Publications

(To save your time you are encouraged to look at the cartoon illustrations for a taste ūüėÜ)

Working papers

Yingzhen Li and Richard E. Turner. Gradient Estimators for Implicit Models. Submitted to NIPS 2017. cartoon

Yingzhen Li, Richard E. Turner and Qiang Liu. Approximate Inference with Amortised MCMC. Submitted to NIPS 2017. cartoon

Yingzhen Li and Qiang Liu. Wild Variational Approximations. preprint presented in NIPS Advances in approximate inference, 2016. cartoon

Refereed conference papers

Yingzhen Li and Yarin Gal. Dropout Inference in Bayesian Neural Networks with Alpha-divergences. accepted at ICML 2017. cartoon

Yingzhen Li and Richard E. Turner. Rényi Divergence Variational Inference. Neural Processing Information Systems (NIPS), 2016.    (Previously titled "Variational Inference with Rényi Divergence") code  cartoon

Jos√© Miguel Hern√°ndez-Lobato*, Yingzhen Li*, Mark Rowland, Daniel Hern√°ndez-Lobato, Thang Bui¬†and¬†Richard E. Turner. Black-box őĪ-divergence Minimization. International Conference on Machine Learning (ICML), 2016.¬† code cartoon

Thang Bui, Daniel Hernández-Lobato, José Miguel Hernández-Lobato, Yingzhen Li and Richard E. Turner. Deep Gaussian Processes for Regression using Approximate Expectation Propagation. International Conference on Machine Learning (ICML), 2016.  code cartoon

Yingzhen Li, Jose Miguel Hernandez-Lobato and Richard E. Turner. Stochastic Expectation Propagation. Neural Processing Information Systems (NIPS), 2015 (spotlight, 4.5%).  demo cartoon

 

Preprints

Yingzhen Li and Richard E. Turner. A Unifying Approximate Inference Framework from Variational Free Energy Relaxation. NIPS Advances in approximate inference workshop, 2016

Daniel Hernández-Lobato, José Miguel Hernández-Lobato, Yingzhen Li, Thang Bui and Richard E. Turner. Stochastic Expectation Propagation for Large Scale Gaussian Process Classification. NIPS Advances in approximate inference workshop (contributed talk), 2015

Yingzhen Li and Ye Zhang. Generating ordered list of Recommended Items: a Hybrid Recommender System of Microblog. 2012

 

Talks

Approximate inference with amortised MCMC. CamAIML workshop, Mar 2017

Objective functions for variational auto-encoders. @ Twitter Cortex Vx (previously Magic Pony), Sept 2016

Variational inference with Rényi divergence. MSR-MLG joint workshop, Mar 2016

Alpha divergence back to conversation. Research Talk @ CBL, Feb 2016

Stochastic optimisation and adaptive learning rates. Reading Group Talk @ CBL (with Mark Rowland), Nov 2015 [code]

Concave-convex procedure. Tea Talk @ CBL, Oct 2015

Expectation propagation as a way of life. Tea Talk @ CBL, Feb 2015. [reference]

Introduction to transfer learning. Reading Group Talk @ CBL (with Pei-Hao Su), Jan 2015.

Bayesian learning for restricted Boltzmann machines. Research Talk @ CBL, Nov 2014.

On Restricted Boltzmann Machine Learning. Guest Talk @ Dept of Math, SYSU, Jun 2014.

Loopy Belief Propagation. RCC Talk @ CBL (with Alex Matthews), Apr 2014.

The Importance of Encoding. Tea Talk @ CBL, Feb 2014. [reference]

IT & ML: Channels, Quantizers, and Divergences. RCC Talk @ CBL (with Antonio Artés-Rodríguez), Jan 2014.

 

Thesis

Compressed Sensing and Related Learning Problems. B.S. in Mathematics, Sun Yat-sen University, May 2013. (Best B.S. Thesis Award). [slides]

 

Things I've done in my undergrad years