Research map / Probabilistic and scientific modeling / Variational and generative sampling
Automatic Differentiation of Programs with Discrete Randomness
Gaurav Arya, Moritz Schauer, Frank Schäfer, Christopher Vincent Rackauckas
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use stochastic derivatives instead of score function estimator for binomial variable | gradient estimation · Bin(n,p) | estimator variance order: n^3 -> n | Improved |
| use stochastic triples instead of score function estimator (with or without control variate) | inhomogeneous random walk · random walk, f(x)=x^2 | gradient estimator variance | Improved |
| differentiate particle filter resampling step with smoothed stochastic derivatives instead of ignoring it | particle filter likelihood gradient · hidden Markov model, d=2 | bias vs Kalman filter derivative | Improved |
| use smoothed instead of unsmoothed stochastic derivatives for non-linear programs | stochastic derivative AD · Geo(p)^3 at p=0.01 | bias: <0.5% bias | No clear effect |
| switch particle filter AD from forward to reverse mode | particle filter · hidden Markov model | run time | Mixed |
| compare smoothed stochastic derivative variance to biased estimators in particle filter | particle filter · hidden Markov model | variance | Hurt |
Closest papers by meaning
- A mathematical model for automatic differentiation in machine learning (NeurIPS 2020 · similarity 0.88)
- Automatic Differentiation in Machine Learning: a Survey (JMLR 2018 · similarity 0.88)
- Storchastic: A Framework for General Stochastic Automatic Differentiation (NeurIPS 2021 · similarity 0.88)
- Randomized Automatic Differentiation (ICLR 2021 · similarity 0.87)
- Two-timescale Derivative Free Optimization for Performative Prediction with Markovian Data (ICML 2024 · similarity 0.84)
- Automatic Differentiation of Optimization Algorithms with Time-Varying Updates (ICML 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
