#bootstrap#infinitesimal jackknife#higher-order approximation

math.NA2019

Deep Neural Network Approach to Forward-Inverse Problems

Hyeontae Jo, Hwijae Son, Hyung Ju Hwang +1

The paper introduces a feed‑forward deep neural network framework that simultaneously approximates solutions of differential equations and identifies model parameters from data, pr…

#differential equations#neural networks#inverse problems#physics-informed learning