Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Meta-Learning Theory-Informed Inductive Biases using Deep Kernel Gaussian Processes
Bahti Zakirov, Gasper Tkacik
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 meta-learned theory-informed kernel instead of plain RBF GP | deep kernel GP · Mouse RGC responses (86 neurons) | test Pearson correlation: Wilcoxon p=6.14e-03 at N=64, p=9.37e-05 at N=1452 | Improved |
| replace meta-learned feature extractor with random weights (ablation) | Theory-Informed Kernel · Mouse RGC responses (86 neurons) | test Pearson correlation: median +0.049 at N=512 | Improved |
| meta-train on theory-derived efficient-coding tasks instead of generic natural-image PCA tasks (ablation) | Theory-Informed Kernel · Mouse RGC responses (86 neurons) | test Pearson correlation: Wilcoxon p=5.04e-03 at N=128, p=2.47e-01 at N=1452 | Improved |
| add task-adaptive linear heads (ablation) | Theory-Informed Kernel · Mouse RGC responses (86 neurons) | test Pearson correlation: Wilcoxon p=2.77e-10 at N=32 | Improved |
| add meta-learned deep feature extractor on top of identity (linear heads on raw pixels) (ablation) | Theory-Informed Kernel · Mouse RGC responses (86 neurons) | test Pearson correlation: Wilcoxon p=6.67e-09 at N=1024 | Improved |
| use theory-informed kernel instead of LN model at very low data | Theory-Informed Kernel · Mouse RGC responses (N<=8 and N<16) | test Pearson correlation | Hurt |
| use pretrained ResNet-18 (ImageNet or SimCLR) frozen features with fitted heads (transfer learning) | RGC response prediction · Mouse RGC responses (86 neurons) | test Pearson correlation | Hurt |
| use theory-informed kernel instead of RBF GP for uncertainty | deep kernel GP · Mouse RGC responses (86 neurons) | NLPD | Improved |
Closest papers by meaning
- MARS: Meta-learning as Score Matching in the Function Space (ICLR 2023 · similarity 0.87)
- A contrastive rule for meta-learning (NeurIPS 2022 · similarity 0.87)
- Meta-Dynamical State Space Models for Integrative Neural Data Analysis (ICLR 2025 · similarity 0.85)
- Modeling Dynamic Neural Activity by combining Naturalistic Video Stimuli and Stimulus-independent Latent Factors (NeurIPS 2025 · similarity 0.85)
- A Meta-Learning Approach to Bayesian Causal Discovery (ICLR 2025 · similarity 0.85)
- Inverse decision-making using neural amortized Bayesian actors (ICLR 2025 · 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.
