Deep Heteroskedastic Regression: Post-Hoc Variance Estimation from Latent Representations
cs.LG
Submitted: 2026-03-02
Updated: 2026-11-11
Code: https://github.com/EricZQu/fairchem
Terminology
Sources
- Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models
- Rethinking Early Stopping: Refine, Then Calibrate
- Calibrated Uncertainty for Molecular Property Prediction using Ensembles of Message Passing Neural Networks
- Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models
- Large-Scale Visual Active Learning with Deep Probabilistic Ensembles
- Learning Smooth and Expressive Interatomic Potentials for Physical Property Prediction
- Open Molecular Crystals 2025 (OMC25) Dataset and Models
- Probabilistic Skip Connections for Deterministic Uncertainty Quantification in Deep Neural Networks
- Vecchia Gaussian Process Ensembles on Internal Representations of Deep Neural Networks
- Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks
- Decoupled Weight Decay Regularization
- Deep Deterministic Uncertainty: A Simple Baseline
- Deep Double Descent: Where Bigger Models and More Data Hurt
- An open dataset of gas adsorption in deformable metal-organic frameworks for direct air capture
- Variational Variance: Simple, Reliable, Calibrated Heteroscedastic Noise Variance Parameterization
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