Research map / Probabilistic and scientific modeling / Variational and generative sampling
Learning Invariances using the Marginal Likelihood
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Add learned rotational invariance | Invariant GP · Odds-vs-even MNIST with partial rotations | test error | Helped |
| Add learned rotational invariance | Invariant GP · Odds-vs-even MNIST with partial rotations | marginal likelihood bound | Helped |
| Add learned affine or local-deformation invariance instead of using the RBF kernel | Gaussian-process classifier · MNIST | test error | Helped |
| Use rotational invariance only instead of affine or local-deformation invariance (ablation) | Invariant GP · MNIST | test error | Mixed |
| Use learned affine invariance | Gaussian-process classifier · Rotated MNIST | test error | Helped |
| Use learned rotation bounds instead of fixed rotational invariance (ablation) | Invariant GP · Rotated MNIST | test error | Hurt |
| Learn all affine transformation parameters instead of fixing the transformation (ablation) | Invariant GP · Rotated MNIST | test error | Hurt |
| Fix the rotational invariance instead of learning transformation parameters (ablation) | Invariant GP · Rotated MNIST | test error | Helped |
| Learn the rotation bound when the true rotation range is 180 degrees (ablation) | Invariant GP · Odds-vs-even MNIST with rotations up to 180 degrees | recovery of rotation range | Hurt |
Closest papers by meaning
- Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations (NeurIPS 2022 · similarity 0.90)
- Automatic Data Augmentation via Invariance-Constrained Learning (ICML 2023 · similarity 0.89)
- Learning Invariances in Neural Networks from Training Data (NeurIPS 2020 · similarity 0.89)
- On the detrimental effect of invariances in the likelihood for variational inference (NeurIPS 2022 · similarity 0.89)
- Learning Conditional Invariances through Non-Commutativity (ICLR 2024 · similarity 0.87)
- The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensing (NeurIPS 2024 · similarity 0.86)
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.