ICML 2017 Workshop on Implicit Models

Session 1

• 8:30-8:40 Introduction
• 8:40-9:10 Kerrie Mengerson: Probabilistic Modelling in the Real World
• 9:10-9:20 Yingzhen Li: Approximate Inference with Amortised MCMC
• 9:20-9:30 Zenna Tavares: Adversarial Inversion for Amortized Inference
• 9:30-10:00 Spotlight session 1

BREAK: 10:00-10:30

Session 2

• 10:30-11:00 Stefano Ermon: Generative Adversarial Imitation Learning
• 11:00-11:10 Jun-Yan Zhu: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• 11:10-11:30 Spotlight session 2
• 11:30-12:30 Poster session

Lunch Break: 12:30 - 2pm

Session 3

• 2:00-2:30 Qiang Liu: Wild Variational Inference with Expressive Variational Families
• 2:30-3:00 Sanjeev Arora: Do GANs actually learn the distribution? Some theory and empirics

Break: 3:00 - 3:30pm

Session 4

• 3:30-4:00 Dougal Sutherland: Evaluating and Training Implicit Generative Models with Two-Sample Tests
• 4:00-4:10 Lars Mescheder: The Numerics of GANs
• 4:10-4:20 Eric Nalisnick: The Amortised bootstrap
• 4:20-4:30 Philemon Brakel: Maximizing Independence with GANs for Non-linear ICA
• 4:30-5:30 Panel discussion