Centers & Labs

RIKEN Center for Advanced Intelligence Project

Approximate Bayesian Inference Team

Team Leader: Mohammad Emtiyaz Khan (Ph.D.)
Mohammad Emtiyaz  Khan(Ph.D.)

Our main goal is to understand the principles of learning from data and use them to develop algorithms that can learn like living beings. Our current focus is on sequential learning and exploration. We are working on problems in several areas of machine learning, such as approximate inference, deep learning, reinforcement learning, active learning, online learning, and reasoning in computer vision. In our recent works, we have combined ideas from a wide range of fields, such as, optimization, Bayesian statistic, information geometry, signal processing, and control systems.

Research Subjects

  • Machine Learning
  • Statistics
  • Artificial Intelligence

Main Research Field

Computer Science

Selected Publications

Papers with an asterisk(*) are based on research conducted outside of RIKEN.
  1. A. Miskin, F. Kunstner, D. Nielsen, M. Schmidt, M.E. Khan.:
    “SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient”
    NEURAL INFORMATION PROCESSING (NeurIPS) (2018)
  2. M.E. Khan and D. Nielsen.:
    “Fast yet Simple Natural-Gradient Descent for Variational Inference in Complex Models”
    International Symposium on Information Theory and Its Applications (ISITA) (2018)
  3. M.E. Khan, D. Nielsen, V. Tangkaratt, W. Lin, Y. Gal, and A. Srivastava.:
    “Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam”
    INTERNATIONAL CONFERENCE OF MACHINE LEARNING (ICML) (2018)
  4. W. Lin, N. Hubacher, and M.E. Khan.:
    “Variational Message Passing with Structured Inference Networks”
    International Conference on Learning Representations(ICLR), (2018).
  5. H. Ding, M.E. Khan, I. sato, M. Sugiyama.:
    “Bayesian Nonparametric Poisson-Process Allocation for Time-Sequence Modeling”
    Artificial Intelligence and Statistics(AISTATS), (2018).
  6. M.E. Khan and W. Lin.:
    “Conjugate-Computation Variational Inference.: Converting Variational Inference in Non-Conjugate Models to Inferences in Conjugate Models”
    Artificial Intelligence and Statistics(AISTATS), (2017).
  7. *M.E. KHAN, P. BAQUE, F. FLEURET, P. FUA.:
    “Kullback-Leibler Proximal Variational Inference”
    NEURAL INFORMATION PROCESSING (NIPS), (2015).
  8. *M.E. KHAN , A. ARAVKIN, M. FRIEDLANDER, M. SEEGER.:
    “Fast Dual Variational Inference for Non-Conjugate Latent Gaussian Models”
    INTERNATIONAL CONFERENCE OF MACHINE LEARNING (ICML), (2013).
  9. *M.E. KHAN , S. MOHAMED, K. MURPHY.:
    “Fast Bayesian Inference for Non-Conjugate Gaussian Process Regression”
    NEURAL INFORMATION PROCESSING (NIPS), (2012).
  10. *B. MARLIN, M. E. KHAN, K. MURPHY.:
    “Piecewise Bounds for Estimating Bernoulli-Logistic Latent Gaussian Models”
    INTERNATIONAL CONFERENCE OF MACHINE LEARNING (ICML), (2011).

Lab Members

Principal Investigator

Mohammad Emtiyaz Khan
Team Leader

Core Members

Pierre Alquier
Research Scientist
Hongyi Ding
Postdoctoral Researcher
Xiangming Meng
Postdoctoral Researcher
Dharmesh Vijay Tailor
Technical Staff I
Vincent Tan Weng Choon
Technical Staff I