Research map / Probabilistic and scientific modeling / Variational and generative sampling
Amortized and online variational inference
Amortizes variational inference across tasks, filtering and undirected models.
59 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Variational and generative sampling, keyword cluster “variational inference · vi · lower”
State History Tried Checklist Preprints Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
5 papers in 2023–24 and 12 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 1.2% to 2.4%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2016 · Neural Variational Inference for Text Processing (ICML 2016 · 215 citations)
- 2017 · Autoencoding Variational Inference For Topic Models (ICLR 2017 · 143 citations)
- 2018 · Iterative Amortized Inference (ICML 2018 · 33 citations)
- 2019 · Variational Denoising Network: Toward Blind Noise Modeling and Removal (NeurIPS 2019 · 211 citations)
- 2020 · Empirical Bayes Transductive Meta-Learning with Synthetic Gradients (ICLR 2020 · 81 citations)
- 2021 · Online Variational Filtering and Parameter Learning (NeurIPS 2021 · 1 citation)
- 2022 · A Deep Variational Approach to Clustering Survival Data (ICLR 2022 · 8 citations)
- 2023 · Variational Open-Domain Question Answering (ICML 2023 · 3 citations)
- 2024 · Sharpness-Aware Minimization Activates the Interactive Teaching's Understanding and Optimization (NeurIPS 2024 · 1 citation)
- 2025 · Synonymous Variational Inference for Perceptual Image Compression (ICML 2025 · 1 citation)
- 2026 · Variational Speculative Decoding: Rethinking Draft Training from Token Likelihood to Sequence Acceptance (ICML 2026 · 0 citations)
Earliest papers here
- Neural Variational Inference for Text Processing (ICML 2016 · 215 citations)
- Scaling Factorial Hidden Markov Models: Stochastic Variational Inference without Messages (NeurIPS 2016 · 8 citations)
- Iterative Refinement of the Approximate Posterior for Directed Belief Networks (NeurIPS 2016 · 3 citations)
What has been tried
47 papers here report 441 measured changes (a component added, removed or swapped, compared with a baseline): helped 66%, no clear effect 10%, hurt 19%, mixed 5%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Increase reconstructed samples during training from M=1 to M=5 | CLIC2020, DIV2K, Kodak · DISTS | Helped | Synonymous Variational Inference for Perceptual Image Compression (ICML 2025 · 1 citation) | |
| Use Poisson rather than Gaussian latents | van Hateren 16 × 16 patches · sparsity (proportion of zeros) | 0% -> 77% | Helped | Brain-like Variational Inference (NeurIPS 2025 · 0 citations) |
| Use an informative prior instead of a uniform prior | AAV and GFP · Black-box optimization performance | Helped | Variational Search Distributions (ICLR 2025 · 0 citations) | |
| Add g-formula confounding adjustment to VCIP | Tumor simulation, γ = 4, τ = 2 · GRP | 0.791 ± 0.334 -> 0.944 ± 0.091 | Helped | Variational Counterfactual Intervention Planning to Achieve Target Outcomes (ICML 2025) |
What reviewers will expect
Datasets and baselines named in the 6 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- MNIST · 2 of 6 papers
Recent preprints
Loading recent arXiv preprints…
Use it
Download BibTeX of 33 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Variational inference theory and gradients (89 papers)
- Annealing and divergence-based variational objectives (79 papers)
- Variational methods for sequence models (40 papers)
Elsewhere in the topic
- Likelihood-free and graphical model estimation (161 papers)
- Flow matching and flow sampling (144 papers)
- Posterior sampling with diffusion guidance (137 papers)
- Score-based generative modeling analysis (128 papers)
- Structured latent VAEs (125 papers)
- Exact inference for probabilistic programs (103 papers)
- Disentangled and discrete latent models (92 papers)
- Latent variable marginalization and estimators (91 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).