Jonathan Ho

I received my PhD in computer science from UC Berkeley in 2020, advised by Pieter Abbeel.

My research interests are unsupervised learning and reinforcement learning.

Preprints

• Axial attention in multidimensional transformers
  Jonathan Ho*, Nal Kalchbrenner*, Dirk Weissenborn, Tim Salimans
  [arXiv]
• Natural image manipulation for autoregressive models using Fisher scores
  Wilson Yan, Jonathan Ho, Pieter Abbeel
  [arXiv]
• Evolution strategies as a scalable alternative to reinforcement learning
  Tim Salimans, Jonathan Ho, Xi Chen, Szymon Sidor, Ilya Sutskever
  [arXiv]

Publications

• Denoising diffusion probabilistic models
  Jonathan Ho, Ajay Jain, Pieter Abbeel
  Neural Information Processing Systems, 2020
  [arXiv] [website] [code]
• Compression with flows via local bits-back coding
  Jonathan Ho, Evan Lohn, Pieter Abbeel
  Neural Information Processing Systems, 2019
  [arXiv]
• Flow++: Improving flow-based generative models with variational dequantization and architecture design
  Jonathan Ho*, Xi Chen*, Aravind Srinivas, Yan Duan, Pieter Abbeel
  International Conference on Machine Learning, 2019
  [arXiv]
• Bit-Swap: Recursive bits-back coding for lossless compression with hierarchical latent variables
  Friso H. Kingma, Pieter Abbeel, Jonathan Ho
  International Conference on Machine Learning, 2019
  [arXiv]
• Evolved policy gradients
  Rein Houthooft, Richard Y. Chen, Phillip Isola, Bradly C. Stadie, Filip Wolski, Jonathan Ho, Pieter Abbeel
  Neural Information Processing Systems, 2018
  [arXiv]
• Meta learning shared hierarchies
  Kevin Frans, Jonathan Ho, Xi Chen, Pieter Abbeel, John Schulman
  International Conference on Learning Representations, 2018
  [arXiv]
• One-shot imitation learning
  Yan Duan, Marcin Andrychowicz, Bradly Stadie, Jonathan Ho, Jonas Schneider, Ilya Sutskever, Pieter Abbeel, Wojciech Zaremba
  Neural Information Processing Systems, 2017
  [pdf] [arXiv]
• Generative adversarial imitation learning
  Jonathan Ho, Stefano Ermon
  Neural Information Processing Systems, 2016
  [pdf] [code]
• Model-free imitation learning with policy optimization
  Jonathan Ho, Jayesh K. Gupta, Stefano Ermon
  International Conference on Machine Learning, 2016
  [pdf] [arXiv]
• Generalization in robotic manipulation through the use of non-rigid registration
  John Schulman, Jonathan Ho, Cameron Lee, Pieter Abbeel
  International Symposium on Robotics Research, 2013
  [pdf] [website]
• Finding locally optimal, collision-free trajectories with sequential convex optimization
  John Schulman, Jonathan Ho, Alex Lee, Ibrahim Awwal, Henry Bradlow, Pieter Abbeel
  Robotics: Science and Systems, 2013
  [pdf] [website]
• Tracking deformable objects with point clouds
  John Schulman, Alex Lee, Jonathan Ho, Pieter Abbeel
  International Conference on Robotics and Automation, 2013
  [pdf] [website]