Hey I’m Kai

Scholar GitHub Email Twitter

I’m a machine learning researcher interested in learning and inference methods for generative models and their (unexplored) real-world applications. I did my Ph.D with Charles Sutton at the Institute for Adaptive and Neural Computation of the University of Edinburgh. Before this, I worked with Zoubin Ghahramani for one and a half years at the Cambridge Machine Learning Group.

I’m a core member of the Turing team that builds the Turing probabilistic programming language in Julia. I will be joining Amazon as a research scientist in late 2022 to work on probabilistic {web, CAD} designs. Until then, I’m working on differentiable private generative models at Hazy, a startup on synthetic data generation.

\[\ast\] denotes equal contributions

Papers

Conference

  •  \[\newtag\] Kai Xu, Akash Srivastava, Dan Gutfreund, Felix Sosa, Tomer Ullman, Joshua B. Tenenbaum, Charles Sutton. “A Bayesian-Symbolic Approach to Learning and Reasoning for Intuitive Physics.”, Neural Information Processing Systems (NeurIPS), 2021. [OpenReview, website, code]
  •  \[\newtag\] Cole L. Hurwitz, Akash Srivastava, Kai Xu, Justin Jude, Matt Perich, Lee E. Miller, Matthias H. Hennig. “Targeted Neural Dynamical Modeling.”, Neural Information Processing Systems (NeurIPS), 2021. [OpenReview]
  •  \[\newtag\] Kai Xu, Rajkarn Singh, Marco Fiore, Mahesh K. Marina, Hakan Bilen, Muhammad Usama, Howard Benn, Cezary Ziemlicki. “SpectraGAN: Spectrum based Generation of City Scale Spatiotemporal Mobile Network Traffic Data”, International Conference on emerging Networking EXperiments and Technologies (CoNEXT; 17% acceptance rate), 2021. [ACM, dataset]
  • Kai Xu\[\ast\], Rajkarn Singh\[\ast\], Hakan Bilen, Marco Fiore, Mahesh K. Marina, Yue Wang. “CartaGenie: Context-Driven Synthesis of City-Scale Mobile Network Traffic Snapshots”, International Conference on Pervasive Computing and Communications (PerCom; acceptance rate < 20%), 2022. [IEEE, dataset]
  • Kai Xu\[\ast\], Tor Erlend Fjelde\[\ast\], Charles Sutton, Hong Ge. “Couplings for Multinomial Hamiltonian Monte Carlo.”, International Conference on Artificial Intelligence and Statistics (AISTATS), 2021. Oral (top 10% of accepted papers) [abs, pdf, arXiv, code]
  • Benjamin Rhodes, Kai Xu, Michael U. Gutmann “Telescoping Density-Ratio Estimation.”, Neural Information Processing Systems (NeurIPS), 2020. Spotlight (top 20% of accepted papers) [abs, pdf, arXiv]
  • Akash Srivastava\[\ast\], Kai Xu\[\ast\], Michael U. Gutmann and Charles Sutton. “Generative Ratio Matching Networks.”, International Conference on Learning Representations (ICLR), 2020. [pdf, OpenReview, code]
  • Cole L. Hurwitz, Kai Xu, Akash Srivastava, Alessio Paolo Buccino and Matthias Hennig. “Scalable Spike Source Localization in Extracellular Recordings using Amortized Variational Inference.”, Neural Information Processing Systems (NeurIPS), 2019. [abs, pdf, arXiv]
  • Kai Xu, Akash Srivastava and Charles Sutton. “Variational Russian Roulette for Deep Bayesian Nonparametrics.”, International Conference on Machine Learning (ICML), 2019. [abs, pdf, suppl, code]
  • Hong Ge, Kai Xu, and Zoubin Ghahramani. “Turing: A Language for Flexible Probabilistic Inference.”, International Conference on Artificial Intelligence and Statistics (AISTATS), 2018. [abs, pdf, code, website]

Workshop

  • Kai Xu, Hong Ge, Will Tebbutt, Mohamed Tarek, Martin Trapp, Zoubin Ghahramani. “AdvancedHMC.jl: A robust, modular and efficient implementation of advanced HMC algorithms.”, Symposium on Advances in Approximate Bayesian Inference (AABI), 2019. [abs, pdf, OpenReview]
  • Tor Erlend Fjelde, Kai Xu, Mohamed Tarek, Sharan Yalburgi, Hong Ge. “Bijectors.jl: Flexible transformations for probability distributions.”, Symposium on Advances in Approximate Bayesian Inference (AABI), 2019. [abs, pdf, OpenReview]

Preprint

  • Mohamed Tarek, Kai Xu, Martin Trapp, Hong Ge, Zoubin Ghahramani. “DynamicPPL: Stan-like Speed for Dynamic Probabilistic Models.”, arXiv preprint arXiv: 2002.02702, 2020. [arXiv]
  • Kai Xu, Dae Hoon Park, Yi Chang and Charles Sutton. “Interpreting Deep Classifiers by Visual Distillation of Dark Knowledge.”, arXiv preprint arXiv: 1803.04042, 2018. [arXiv, pdf, demo, code, website]

Software

  • Turing.jl: Bayesian inference with probabilistic programming. [GitHub, website]
  • AdvancedHMC.jl: Robust, modular and efficient implementation of advanced Hamiltonian Monte Carlo algorithms. [GitHub]
  • DensityRatioEstimation.jl: A Julia package for density ratio estimation. [GitHub]

Professional Services

Journal reviewing

Journal of Machine Learning Research (JMLR)

Conference reviewing

Neural Information Processing Systems (NeurIPS), International Conference on Machine Learning (ICML), International Conference on Learning Representations (ICLR) and International Conference on Artificial Intelligence and Statistics (AISTATS)

Pre-Ph.D / Casual Projects

  • Mobile Robot Control using ROS [poster]
  • DBD Plasma Reactor Power Monitoring System
  • Wireless Brain-Computer Interface for Game Control [video]
  • FlatShare [code]
  • Gravity Snake [demo, code]: You control the snake via accelerometers—the snake always heads downwards and you need to steer it by rotating your phone!

Hobbies

↑

Created via Emacs with Org mode | Styled by Nord | Updated on 19 Apr 2022

Copyright © 2022, Kai Xu