NeurIPS 2020 accepted papers on Probabilistic and scientific modeling
270 of the 1,901 papers accepted at NeurIPS 2020 (14.2%) are on Probabilistic and scientific modeling, compared with 13.9% at NeurIPS 2019. They fall into 8 topics.
See NeurIPS 2020 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 · 87 papers
- NVAE: A Deep Hierarchical Variational Autoencoder (361 citations)
- MetaSDF: Meta-Learning Signed Distance Functions (112 citations)
- Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder (71 citations)
- Improving Inference for Neural Image Compression (54 citations)
- Modeling Noisy Annotations for Crowd Counting (51 citations)
- Stochastic Normalizing Flows (41 citations)
- SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows (40 citations)
- Riemannian Continuous Normalizing Flows (34 citations)
- Gradient Estimation with Stochastic Softmax Tricks (33 citations)
- Why Normalizing Flows Fail to Detect Out-of-Distribution Data (30 citations)
- Differentiable Neural Architecture Search in Equivalent Space with Exploration Enhancement (28 citations)
- Improving Local Identifiability in Probabilistic Box Embeddings (27 citations)
and 75 more in the interactive map.
Uncertainty and Gaussian processes · 46 papers
- Bayesian Deep Learning and a Probabilistic Perspective of Generalization (177 citations)
- Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness (102 citations)
- Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts (68 citations)
- On the Expressiveness of Approximate Inference in Bayesian Neural Networks (53 citations)
- Multi-Robot Collision Avoidance under Uncertainty with Probabilistic Safety Barrier Certificates (51 citations)
- Variational Bayesian Unlearning (44 citations)
- Predictive inference is free with the jackknife+-after-bootstrap (40 citations)
- Improving model calibration with accuracy versus uncertainty optimization (32 citations)
- Variational Bayesian Monte Carlo with Noisy Likelihoods (31 citations)
- Bayesian Deep Ensembles via the Neural Tangent Kernel (29 citations)
- Depth Uncertainty in Neural Networks (29 citations)
- Learning under Model Misspecification: Applications to Variational and Ensemble methods (29 citations)
and 34 more in the interactive map.
Molecules and proteins · 37 papers
- CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models (82 citations)
- RetroXpert: Decompose Retrosynthesis Prediction Like A Chemist (51 citations)
- Guiding Deep Molecular Optimization with Genetic Exploration (33 citations)
- Information Theoretic Counterfactual Learning from Missing-Not-At-Random Feedback (30 citations)
- BoxE: A Box Embedding Model for Knowledge Base Completion (27 citations)
- Deep active inference agents using Monte-Carlo methods (26 citations)
- Classification with Valid and Adaptive Coverage (24 citations)
- Recurrent Quantum Neural Networks (20 citations)
- Learning Sparse Prototypes for Text Generation (16 citations)
- Neural Bridge Sampling for Evaluating Safety-Critical Autonomous Systems (16 citations)
- Multiparameter Persistence Image for Topological Machine Learning (15 citations)
- Barking up the right tree: an approach to search over molecule synthesis DAGs (11 citations)
and 25 more in the interactive map.
Dynamical systems · 34 papers
- Learning identifiable and interpretable latent models of high-dimensional neural activity using pi-VAE (49 citations)
- Recurrent Switching Dynamical Systems Models for Multiple Interacting Neural Populations (45 citations)
- Reverse-engineering recurrent neural network solutions to a hierarchical inference task for mice (45 citations)
- Uncovering the Topology of Time-Varying fMRI Data using Cubical Persistence (34 citations)
- Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations (23 citations)
- Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints (19 citations)
- STLnet: Signal Temporal Logic Enforced Multivariate Recurrent Neural Networks (18 citations)
- Efficient estimation of neural tuning during naturalistic behavior (16 citations)
- Identifying signal and noise structure in neural population activity with Gaussian process factor models (16 citations)
- System Identification with Biophysical Constraints: A Circuit Model of the Inner Retina (15 citations)
- Non-reversible Gaussian processes for identifying latent dynamical structure in neural data (14 citations)
- Learning Physical Constraints with Neural Projections (11 citations)
and 22 more in the interactive map.
Causal discovery · 24 papers
- Algorithmic recourse under imperfect causal knowledge: a probabilistic approach (87 citations)
- Deep Structural Causal Models for Tractable Counterfactual Inference (87 citations)
- Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect (50 citations)
- Causal Discovery in Physical Systems from Videos (43 citations)
- A Causal View on Robustness of Neural Networks (41 citations)
- High-recall causal discovery for autocorrelated time series with latent confounders (38 citations)
- Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability (36 citations)
- Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models (31 citations)
- CASTLE: Regularization via Auxiliary Causal Graph Discovery (28 citations)
- Causal Discovery from Soft Interventions with Unknown Targets: Characterization and Learning (22 citations)
- How Robust are the Estimated Effects of Nonpharmaceutical Interventions against COVID-19? (18 citations)
- Differentiable Causal Discovery from Interventional Data (17 citations)
and 12 more in the interactive map.
Bayesian optimization · 17 papers
- BoTorch: A Framework for Efficient Monte-Carlo Bayesian Optimization (201 citations)
- Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization (121 citations)
- Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining (49 citations)
- Diversity-Guided Multi-Objective Bayesian Optimization With Batch Evaluations (40 citations)
- Re-Examining Linear Embeddings for High-Dimensional Bayesian Optimization (37 citations)
- Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search (30 citations)
- Black-Box Optimization with Local Generative Surrogates (24 citations)
- BOSS: Bayesian Optimization over String Spaces (24 citations)
- Multi-Fidelity Bayesian Optimization via Deep Neural Networks (22 citations)
- Model Inversion Networks for Model-Based Optimization (21 citations)
- Automatically Learning Compact Quality-aware Surrogates for Optimization Problems (5 citations)
- Bayesian Optimization of Risk Measures (5 citations)
and 5 more in the interactive map.
Treatment effects · 14 papers
- Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks (50 citations)
- Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models (38 citations)
- Counterfactual Prediction for Bundle Treatment (18 citations)
- Sense and Sensitivity Analysis: Simple Post-Hoc Analysis of Bias Due to Unobserved Confounding (17 citations)
- Reconsidering Generative Objectives For Counterfactual Reasoning (15 citations)
- OrganITE: Optimal transplant donor organ offering using an individual treatment effect (12 citations)
- Robust Recursive Partitioning for Heterogeneous Treatment Effects with Uncertainty Quantification (8 citations)
- Minimax Optimal Nonparametric Estimation of Heterogeneous Treatment Effects (6 citations)
- A Class of Algorithms for General Instrumental Variable Models (4 citations)
- A/B Testing in Dense Large-Scale Networks: Design and Inference (2 citations)
- Causal Estimation with Functional Confounders (2 citations)
- General Control Functions for Causal Effect Estimation from IVs (2 citations)
and 2 more in the interactive map.
Differential equations and PDEs · 11 papers
- Implicit Neural Representations with Periodic Activation Functions (262 citations)
- Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers (128 citations)
- Dissecting Neural ODEs (86 citations)
- Learning Differential Equations that are Easy to Solve (51 citations)
- Neural Manifold Ordinary Differential Equations (27 citations)
- On Second Order Behaviour in Augmented Neural ODEs (21 citations)
- Training Generative Adversarial Networks by Solving Ordinary Differential Equations (15 citations)
- Deep Energy-based Modeling of Discrete-Time Physics (14 citations)
- Numerically Solving Parametric Families of High-Dimensional Kolmogorov Partial Differential Equations via Deep Learning (5 citations)
- A shooting formulation of deep learning (4 citations)
- Focus of Attention Improves Information Transfer in Visual Features
