Research map / Optimization / Optimizers
Analytically Tractable Hidden-States Inference in Bayesian Neural Networks
Luong-Ha Nguyen, James-A. Goulet
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 |
|---|---|---|---|
| apply TAGI hidden-state inference on the input image toward a chosen target label | 2 conv. CNN on MNIST · MNIST | error rate (%): 0.64 -> 99.8 | Improved |
| apply TAGI hidden-state inference as a non-targeted attack | 2 conv. CNN on MNIST · MNIST | error rate (%): 0.64 -> 99.9 | Improved |
| apply TAGI hidden-state inference as a targeted attack | 3 conv. CNN on Cifar10 · Cifar10 | error rate (%): 22.0 -> 99.6 | Improved |
| apply TAGI hidden-state inference as a non-targeted attack | 3 conv. CNN on Cifar10 · Cifar10 | error rate (%): 22.0 -> 99.9 | Improved |
| add positive derivative constraint alpha=+1 (seek minimum), start 0.25 (ablation) | TAGI inference-based optimization on 1D toy function · y=x^3-3x | inferred optimal location: 0.965 -> -0.993 | Improved |
| add negative derivative constraint alpha=-1 (seek maximum), start -0.25 (ablation) | TAGI inference-based optimization on 1D toy function · y=x^3-3x | inferred optimal location: -0.992 -> 0.965 | Improved |
| start optimization at 1.9 instead of near the optimum (ablation) | TAGI inference-based optimization · y=x^3-3x | reaching local maximum at x=-1 | Hurt |
| use TAGI inference of actions instead of PPO gradient ascent | continuous-action RL · Half-cheetah (Mujoco) | average reward: 1649 -> 1934 | Improved |
| use TAGI inference of actions instead of PPO gradient ascent | continuous-action RL · Inverted pendulum (Mujoco) | average reward: 887 -> 983 | Improved |
Closest papers by meaning
- Tractable Approximate Gaussian Inference for Bayesian Neural Networks (JMLR 2021 · similarity 0.87)
- On the Expressiveness of Approximate Inference in Bayesian Neural Networks (NeurIPS 2020 · similarity 0.85)
- A Study of Bayesian Neural Network Surrogates for Bayesian Optimization (ICLR 2024 · similarity 0.84)
- Gated Inference Network: Inference and Learning State-Space Models (NeurIPS 2024 · similarity 0.84)
- Bayesian Exploration Networks (ICML 2024 · similarity 0.84)
- Inverse decision-making using neural amortized Bayesian actors (ICLR 2025 · similarity 0.83)
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.
