Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Loss function based second-order Jensen inequality and its application to particle variational inference
Futoshi Futami, Tomoharu Iwata, Naonori Ueda, Issei Sato, Masashi Sugiyama
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 |
|---|---|---|---|
| Optimize the PAC-Bayesian bound using loss-variance repulsion (VAR) | Neural-network Thompson sampling · Contextual bandit real-data tasks | cumulative regret | Improved |
| Use VAR instead of f-SVGD | Neural-network regression · UCI regression datasets | regression performance | No clear effect |
| Use VAR instead of f-SVGD | Neural-network classification · MNIST | classification performance | No clear effect |
| Use VAR instead of f-SVGD | ResNet-32 ensemble · CIFAR-10 | classification performance | No clear effect |
| Optimize predictive variance in the objective (PAC²_E) | Neural-network regression · UCI regression datasets | regression performance | Hurt |
| Use VAR or f-SVGD instead of MAP estimation | Neural-network classifiers · MNIST and CIFAR-10 out-of-distribution attack samples | robustness | Improved |
Closest papers by meaning
- Understanding and Accelerating Particle-Based Variational Inference (ICML 2019 · similarity 0.89)
- To discretize continually: Mean shift interacting particle systems for Bayesian inference (NeurIPS 2026 · similarity 0.87)
- Variational Particle Approximations (JMLR 2017 · similarity 0.87)
- Particle Semi-Implicit Variational Inference (NeurIPS 2024 · similarity 0.87)
- Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians (ICML 2024 · similarity 0.87)
- GAD-PVI: A General Accelerated Dynamic-Weight Particle-Based Variational Inference Framework (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.
