Research map / Probabilistic and scientific modeling / Variational and generative sampling
Inference by Reparameterization in Neural Population Codes
Rajkumar Vasudeva Raju, Zachary Pitkow
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 |
|---|---|---|---|
| increase timescale ratio gamma = tau_slow/tau_fast relative to reference gamma0 = 10 | recurrent neural population network · Gaussian graphical models, tree model | relative MSE of inferred parameters | Improved |
| use the neural network instead of loopy belief propagation | neural reparameterization network · chains, single loops, grids up to 20x20, dense graphs up to 25 variables | accuracy of pseudomarginal means and covariances | No clear effect |
| add independent Gaussian noise of 0.1 std of each signal | neural network inference · 5x5 square grid | match of inferred expectation parameters | No clear effect |
| increase neurons per parameter from one to five | neural network inference · 5x5 square grid with noise | inference performance | Improved |
Closest papers by meaning
- A probabilistic population code based on neural samples (NeurIPS 2018 · similarity 0.90)
- Brain-like Variational Inference (NeurIPS 2025 · similarity 0.86)
- Divide-and-Conquer Predictive Coding: a structured Bayesian inference algorithm (NeurIPS 2024 · similarity 0.86)
- Complex priors and flexible inference in recurrent circuits with dendritic nonlinearities (ICLR 2024 · similarity 0.86)
- Neural Conditional Probability for Uncertainty Quantification (NeurIPS 2024 · similarity 0.86)
- Neural Network Approximators for Marginal MAP in Probabilistic Circuits (AAAI 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.
