Explore >> Select a destination
|
You are here 
|
11011110.github.io | ||
| | | | |
blog.geomblog.org
|
|
| | | | | Session 3: Representation and Profiling Session 4: Fairness methods. | |
| | | | |
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... | |
| | | | |
dustintran.com
|
|
| | | | | Two papers of mine were released today on arXiv. Operator variational inference, in collaboration with Rajesh Ranganath, Jaan Altosaar, and David Blei. Model criticism for Bayesian causal inference, in collaboration with Francisco Ruiz, Susan Athey, and David Blei. Last week, I gave a talk at OpenAI on operator variational inference and Edward. I can now release those slides online. Operator variational inference Operator VI is a paper I'm really excited about. It is at NIPS this year. Most directly, it'... | |
| | | | |
disconnect.blog
|
|
| | | Eric Schmidt is the latest tech executive to claim AI must be built regardless of the climate cost | ||
