I have a broad interest in both the math and the scientific worlds, and I am open to new knowledge at all time. Currently, I am a research engineer at Deepmind, with a focus on applying pioneer machine learning techniques to large-scale, real-world products.
In 2021, I defended my PhD from the University of Amsterdam, supervised by my amazing advisors Prof. Max Welling and Dr. Herk van Hoof. My research interests include representation learning, generative modeling, and reinforcement learning.
My PhD thesis (here) is dedicated to Granvil Keith George, whose spirit has supported me throughout my research career.
My undergraduate honor thesis advisor, Professor Bourdon, also has nourished me with the heart of humanity: compassion, caring and selflessness.
My Masters degree was in Applied Mathematics from the University of Michigan.
E-mail: wendyshang at deepmind.com
Publications and Preprints
Reproducing Kernel Hilbert Spaces Supporting Nontrivial Hermitian Weighted Composition Operators.
P. Bourdon and W. Shang. Complex Analysis and Operator Theory, 2011.
Talks and Posters
Discriminative Training Of Structured Dictionaries Via Orthogonal Matching Pursuit.
Women in Machine Learning Workshop, 2014.
The Weighted Composition Operators in Hilbert Spaces. (won the poster award)
the Joint Math Meetings Student Poster Session, 2011.
On the Norm Preservation Properties of Convolutional Neural Networks.
Women in Machine Learning Workshop, 2015.
Convolutional Neural Networks for Crop Yield Prediction using Satellite Images.
Helena Russello, Masters of AI, 2018. (co-advised with Dr. Santiago Gaitan, IBM)
An Empirical Comparison of Deep Conditional Generative Models with Applications to Attribute-Guided Face Synthesis.
Kewin Dereniewicz, Masters of Data Science, 2018. (co-advised with Benjamin Timmermans, IBM)
Learning World Graphs for Accelerated Hierarchical Reinforcement Learning.
W. Shang, A.Trott*, S. Zheng*, C. Xiong, R. Socher. ICML Real-world Sequential Decision Making workshop, 2019. [project page]
Learning to Navigate Wikipedia by Taking Random Walks.
M. Zaheer, K. Marino, W. Grathwohl, J. Schultz, W. Shang,
S. Babayan, A. Ahuja, I. Dasgupta, C. Kaser-Chen, R. Fergus
Neurips 2022. [PDF]
MuZero with Self-competition for Rate Control in VP9 Video Compression.
A. Mandhane, A. Zhernov, M. Rauh, C. Gu, M. Wang, F. Xue, W. Shang
D. Pang, R. Claus, C. Chiang, C. Chen, J. Han, A. Chen, D. Mankowitz, J. Broshear, J. Schrittwieser, T. Hubert, O. Vinyals
Reinforcement Learning with Latent Flow.
W. Shang*, X. Wang*, A. Lakshminarayanan, A. Rajeswaran, Y. Gao, P. Abbeel, M. Laskin
Neurips 2021. [code and PDF]
selected as a contributive talk at Neurips, Deep RL Workshop, 2020.
Agent-Centric Representations for Multi-agent Reinforcement Learning.
W. Shang, L. Espeholt, A. Raichuk, T. Salimans. 2020 [project page]
Decompose Video Representations from Temporal Coherence and Dynamics.
W. Shang, S. Liu, A. Vahdat, S. De Mello, J. Kautz. 2019 [project page]
Stochastic Activation Actor-Critic Methods.
W. Shang, H. van Hoof, M. Welling. ECML-PKDD 2019. [code and PDF]
selected as a contributive talk at UAI, Uncertainty in Deeplearning Workshop, 2018.
Unsupervised Domain Adaptation for Distance Metric Learning
K. Sohn. W. Shang, X. Yu, M. Chandraker. ICLR, 2019.
Attentive Conditional Channel-Recurrent Autoencoding for Attribute Conditioned Face Synthesis
W. Shang, K. Sohn. WACV, 2019. [code and PDF]
Channel-Recurrent Autoencoding for Image Modeling
W. Shang, K. Sohn, Y. Tian. WACV, 2018. [code and PDF]
ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games
Yuandong Tian, Qucheng Gong, W. Shang, Yuxin Wu and Larry Zitnick. NIPS, 2017.
Exploring Normalization in Deep Residual Networks with Concatenated Rectified Linear Units
W. Shang, J. Chiu, and K. Sohn. AAAI, 2017.
Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units
W. Shang, K. Sohn, D. Almeida and H. Lee. ICML, 2016.
Discriminative Training of Structured Dictionaries via Block Orthogonal Matching Pursuit
W. Shang, K. Sohn, and H. Lee. Siam SDM, 2016.
Improved Multimodal Deep Learning with Variation of Information.
K. Sohn, W. Shang, H. Lee. NIPS, 2014.
A Moment-based Approach for DVH-guided Radiotherapy Treatment Plan.
M. Zarepisheh, M. Shakourifar, G. Trigila, P. Ghomi, S. Couzens, A. Abebe, L. Norena, W. Shang, S. Jiang and Y. Zinchenko. Physics in Medicine and Biology, 2013.
Normal Weighted Composition Operators on Weighted Dirichlet Spaces.
L. Lu, Y. Nakada, D. Nestor, W. Shang and R. Weir. JMAA, 2014.
Neurips, ICML, CVPR, ICCV, UAI, AISTATS, AAAI,
Transactions on Computational Intelligence and AI in Games, Transactions on Neural Networks and Learning Systems .
Computer Vision Software Engineer.
Oculus, Menlo Park, CA, Spring 2016-Fall 2017.
Salesforce Research, Palo Alto, CA, Spring 2019.
NVIDIA Research, Santa Clara, CA, Summer 2019.
Deepmind, NY, NY, Fall 2020-Now.
Google Brain, Amsterdam, NL, Spring 2020.
UC Berkeley, Berkeley, CA, Summer 2020.