ICLR 2017 accepted papers on Probabilistic and scientific modeling
23 of the 198 papers accepted at ICLR 2017 (11.6%) are on Probabilistic and scientific modeling. They fall into 4 topics.
See ICLR 2017 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 · 15 papers
- Categorical Reparameterization with Gumbel-Softmax (3,310 citations)
- beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework (2,979 citations)
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables (1,471 citations)
- Density estimation using Real NVP (735 citations)
- Adversarially Learned Inference (663 citations)
- Variational Lossy Autoencoder (241 citations)
- Autoencoding Variational Inference For Topic Models (143 citations)
- Deep Probabilistic Programming (110 citations)
- PixelVAE: A Latent Variable Model for Natural Images (76 citations)
- PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications (75 citations)
- Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data (74 citations)
- Stick-Breaking Variational Autoencoders (45 citations)
and 3 more in the interactive map.
Dynamical systems · 5 papers
- A Compositional Object-Based Approach to Learning Physical Dynamics (153 citations)
- Multilayer Recurrent Network Models of Primate Retinal Ganglion Cell Responses (66 citations)
- Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks (52 citations)
- Recurrent Hidden Semi-Markov Model (28 citations)
- Online Bayesian Transfer Learning for Sequential Data Modeling (14 citations)
Molecules and proteins · 2 papers
- Hierarchical Multiscale Recurrent Neural Networks (235 citations)
- The Neural Noisy Channel (20 citations)
Bayesian optimization · 1 paper
- Learning Curve Prediction with Bayesian Neural Networks (170 citations)
