Research map / Probabilistic and scientific modeling / Variational and generative sampling
Unsupervised Risk Estimation Using Only Conditional Independence Structure
Jacob Steinhardt, Percy Liang
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 tensor decomposition followed by L-BFGS to estimate test risk from unlabeled samples | Unsupervised risk estimation · Modified MNIST across distortion a | risk estimation accuracy | Improved |
| Adapt the seed model using unlabeled target-domain data | Logistic regression on modified MNIST · Domain adaptation across distortion a, 10,000 training and 10,000 test examples | risk | Mixed |
| Use only 300 labeled examples to obtain the seed model, then adapt with unlabeled data | Logistic regression on modified MNIST · Domain adaptation across distortion λ, 300 training and 10,000 test examples | risk | Mixed |
| Add L-BFGS refinement after tensor initialization (ablation) | Tensor risk estimator · Modified MNIST across distortion a | risk estimation accuracy | Improved |
Closest papers by meaning
- Arbitrary Conditional Distributions with Energy (NeurIPS 2021 · similarity 0.87)
- Model-Powered Conditional Independence Test (NeurIPS 2017 · similarity 0.86)
- Distributionally Robust Local Non-parametric Conditional Estimation (NeurIPS 2020 · similarity 0.86)
- On the Provable Advantage of Unsupervised Pretraining (ICLR 2024 · similarity 0.85)
- Kernel conditional tests from learning-theoretic bounds (NeurIPS 2025 · similarity 0.85)
- Neural Conditional Probability for Uncertainty Quantification (NeurIPS 2024 · similarity 0.84)
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.
