Explore >> Select a destination
|
You are here 
|
proceedings.neurips.cc | ||
| | | | |
dustintran.com
|
|
| | | | | I'm excited to announce a paper that Rajesh Ranganath, Dave Blei, and I released today on arXiv, titled Deep and Hierarchical Implicit Models. Implicit probabilistic models are all about sampling as a primitive: they define a process to simulate data and do not require tractable densities (Diggle & Gratton (1984), Hartig, Calabrese, Reineking, Wiegand, & Huth (2011)) . We leverage this fundamental idea to develop new classes of models: they encompass simulators in the scientific communities, generative a... | |
| | | | |
tiao.io
|
|
| | | | | We propose a framework that lifts the capabilities of graph convolutional networks (GCNs) to scenarios where no input graph is given and increases their robustness to adversarial attacks. We formulate a joint probabilistic model that considers a prior distribution over graphs along with a GCN-based likelihood and develop a stochastic variational inference algorithm to estimate the graph posterior and the GCN parameters jointly. To address the problem of propagating gradients through latent variables draw... | |
| | | | |
blog.shakirm.com
|
|
| | | | | [dropcap]Probabilistic[/dropcap] inference lies no longer atthe fringe. The importance of how we connect our observed data to the assumptions made by ourstatisticalmodels-the task of inference-w... | |
| | | | |
resources.paperdigest.org
|
|
| | | The Conference on Neural Information Processing Systems (NIPS) is one of the top machine learning conferences in the world. Paper Digest Team analyze all papers published on NIPS in the past years, and presents the 15 most influential papers for each year. This ranking list is automatically construc | ||
