ICML 2017 accepted papers on Probabilistic and scientific modeling
75 of the 435 papers accepted at ICML 2017 (17.2%) are on Probabilistic and scientific modeling, compared with 19.9% at ICML 2016. They fall into 7 topics.
See ICML 2017 in the interactive map
Submitting to ICML? 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 · 31 papers
- Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering (607 citations)
- Compressed Sensing using Generative Models (281 citations)
- Discovering Discrete Latent Topics with Neural Variational Inference (215 citations)
- Dynamic Word Embeddings (167 citations)
- Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks (157 citations)
- Grammar Variational Autoencoder (112 citations)
- Improved Variational Autoencoders for Text Modeling using Dilated Convolutions (93 citations)
- Learning Hierarchical Features from Deep Generative Models (86 citations)
- Measuring Sample Quality with Kernels (81 citations)
- Sequence to Better Sequence: Continuous Revision of Combinatorial Structures (75 citations)
- Variational Boosting: Iteratively Refining Posterior Approximations (58 citations)
- Learning Deep Latent Gaussian Models with Markov Chain Monte Carlo (57 citations)
and 19 more in the interactive map.
Uncertainty and Gaussian processes · 14 papers
- Deep Bayesian Active Learning with Image Data (573 citations)
- Multiplicative Normalizing Flows for Variational Bayesian Neural Networks (222 citations)
- Dropout Inference in Bayesian Neural Networks with Alpha-divergences (105 citations)
- Random Feature Expansions for Deep Gaussian Processes (75 citations)
- Prediction under Uncertainty in Sparse Spectrum Gaussian Processes with Applications to Filtering and Control (25 citations)
- Asynchronous Distributed Variational Gaussian Process for Regression (19 citations)
- Bayesian Boolean Matrix Factorisation (17 citations)
- Bayesian Models of Data Streams with Hierarchical Power Priors (11 citations)
- Scalable Multi-Class Gaussian Process Classification using Expectation Propagation (11 citations)
- Fast Bayesian Intensity Estimation for the Permanental Process (9 citations)
- Post-Inference Prior Swapping (6 citations)
- Robust Probabilistic Modeling with Bayesian Data Reweighting (6 citations)
and 2 more in the interactive map.
Molecules and proteins · 12 papers
- Analogical Inference for Multi-relational Embeddings (240 citations)
- Uncovering Causality from Multivariate Hawkes Integrated Cumulants (46 citations)
- Sequence Modeling via Segmentations (37 citations)
- Learning Hawkes Processes from Short Doubly-Censored Event Sequences (34 citations)
- Automatic Discovery of the Statistical Types of Variables in a Dataset (27 citations)
- Selective Inference for Sparse High-Order Interaction Models (27 citations)
- Latent Intention Dialogue Models (24 citations)
- iSurvive: An Interpretable, Event-time Prediction Model for mHealth (16 citations)
- Learning from Clinical Judgments: Semi-Markov-Modulated Marked Hawkes Processes for Risk Prognosis (15 citations)
- Learning to Discover Sparse Graphical Models (11 citations)
- Learning in POMDPs with Monte Carlo Tree Search (3 citations)
- A Birth-Death Process for Feature Allocation (1 citation)
Bayesian optimization · 9 papers
- Max-value Entropy Search for Efficient Bayesian Optimization (189 citations)
- Multi-fidelity Bayesian Optimisation with Continuous Approximations (104 citations)
- Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space (94 citations)
- High Dimensional Bayesian Optimization with Elastic Gaussian Process (59 citations)
- Counterfactual Data-Fusion for Online Reinforcement Learners (41 citations)
- Preferential Bayesian Optimization (36 citations)
- Batched High-dimensional Bayesian Optimization via Structural Kernel Learning (20 citations)
- Local Bayesian Optimization of Motor Skills (11 citations)
- Bayesian Optimization with Tree-structured Dependencies
Treatment effects · 3 papers
Causal discovery · 3 papers
- Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics (168 citations)
- Identification and Model Testing in Linear Structural Equation Models using Auxiliary Variables (10 citations)
- Uncertainty Assessment and False Discovery Rate Control in High-Dimensional Granger Causal Inference (7 citations)
