Calibrating your confidence requires thinking of all the ways you could be wrong
cs.LG, stat.ML
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- How Good is the Bayes Posterior in Deep Neural Networks Really?
- On the intelligibility of the universe and the notions of simplicity, complexity and irreducibility
- A Note on the PAC Bayesian Theorem
- Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data
- Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach
- Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI
- 'In-Between' Uncertainty in Bayesian Neural Networks
- Variational Adaptive-Newton Method for Explorative Learning
- Auto-Encoding Variational Bayes
- Variational Learning is Effective for Large Deep Networks
- VIKING: Deep variational inference with stochastic projections
- Empirical Analysis of the Hessian of Over-Parametrized Neural Networks
- The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size
- Bayes without Underfitting: Fully Correlated Deep Learning Posteriors via Alternating Projections
- Randomized Orthogonal Projection Methods for Krylov Subspace Solvers
- Randomized Numerical Linear Algebra: Foundations & Algorithms
- Bayesian generative models can flag performance loss, bias, and out-of-distribution image content
- Do Deep Generative Models Know What They Don't Know?
- Lower expected Fisher rank implies better PAC generalization
- Riemannian Laplace Approximation with the Fisher Metric
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis