Research map / Probabilistic and scientific modeling / Variational and generative sampling
AIDE: An algorithm for measuring the accuracy of probabilistic inference algorithms
Marco Cusumano-Towner, Vikash K Mansinghka
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 AIDE with an SMC target and exact posterior gold standard | SMC inference in Bayesian linear regression · Bayesian linear regression | AIDE bias | No clear effect |
| Use AIDE with a variational-inference target and exact posterior gold standard | Variational inference · Bayesian linear regression | AIDE bias | No clear effect |
| Use the AIS-based meta-inference procedure for Metropolis-Hastings | Metropolis-Hastings · Bayesian linear regression | AIDE bias | Hurt |
| Use an approximate best-in-class SMC gold standard instead of the exact posterior gold standard | AIDE for HMM SMC inference · Hidden Markov model | estimated divergence | No clear effect |
| Increase the number of particles in the target SMC sampler | SMC · Hidden Markov model | estimated divergence bound | Improved |
| Use the optimal proposal instead of the prior proposal | SMC · Hidden Markov model | estimated divergence bound | Improved |
| Increase the number of target meta-inference runs M_TARGET | AIDE · Hidden Markov model | estimated divergence bound | Improved |
| Use AIDE rather than an expected-number-of-clusters probe | Inference evaluation · Dirichlet process mixture model | detection of inaccurate inference | Improved |
| Add rejuvenation kernels | SMC · Dirichlet process mixture model, galaxy velocity data | convergence | Improved |
Closest papers by meaning
- Variational Inference for Sequential Data with Future Likelihood Estimates (ICML 2020 · similarity 0.84)
- Statistical Inference with Unnormalized Discrete Models and Localized Homogeneous Divergences (JMLR 2017 · similarity 0.84)
- Measuring the reliability of MCMC inference with bidirectional Monte Carlo (NeurIPS 2016 · similarity 0.84)
- Asymptotics of Alpha-Divergence Variational Inference Algorithms with Exponential Families (NeurIPS 2024 · similarity 0.83)
- Prediction-Powered Adaptive Shrinkage Estimation (ICML 2025 · similarity 0.82)
- Generalized Variational Inference via Optimal Transport (AAAI 2024 · similarity 0.82)
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.
