Yeming Wen

I am a first-year graduate student in Machine Learning Group at the University of Toronto and Vector Institute, studying under Jimmy Ba and Roger Grosse. I recieved my bachelors at the University of Toronto in 2017.

Email  /  CV  /  Scholar  /  LinkedIn


My research interests focus on the development of efficient learning algorithms for deep neural networks. In particular, how to properly regularize deep neural networks such that it can continuously learn a number of tasks and generalize better.

BatchEnsemble: an Alternative Approach to Efficient Ensemble and Lifelong Learning
Yeming Wen, Dustin Tran & Jimmy Ba
8th International Conference on Learning Representations (ICLR), 2020
Bayesian Deep Learning Workshop at NeurIps, 2019

How to efficiently ensemble deep neural networks efficiently in both computation and memory.

Benchmarking Model-Based Reinforcement Learning
Tingwu Wang, Xuchan Bao, Ignasi Clavera, Jerrick Hoang, Yeming Wen, Eric Langlois, Shunshi Zhang, Guodong Zhang, Pieter Abbeel & Jimmy Ba
Arxiv, 2019

Benchmarking several commonly used model-based algorithms.

Interplay Between Optimization and Generalization of Stochastic Gradient Descent with Covariance Noise
Yeming Wen*, Kevin Luk*, Maxime Gazeau*, Guodong Zhang, Harris Chan & Jimmy Ba
23rd International Conference on Artificial Intelligence and Statistics (AISTATS), 2020

How to add a noise to gradients with correct covariance structure such that large-batch training genenalizes better without longer training.

Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches
Yeming Wen, Paul Vicol, Jimmy Ba, Dustin Tran & Roger Grosse
6th International Conference on Learning Representations (ICLR), 2018

How to efficiently make psedo-independent weight perturbations on mini-batches in evolution strategies and variational BNNs as activation perturbations in dropout.

Last Update: June, 16th, 2018;
Template: this/that, ce/cette, das/der, kono/sono and zhege/nage.