ICLR 2019 accepted papers on Probabilistic and scientific modeling
61 of the 502 papers accepted at ICLR 2019 (12.2%) are on Probabilistic and scientific modeling, compared with 10.1% at ICLR 2018. They fall into 6 topics.
See ICLR 2019 in the interactive map
Submitting to ICLR? 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
- Lagging Inference Networks and Posterior Collapse in Variational Autoencoders (207 citations)
- Meta-Learning with Latent Embedding Optimization (200 citations)
- Analyzing Inverse Problems with Invertible Neural Networks (149 citations)
- FFJORD: Free-Form Continuous Dynamics for Scalable Reversible Generative Models (127 citations)
- DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder (120 citations)
- Diagnosing and Enhancing VAE Models (89 citations)
- Sliced Wasserstein Auto-Encoders (75 citations)
- Practical lossless compression with latent variables using bits back coding (68 citations)
- Variational Autoencoder with Arbitrary Conditioning (63 citations)
- Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer (62 citations)
- Do Deep Generative Models Know What They Don't Know? (55 citations)
- Integer Networks for Data Compression with Latent-Variable Models (53 citations)
and 19 more in the interactive map.
Molecules and proteins · 13 papers
- Learning Protein Structure with a Differentiable Simulator (93 citations)
- Learning Mixed-Curvature Representations in Product Spaces (77 citations)
- Meta-Learning Probabilistic Inference for Prediction (64 citations)
- FlowQA: Grasping Flow in History for Conversational Machine Comprehension (63 citations)
- Smoothing the Geometry of Probabilistic Box Embeddings (46 citations)
- KnockoffGAN: Generating Knockoffs for Feature Selection using Generative Adversarial Networks (38 citations)
- Measuring Compositionality in Representation Learning (24 citations)
- Improving Sequence-to-Sequence Learning via Optimal Transport (23 citations)
- A Statistical Approach to Assessing Neural Network Robustness (16 citations)
- Beyond Greedy Ranking: Slate Optimization via List-CVAE (16 citations)
- Top-Down Neural Model For Formulae (12 citations)
- Minimum Divergence vs. Maximum Margin: an Empirical Comparison on Seq2Seq Models (9 citations)
and 1 more in the interactive map.
Uncertainty and Gaussian processes · 10 papers
- Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes (149 citations)
- FUNCTIONAL VARIATIONAL BAYESIAN NEURAL NETWORKS (116 citations)
- Amortized Bayesian Meta-Learning (71 citations)
- Deterministic Variational Inference for Robust Bayesian Neural Networks (59 citations)
- Bias-Reduced Uncertainty Estimation for Deep Neural Classifiers (33 citations)
- Bayesian Prediction of Future Street Scenes using Synthetic Likelihoods (23 citations)
- The Deep Weight Prior (14 citations)
- Variance Networks: When Expectation Does Not Meet Your Expectations (14 citations)
- Function Space Particle Optimization for Bayesian Neural Networks (11 citations)
- Feed-forward Propagation in Probabilistic Neural Networks with Categorical and Max Layers (10 citations)
Dynamical systems · 5 papers
- Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids (169 citations)
- Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning (82 citations)
- Tree-Structured Recurrent Switching Linear Dynamical Systems for Multi-Scale Modeling (33 citations)
- Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity (32 citations)
- Optimal Control Via Neural Networks: A Convex Approach (27 citations)
Bayesian optimization · 1 paper
Differential equations and PDEs · 1 paper
- Learning Neural PDE Solvers with Convergence Guarantees (51 citations)
