Ziyu Wang
I'm a PhD student in Tsinghua University, supervised by Profs Jun Zhu and Bo Zhang.
I work in (primarily probablistic) machine learning. I'm particularly interested in uncertainty estimation, and the interactions between theory, computation and applications.
You can reach me through gmail at wzy196. My CV.
Other persons with the same name.
Publications

Scalable QuasiBayesian Inference for Instrumental Variable Regression.
Ziyu Wang*, Yuhao Zhou*, Tongzheng Ren, Jun Zhu
Short version (PDF) to appear in NeurIPS.
TL;DR
 QuasiBayesian inference for kernelized and (heuristically) NNparameterized IV models, based on the dual/minimax formulation of IVR.
 QuasiBayes is needed for IV because we can't do Bayesian modeling, which is because we don't know the full data generating process.
 A guess will be wrong, and still difficult to make use of, because you will have to do Bayesian inference over deep [conditional] generative models.
 But still, theory and computation are not straightforward.
 We prove posterior consistency (more theory coming soon), and derive an inference algorithm with a modified randomized prior trick.

Fork or Fail: CycleConsistent Training with ManytoOne Mappings.
Qipeng Guo, Zhijing Jin, Ziyu Wang, Xipeng Qiu, Weinan Zhang, Jun Zhu, Zheng Zhang, David Wipf.
AISTATS 2021.
PDF
TL;DR
 Domain alignment without paired data, when bijections do not exist.

Further Analysis of Outlier Detection with Deep Generative Models.
Ziyu Wang, Bin Dai, David Wipf, Jun Zhu.
NeurIPS 2020.
PDF
Code
Poster
Slides
TL;DR
 This is about the observation that DGMs assign higher likelihood to semantically different outliers.
Intuitively this is due to concentration of measure/typicality ("Gaussian distributions are soap bubbles"), but it seemed difficult to confirm empirically.
 We argue previous attempts relied on tests that were more prone to estimation error, and propose a fix which connects to the idea of atypicality and the longitudinal view of highdimensional data.
 A few other observations are difficult to summarize, so check out the paper if you're interested.

The Usual Suspects? Reassessing Blame for VAE Posterior Collapse.
Bin Dai, Ziyu Wang, David Wipf.
ICML 2020.
PDF
TL;DR
 Reasons for posterior collapse in nonlinear VAEs, which may or may not be similar to the linear case.
 Of particular importance is the practicality of designing AE architecture with low reconstruction errors.

Practicality: [n.] Quality of being suitable for a particular occasion or use. The possibility of being put into practice.

A Wasserstein Minimum Velocity Approach to Learning Unnormalized Models.
Ziyu Wang, Shuyu Cheng, Yueru Li, Jun Zhu, Bo Zhang.
AISTATS 2020.
PDF
Code
AABI Poster
TL;DR
 An alternative approximation to the score matching objectives, which works with DNNs. And generalizations.
 The title was a tribute to the unpublished work "A Minimum Velocity Approach to Learning".

Function Space Particle Optimization for Bayesian Neural Networks.
Ziyu Wang, Tongzheng Ren, Jun Zhu, Bo Zhang.
ICLR 2019.
PDF
Code
Poster
TL;DR
 A cute SVGD/ParVIlike algorithm, but in function space. GIF.
 The functionspace view is important for overparameterized priors like BNNs, because there is a combinatorial number of local maximas in the "weight space", and you can't believe your inference algorithm covers them all.
Too bad we still haven't figured out how to do it properly (in the general case), after all these years.
 But if you can afford to train an ensemble of models, this works well in practice.
Miscellaneous
Reading group slides:
Random quotes.