Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Excess Risk Bounds for the Bayes Risk using Variational Inference in Latent Gaussian Models
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 |
|---|---|---|---|
| Use collapsed approximation q*_2Bi (independent expectation RCLM) instead of standard sparse-GP q*_2A objective for CTM (ablation) | correlated topic model (CTM) on artificial data · Artificial data (CTM), cumulative test loss | cumulative test log loss under r2Bay | Mixed |
| Use direct loss minimization objective (q*_2D) instead of variational objective (ablation) | correlated topic model (CTM) · Artificial data (CTM), cumulative test loss | cumulative test log loss under r2Bay | Helped |
| Use q*_2A (standard sparse GP variational objective) for CTM training (ablation) | correlated topic model (CTM) · Artificial data (CTM), cumulative test loss | cumulative test log loss under r2Bay | Hurt |
| Add a small variance (epsilon-inflation) to point estimates so they can be compared in risk bounds | Bayesian predictor risk bound for LGM · theoretical bound | excess risk bound | Helped |
Closest papers by meaning
- Variational Bayes on Monte Carlo Steroids (NeurIPS 2016 · similarity 0.91)
- Logistic Variational Bayes Revisited (ICML 2024 · similarity 0.89)
- Importance Weighted Hierarchical Variational Inference (NeurIPS 2019 · similarity 0.89)
- New Bounds for Sparse Variational Gaussian Processes (ICML 2025 · similarity 0.88)
- Sparse Variational Student-t Processes (AAAI 2024 · similarity 0.88)
- Amortized Structured Stochastic Variational Inference for Gaussian Process Latent Variable Models (NeurIPS 2026 · similarity 0.88)
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.