Research map / Probabilistic and scientific modeling / Variational and generative sampling
Autoconj: Recognizing and Exploiting Conjugacy Without a Domain-Specific Language
Matthew D. Hoffman, Matthew J Johnson, Dustin Tran
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 |
|---|---|---|---|
| Run Autoconj CAVI with TensorFlow on 1 GPU instead of NumPy on 1 CPU | Autoconj CAVI · Mixture of Gaussians, 500 VI iterations | Runtime (s): 62.9 -> 4.3 | Improved |
| Use TensorFlow on 1 CPU instead of NumPy on 1 CPU | Autoconj CAVI · Mixture of Gaussians, 500 VI iterations | Runtime (s): 62.9 -> 75.9 | Hurt |
| Run TensorFlow CAVI on 6 CPUs instead of 1 CPU | Autoconj CAVI · Mixture of Gaussians, 500 VI iterations | Runtime (s): 75.9 -> 19.7 | Improved |
| Run TensorFlow CAVI on 1 GPU instead of 1 CPU | Autoconj CAVI · Mixture of Gaussians, 500 VI iterations | Runtime (s): 75.9 -> 4.3 | Improved |
Closest papers by meaning
- On the Generative Utility of Cyclic Conditionals (NeurIPS 2021 · similarity 0.84)
- Exact Bayesian Inference on Discrete Models via Probability Generating Functions: A Probabilistic Programming Approach (NeurIPS 2023 · similarity 0.84)
- Exploiting LLMs for Automatic Hypothesis Assessment via a Logit-Based Calibrated Prior (NeurIPS 2025 · similarity 0.82)
- Probabilistic Conformal Prediction with Approximate Conditional Validity (ICLR 2025 · similarity 0.82)
- Testing Causal Models with Hidden Variables in Polynomial Delay via Conditional Independencies (AAAI 2025 · similarity 0.82)
- SymDiff: Equivariant Diffusion via Stochastic Symmetrisation (ICLR 2025 · 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.
