Research map / Probabilistic and scientific modeling
Uncertainty and Gaussian processes: research map
1,162 accepted papers on Uncertainty and Gaussian processes in Probabilistic and scientific modeling, from ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026), grouped into 4 clusters and 15 approaches. The busiest year so far is 2026.
Within Probabilistic and scientific modeling, its share shrank from 13.4% in 2023–24 to 10.1% in 2025–26 (272 → 308 papers at ICML, NeurIPS, CVPR and AAAI, the venues with data for all four years).
Explore Uncertainty and Gaussian processes in the interactive map
Working on something in this topic? Describe your idea in scime atlas to see which approach it falls under, the closest papers by meaning and how crowded the spot has become.
Approaches and key papers
bayesian inference · posterior · priors · 509 papers
Approaches in this cluster:
- Nonparametric and PAC-Bayes Bayesian learning (130 papers)
Develops Bayesian nonparametric models and links PAC-Bayes theory with Bayesian inference. - Simulation-based inference (118 papers)
Estimates posteriors for simulators using learned statistics and active sequential estimation. - Variational Bayesian deep learning (105 papers)
Parameterizes and analyzes variational posteriors for deep models, linking ensembles to Bayesian inference. - Approximate inference in Bayesian neural networks (93 papers)
Examines how well approximate posteriors and cold posteriors behave in Bayesian neural networks. - Bayesian view of meta-learning (63 papers)
Recasts meta-learning and in-context learning as hierarchical Bayesian inference.
Most cited and most cited since 2024:
- A Theoretically Grounded Application of Dropout in Recurrent Neural Networks (NeurIPS 2016 · 887 citations)
- Deep Bayesian Active Learning with Image Data (ICML 2017 · 573 citations)
- Bayesian Low-Rank Learning (Bella): A Practical Approach to Bayesian Neural Networks (AAAI 2025 · 6 citations)
- Variational Bayesian Last Layers (ICLR 2024 · 6 citations)
uncertainty estimation · epistemic · quantification · 318 papers
Approaches in this cluster:
- Priors and functional variational uncertainty (112 papers)
Builds expressive priors, depth-based and functional variational methods for uncertainty estimation. - Single-model predictive uncertainty (74 papers)
Equips deep networks with uncertainty through SDEs, ensembles, bias reduction and cheap Bayesian conversion. - Epistemic versus aleatoric decomposition (75 papers)
Critically analyzes how to define and separate epistemic and aleatoric uncertainty. - Bayesian decision-making under uncertainty (57 papers)
Applies Bayesian modeling and distillation to decisions and measurement under model uncertainty.
Most cited and most cited since 2024:
- What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? (NeurIPS 2017 · 2,921 citations)
- Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning (ICML 2016 · 2,628 citations)
- Producing and Leveraging Online Map Uncertainty in Trajectory Prediction (CVPR 2024 · 37 citations)
- Deep Active Learning with Noise Stability (AAAI 2024 · 22 citations)
gaussian processes · gp · kernel · 263 papers
Approaches in this cluster:
- Sparse variational Gaussian processes (92 papers)
Scales Gaussian processes with sparse inducing-point and variational approximations. - PAC-Bayes and decoupled GP learning (83 papers)
Learns Gaussian processes via decoupled variational bases, PAC-Bayes bounds and random projections. - Infinite-width networks as Gaussian processes (49 papers)
Connects wide neural networks and deep kernels to Gaussian processes. - Structured Gaussian process models (39 papers)
Models nonstationary covariances, mixtures and latent structure with identifiability analysis.
Most cited and most cited since 2024:
- Deep Neural Networks as Gaussian Processes (ICLR 2018 · 553 citations)
- GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration (NeurIPS 2018 · 528 citations)
- Gaussian Process Neural Additive Models (AAAI 2024 · 11 citations)
- Sparse Variational Student-t Processes (AAAI 2024 · 5 citations)
conformal · intervals · prediction · 72 papers
Approaches in this cluster:
- Regression uncertainty quantification (43 papers)
Estimates predictive uncertainty for deep and high-dimensional regression. - Conformal prediction methods (29 papers)
Constructs conformal prediction sets with localized, ensemble and Bayesian approaches.
Most cited and most cited since 2024:
- High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach (ICML 2018 · 150 citations)
- Learning for Single-Shot Confidence Calibration in Deep Neural Networks Through Stochastic Inferences (CVPR 2019 · 71 citations)
- Robust Uncertainty Quantification Using Conformalised Monte Carlo Prediction (AAAI 2024 · 23 citations)
- CUQDS: Conformal Uncertainty Quantification Under Distribution Shift for Trajectory Prediction (AAAI 2025 · 8 citations)
Related topics in Probabilistic and scientific modeling
- Dynamical systems (969)
- Molecules and proteins (1,990)
- Variational and generative sampling (2,060)
- Treatment effects (421)
- Differential equations and PDEs (614)
- Causal discovery (830)
- Bayesian optimization (397)