Chen Dan 丹晨
I am a final year Ph.D. student at Computer Science Department, Carnegie Mellon University, advised by Pradeep Ravikumar (previously also co-advised by Avrim Blum). Prior to this, I received B.Sc from School of EECS, Peking University, where I worked with Liwei Wang.
My research interest is in the broad area of robust statistical learning, with an emphasis on the theoretical understanding and practical algorithms for learning under various types of adversarial distribution shift. This encompasses many new challenges in ML, including:
- Adversarial Examples: See e.g. my papers in ICML'20a and ICLR'20;
- Class/Group Imbalance: ICML'21 and ICML'20b;
- Outliers in Data: ICML'21.
Email: cdan at cs dot cmu dot edu ; You may also find me on Google Scolar, DBLP, and Twitter.
News
- [September 2021] Our Paper Boosted CVaR Classification has been accepted to NeurIPS 2021. ArXiv version to be available soon!
- [May 2021] Our Paper DORO: Distributional and Outlier Robust Optimization has been accepted to ICML 2021. arXiv
- [January 2021] Our paper Learning Complexity of Simulated Annealing has been accepted by AISTATS 2021. arXiv
- [May 2020] Our paper Sharp Statistical Guarantees for Adversarially Robust Gaussian Classification has been accepted by ICML 2020. arXiv
- [May 2020] Our paper Class-Weighted Classification: Trade-offs and Robust Approaches has been accepted by ICML 2020. arXiv
- More...