ICML 2018 accepted papers on Probabilistic and scientific modeling
106 of the 623 papers accepted at ICML 2018 (17.0%) are on Probabilistic and scientific modeling, compared with 17.2% at ICML 2017. They fall into 8 topics.
See ICML 2018 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 · 41 papers
- Mutual Information Neural Estimation (574 citations)
- A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music (301 citations)
- Yes, but Did It Work?: Evaluating Variational Inference (84 citations)
- Inference Suboptimality in Variational Autoencoders (79 citations)
- Pathwise Derivatives Beyond the Reparameterization Trick (60 citations)
- PixelSNAIL: An Improved Autoregressive Generative Model (51 citations)
- Message Passing Stein Variational Gradient Descent (49 citations)
- A Spectral Approach to Gradient Estimation for Implicit Distributions (43 citations)
- Fixing a Broken ELBO (39 citations)
- Adversarially Regularized Autoencoders (38 citations)
- DVAE++: Discrete Variational Autoencoders with Overlapping Transformations (38 citations)
- On Nesting Monte Carlo Estimators (35 citations)
and 29 more in the interactive map.
Uncertainty and Gaussian processes · 24 papers
- Bayesian Uncertainty Estimation for Batch Normalized Deep Networks (167 citations)
- High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach (150 citations)
- Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning (113 citations)
- Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam (59 citations)
- Conditional Neural Processes (51 citations)
- Differentiable Compositional Kernel Learning for Gaussian Processes (43 citations)
- Adversarial Distillation of Bayesian Neural Network Posteriors (30 citations)
- Fast Information-theoretic Bayesian Optimisation (26 citations)
- Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors (26 citations)
- Noisy Natural Gradient as Variational Inference (25 citations)
- Generalized Robust Bayesian Committee Machine for Large-scale Gaussian Process Regression (23 citations)
- Variational Bayesian dropout: pitfalls and fixes (23 citations)
and 12 more in the interactive map.
Molecules and proteins · 17 papers
- Fast Decoding in Sequence Models Using Discrete Latent Variables (169 citations)
- Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry (61 citations)
- MAGAN: Aligning Biological Manifolds (33 citations)
- Adversarial Time-to-Event Modeling (24 citations)
- oi-VAE: Output Interpretable VAEs for Nonlinear Group Factor Analysis (19 citations)
- Spline Filters For End-to-End Deep Learning (18 citations)
- Parallel Bayesian Network Structure Learning (13 citations)
- Probabilistic Boolean Tensor Decomposition (13 citations)
- Variable Selection via Penalized Neural Network: a Drop-Out-One Loss Approach (13 citations)
- Learning Hidden Markov Models from Pairwise Co-occurrences with Application to Topic Modeling (11 citations)
- A Robust Approach to Sequential Information Theoretic Planning (7 citations)
- Nonparametric variable importance using an augmented neural network with multi-task learning (6 citations)
and 5 more in the interactive map.
Bayesian optimization · 8 papers
- BOHB: Robust and Efficient Hyperparameter Optimization at Scale (180 citations)
- Batch Bayesian Optimization via Multi-objective Acquisition Ensemble for Automated Analog Circuit Design (80 citations)
- BOCK : Bayesian Optimization with Cylindrical Kernels (73 citations)
- Bayesian Optimization of Combinatorial Structures (72 citations)
- Stagewise Safe Bayesian Optimization with Gaussian Processes (65 citations)
- AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning (57 citations)
- Optimization, fast and slow: optimally switching between local and Bayesian optimization (22 citations)
- Structured Variationally Auto-encoded Optimization (21 citations)
Dynamical systems · 8 papers
- Graph Networks as Learnable Physics Engines for Inference and Control (271 citations)
- Neural Relational Inference for Interacting Systems (267 citations)
- Comparing Dynamics: Deep Neural Networks versus Glassy Systems (47 citations)
- Learning unknown ODE models with Gaussian processes (34 citations)
- Robust and Scalable Models of Microbiome Dynamics (28 citations)
- Dependent Relational Gamma Process Models for Longitudinal Networks (15 citations)
- Learning Dynamics of Linear Denoising Autoencoders (4 citations)
- Revealing Common Statistical Behaviors in Heterogeneous Populations (1 citation)
Causal discovery · 4 papers
- Learning Independent Causal Mechanisms (87 citations)
- Characterizing and Learning Equivalence Classes of Causal DAGs under Interventions (36 citations)
- Detecting non-causal artifacts in multivariate linear regression models (10 citations)
- Minimal I-MAP MCMC for Scalable Structure Discovery in Causal DAG Models (7 citations)
Differential equations and PDEs · 2 papers
- PDE-Net: Learning PDEs from Data (206 citations)
- Learning Equations for Extrapolation and Control (45 citations)
