VI Tutorial at IST

Our friends from DeepSPIN invited us to IST in sunny Lisbon from 27-29 May.

Schedule

Check the branch IST2019 for all modules

Day 1 (27 May 9:00-12:00)

• Deep generative models
• Variational inference

Day 2 (28 May 9:00-12:00)

• Discrete latent variables
• Continuous latent variables

Day 3 (29 May 9:00-12:00)

• Automatic differentiation VI
• Normalising flows

Advanced topics

Beyond Gaussian posterior with normalising flows:

• Variational Inference with Normalising Flows
• Improving Variational Inference with Inverse Autoregressive Flow

Beyond mean-field:

• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Sequential Neural Models with Stochastic Layers
• A Stochastic Decoder for Neural Machine Translation

Beyond Gaussian prior:

• Automatic Differentiation Variational Inference

More about posterior collapse:

• Variational Lossy Autoencoder
• Towards a Deeper Understanding of Variational Autoencoding Models and InfoVAE: Information Maximizing Variational Autoencoders
• Fixing a Broken ELBO

Beyond KL divergence:

• Operator Variational Inference

Beyond likelihood learning:

• Deep and Hierarchical Implicit Models

Beyond baselines:

• MuProp: Unbiased Backpropagation for Stochastic Neural Networks
• REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models
• Backpropagation through the Void: Optimizing control variates for black-box gradient estimation