NeurIPS 2017 accepted papers on Probabilistic and scientific modeling
127 of the 688 papers accepted at NeurIPS 2017 (18.5%) are on Probabilistic and scientific modeling, compared with 18.8% at NeurIPS 2016. They fall into 8 topics.
See NeurIPS 2017 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 · 51 papers
- Neural Discrete Representation Learning (2,816 citations)
- Masked Autoregressive Flow for Density Estimation (201 citations)
- Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data (166 citations)
- REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models (148 citations)
- Learning Disentangled Representations with Semi-Supervised Deep Generative Models (140 citations)
- Estimating Mutual Information for Discrete-Continuous Mixtures (106 citations)
- Wasserstein Learning of Deep Generative Point Process Models (102 citations)
- Hierarchical Implicit Models and Likelihood-Free Variational Inference (96 citations)
- Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inference (66 citations)
- Ensemble Sampling (46 citations)
- Differentiable Learning of Submodular Models (42 citations)
- Variational Memory Addressing in Generative Models (39 citations)
and 39 more in the interactive map.
Uncertainty and Gaussian processes · 24 papers
- What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? (2,921 citations)
- Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles (734 citations)
- Bayesian Compression for Deep Learning (335 citations)
- Flexible statistical inference for mechanistic models of neural dynamics (139 citations)
- Spectral Mixture Kernels for Multi-Output Gaussian Processes (56 citations)
- Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes (54 citations)
- Convolutional Gaussian Processes (51 citations)
- Doubly Stochastic Variational Inference for Deep Gaussian Processes (50 citations)
- Variational Inference for Gaussian Process Models with Linear Complexity (48 citations)
- Learning from uncertain curves: The 2-Wasserstein metric for Gaussian processes (39 citations)
- Linearly constrained Gaussian processes (32 citations)
- Scalable Log Determinants for Gaussian Process Kernel Learning (25 citations)
and 12 more in the interactive map.
Dynamical systems · 22 papers
- InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations (136 citations)
- Gaussian process based nonlinear latent structure discovery in multivariate spike train data (81 citations)
- Reconstructing perceived faces from brain activations with deep adversarial neural decoding (62 citations)
- Neural Networks for Efficient Bayesian Decoding of Natural Images from Retinal Neurons (59 citations)
- Quantifying how much sensory information in a neural code is relevant for behavior (34 citations)
- Variational Laws of Visual Attention for Dynamic Scenes (24 citations)
- Model-based Bayesian inference of neural activity and connectivity from all-optical interrogation of a neural circuit (21 citations)
- Extracting low-dimensional dynamics from multiple large-scale neural population recordings by learning to predict correlations (17 citations)
- Training recurrent networks to generate hypotheses about how the brain solves hard navigation problems (17 citations)
- Predictive State Recurrent Neural Networks (15 citations)
- Toward Goal-Driven Neural Network Models for the Rodent Whisker-Trigeminal System (15 citations)
- Cross-Spectral Factor Analysis (14 citations)
and 10 more in the interactive map.
Molecules and proteins · 15 papers
- Protein Interface Prediction using Graph Convolutional Networks (557 citations)
- SchNet: A continuous-filter convolutional neural network for modeling quantum interactions (470 citations)
- The Neural Hawkes Process: A Neurally Self-Modulating Multivariate Point Process (204 citations)
- Differentiable Learning of Logical Rules for Knowledge Base Reasoning (171 citations)
- DropoutNet: Addressing Cold Start in Recommender Systems (149 citations)
- Task-based End-to-end Model Learning in Stochastic Optimization (122 citations)
- Neural Expectation Maximization (113 citations)
- From Bayesian Sparsity to Gated Recurrent Nets (20 citations)
- Inverse Filtering for Hidden Markov Models (18 citations)
- NeuralFDR: Learning Discovery Thresholds from Hypothesis Features (12 citations)
- Plan, Attend, Generate: Planning for Sequence-to-Sequence Models (12 citations)
- Q-LDA: Uncovering Latent Patterns in Text-based Sequential Decision Processes (3 citations)
and 3 more in the interactive map.
Bayesian optimization · 5 papers
- Practical Bayesian Optimization for Model Fitting with Bayesian Adaptive Direct Search (157 citations)
- Bayesian Optimization with Gradients (129 citations)
- Lookahead Bayesian Optimization with Inequality Constraints (28 citations)
- Process-constrained batch Bayesian optimisation (21 citations)
- An Empirical Bayes Approach to Optimizing Machine Learning Algorithms
Causal discovery · 5 papers
- Avoiding Discrimination through Causal Reasoning (176 citations)
- Permutation-based Causal Inference Algorithms with Interventions (56 citations)
- Learning Causal Structures Using Regression Invariance (13 citations)
- Discovering Potential Correlations via Hypercontractivity (4 citations)
- GP CaKe: Effective brain connectivity with causal kernels (4 citations)
Treatment effects · 4 papers
- Causal Effect Inference with Deep Latent-Variable Models (281 citations)
- Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processes (152 citations)
- Matching on Balanced Nonlinear Representations for Treatment Effects Estimation (36 citations)
- Learning spatiotemporal piecewise-geodesic trajectories from longitudinal manifold-valued data (12 citations)
Differential equations and PDEs · 1 paper
- Principles of Riemannian Geometry in Neural Networks (38 citations)
