NeurIPS 2019 accepted papers on Probabilistic and scientific modeling
198 of the 1,429 papers accepted at NeurIPS 2019 (13.9%) are on Probabilistic and scientific modeling, compared with 16.3% at NeurIPS 2018. They fall into 8 topics.
See NeurIPS 2019 in the interactive map
Submitting to NeurIPS? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Variational and generative sampling · 69 papers
- Generative Modeling by Estimating Gradients of the Data Distribution (1,076 citations)
- Variational Denoising Network: Toward Blind Noise Modeling and Removal (211 citations)
- Residual Flows for Invertible Generative Modeling (175 citations)
- BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling (116 citations)
- Learning Non-Convergent Non-Persistent Short-Run MCMC Toward Energy-Based Model (96 citations)
- Discrete Flows: Invertible Generative Models of Discrete Data (66 citations)
- Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting (65 citations)
- Semi-Implicit Graph Variational Auto-Encoders (61 citations)
- Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders (49 citations)
- The continuous Bernoulli: fixing a pervasive error in variational autoencoders (49 citations)
- Expressive power of tensor-network factorizations for probabilistic modeling (41 citations)
- Compression with Flows via Local Bits-Back Coding (36 citations)
and 57 more in the interactive map.
Uncertainty and Gaussian processes · 41 papers
- Can you trust your model's uncertainty? Evaluating predictive uncertainty under dataset shift (924 citations)
- A Simple Baseline for Bayesian Uncertainty in Deep Learning (173 citations)
- Practical Deep Learning with Bayesian Principles (124 citations)
- Bayesian Layers: A Module for Neural Network Uncertainty (77 citations)
- Single-Model Uncertainties for Deep Learning (74 citations)
- CXPlain: Causal Explanations for Model Interpretation under Uncertainty (73 citations)
- Variational Bayesian Optimal Experimental Design (47 citations)
- Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dimensions (36 citations)
- Exact Gaussian Processes on a Million Data Points (32 citations)
- The Functional Neural Process (32 citations)
- Accurate Uncertainty Estimation and Decomposition in Ensemble Learning (31 citations)
- Bayesian Learning of Sum-Product Networks (20 citations)
and 29 more in the interactive map.
Dynamical systems · 27 papers
- Hamiltonian Neural Networks (447 citations)
- Differentiable Cloth Simulation for Inverse Problems (72 citations)
- Learning Stable Deep Dynamics Models (54 citations)
- Attentive State-Space Modeling of Disease Progression (52 citations)
- A unified theory for the origin of grid cells through the lens of pattern formation (48 citations)
- Universality and individuality in neural dynamics across large populations of recurrent networks (38 citations)
- Learning-In-The-Loop Optimization: End-To-End Control And Co-Design Of Soft Robots Through Learned Deep Latent Representations (32 citations)
- Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement (26 citations)
- Manifold-regression to predict from MEG/EEG brain signals without source modeling (25 citations)
- Enabling hyperparameter optimization in sequential autoencoders for spiking neural data (22 citations)
- Better Transfer Learning with Inferred Successor Maps (20 citations)
- Seeing the Wind: Visual Wind Speed Prediction with a Coupled Convolutional and Recurrent Neural Network (18 citations)
and 15 more in the interactive map.
Molecules and proteins · 22 papers
- Generative Models for Graph-Based Protein Design (209 citations)
- Levenshtein Transformer (182 citations)
- Cormorant: Covariant Molecular Neural Networks (134 citations)
- Learning Disentangled Representations for Recommendation (99 citations)
- A Model to Search for Synthesizable Molecules (71 citations)
- Conformal Prediction Under Covariate Shift (53 citations)
- Blow: a single-scale hyperconditioned flow for non-parallel raw-audio voice conversion (49 citations)
- End-to-End Learning on 3D Protein Structure for Interface Prediction (41 citations)
- NAOMI: Non-Autoregressive Multiresolution Sequence Imputation (16 citations)
- Coordinated hippocampal-entorhinal replay as structural inference (14 citations)
- Meta Learning with Relational Information for Short Sequences (10 citations)
- Regression Planning Networks (9 citations)
and 10 more in the interactive map.
Causal discovery · 17 papers
- Causal Confusion in Imitation Learning (162 citations)
- Characterization and Learning of Causal Graphs with Latent Variables from Soft Interventions (23 citations)
- The Case for Evaluating Causal Models Using Interventional Measures and Empirical Data (17 citations)
- Neuropathic Pain Diagnosis Simulator for Causal Discovery Algorithm Evaluation (14 citations)
- Triad Constraints for Learning Causal Structure of Latent Variables (12 citations)
- A Normative Theory for Causal Inference and Bayes Factor Computation in Neural Circuits (11 citations)
- Specific and Shared Causal Relation Modeling and Mechanism-Based Clustering (10 citations)
- Identifying Causal Effects via Context-specific Independence Relations (9 citations)
- Selecting causal brain features with a single conditional independence test per feature (7 citations)
- Kernel Instrumental Variable Regression (6 citations)
- Efficient Identification in Linear Structural Causal Models with Instrumental Cutsets (5 citations)
- An Algorithm to Learn Polytree Networks with Hidden Nodes (4 citations)
and 5 more in the interactive map.
Bayesian optimization · 10 papers
- BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning (294 citations)
- Scalable Global Optimization via Local Bayesian Optimization (137 citations)
- Max-value Entropy Search for Multi-Objective Bayesian Optimization (72 citations)
- Demystifying Black-box Models with Symbolic Metamodels (51 citations)
- Learning search spaces for Bayesian optimization: Another view of hyperparameter transfer learning (36 citations)
- Bayesian Optimization with Unknown Search Space (22 citations)
- Safe Exploration for Interactive Machine Learning (21 citations)
- Practical Two-Step Lookahead Bayesian Optimization (20 citations)
- Offline Contextual Bayesian Optimization (10 citations)
- Learning Bayesian Networks with Low Rank Conditional Probability Tables (3 citations)
Treatment effects · 8 papers
- Deep Generalized Method of Moments for Instrumental Variable Analysis (56 citations)
- Adapting Neural Networks for the Estimation of Treatment Effects (52 citations)
- Machine Learning Estimation of Heterogeneous Treatment Effects with Instruments (32 citations)
- Using Embeddings to Correct for Unobserved Confounding in Networks (28 citations)
- Covariate-Powered Empirical Bayes Estimation (11 citations)
- Learning Sample-Specific Models with Low-Rank Personalized Regression (10 citations)
- Assessing Disparate Impact of Personalized Interventions: Identifiability and Bounds (8 citations)
- Debiased Bayesian inference for average treatment effects (5 citations)
Differential equations and PDEs · 4 papers
- Neural Jump Stochastic Differential Equations (108 citations)
- Augmented Neural ODEs (54 citations)
- Neural Networks with Cheap Differential Operators (12 citations)
- A Solvable High-Dimensional Model of GAN (10 citations)
