Short Bio

Yao-Yuan is currently working in DeepMind. He received his Ph.D. in 2022 from the Computer Science and Engineering department of UCSD, advised by Professor Kamalika Chaudhuri. His thesis was on trustworthy machine learning, which includes topics such as adversarial examples, interpretability, and spurious correlations. Prior to joining UCSD, he received his B.S. in Computer Science from National Taiwan University in 2016.

Here are my CV, research statement, and three representative papers (paper1, paper2, paper3).

Here are some problems he previously worked on:

  • Cost-sensitive multi-label classification
  • Active learning
  • Brain decoding with electroencephalogram (EEG)

News

Experiences

Publications

Preprints

Postprints

Presentations

What You See is What You Get: Distributional Generalization for Algorithm Design in Deep Learning
UCSD, La Jolla, CA, March 2022 [link]
What You See is What You Get: Distributional Generalization for Algorithm Design in Deep Learning
Apple, Virtual, March 2022
A Closer Look at Accuracy vs. Robustness
INFORMS annual meeting, Anaheim, CA, October 2021 [link]
In- and Out-of-Distribution Generalization Properties of Adversarially Robust Models
Science of Deep Learning at Facebook, Virtual, August 2021
Close Category Generalization for Out-of-Distribution Classification
SoCal ML Symposium 2021, Virtual, March 2021
A Closer Look at Accuracy vs. Robustness
SoCal ML Symposium 2021, Virtual, March 2021
A Closer Look at Accuracy vs. Robustness
G-Research, Virtual, January 2021 [slide]
A Closer Look at Accuracy vs. Robustness
NeurIPS 2020, Virtual, December 2020 [video]
Robustness for Non-Parametric Classification: A Generic Attack and Defense
AISTATS 2020, Virtual, August 2020 [video] [slide]
A Closer Look at Accuracy vs. Robustness
ICML UDL 2020, Virtual, June 2020 [video] [slide]
Deep Learning with a Rethinking Structure for Multi-label Classification
ACML, Nagoya, Japan, November 2019 [slide] [poster]
Deep Learning with a Rethinking Structure for Multi-label Classification
ACML-Mol, Beijing, China, November 2018 [slide]
Cost-Sensitive Reference Pair Encoding for Multi-Label Learning
PAKDD, Melbourne, Australia, June 2018 [slide]
Cost-Sensitive Random Pair Encoding for Cost-Sensitive Multi-Label Classification
NTU Machine Learning Symposium, Taipei, Taiwan, December 2016 [slide]
Near-uniform Aggregation of Gradient Boosting Machines for KDD Cup 2015
KDD, Sydney, Australia, August 2015 [slide]
Introduction to Machine Learning: Teaching Machine to Read Gestures
SITCON, Taipei, Taiwan, March 2015 [slide]

Awards

Projects