Fast and correct gradient-based optimisation for probabilistic programming via smoothing
DOI10.1007/978-3-031-30044-8_18zbMATH Open1541.68094MaRDI QIDQ6535252FDOQ6535252
Authors: Basim Khajwal, Chih-Hao Luke Ong, Dominik Wagner 
Publication date: 24 November 2023
Recommendations
variational inferencetype systemsprobabilistic programmingvalue semanticsreparameterisation gradient
Theory of programming languages (68N15) Applications of mathematical programming (90C90) Stochastic programming (90C15) Mathematical aspects of software engineering (specification, verification, metrics, requirements, etc.) (68N30) Other programming paradigms (object-oriented, sequential, concurrent, automatic, etc.) (68N19)
Cites Work
- Machine learning. A probabilistic perspective
- Gradient Convergence in Gradient methods with Errors
- Comparative smootheology
- Probability theory. A comprehensive course
- Discontinuous Optimization by Smoothing
- Borel structures for function spaces
- Title not available (Why is that?)
- Probabilistic coherence spaces are fully abstract for probabilistic PCF
- Convex optimization algorithms
- A Convenient Category for Higher-Order Probability Theory
- Semantics for probabilistic programming: higher-order functions, continuous distributions, and soft constraints
- Monte Carlo gradient estimation in machine learning
- A lambda-calculus foundation for universal probabilistic programming
- Commutative semantics for probabilistic programming
- Densities of almost surely terminating probabilistic programs are differentiable almost everywhere
- A provably correct sampler for probabilistic programs
This page was built for publication: Fast and correct gradient-based optimisation for probabilistic programming via smoothing
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6535252)
