Ping-yeh Chiang

PhD student, University of Maryland, College Park

Joined

September 2019

Names

Ping-yeh Chiang (Preferred)

Emails

****@cs.umd.edu (Confirmed)

****@gmail.com (Confirmed)

****@umd.edu (Confirmed)

Personal Links

Google Scholar

DBLP

Career & Education History

PhD student

University of Maryland, College Park (umd.edu)

2018 – Present

Advisors, Relations & Conflicts

PhD Advisor

Tom Goldstein

2018 – Present

Expertise

adversarial robustness

Present

certified adversarial robustness

Present

robustness to domain shift

Present

Publications

NEFTune: Noisy Embeddings Improve Instruction Finetuning
Neel Jain, Ping-yeh Chiang, Yuxin Wen, John Kirchenbauer, Hong-Min Chu, Gowthami Somepalli, Brian R. Bartoldson, Bhavya Kailkhura, Avi Schwarzschild, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein
- ICLR 2024 poster
- Readers: Everyone
Baseline Defenses for Adversarial Attacks Against Aligned Language Models
Neel Jain, Avi Schwarzschild, Yuxin Wen, Gowthami Somepalli, John Kirchenbauer, Ping-yeh Chiang, Micah Goldblum, Aniruddha Saha, Jonas Geiping, Tom Goldstein
- Submitted to ICLR 2024
- Readers: Everyone
Active Learning at the ImageNet Scale
Hong-Min Chu, Ping-yeh Chiang, Zeyad Emam, Wojciech Czaja, Richard Leapman, Micah Goldblum, Tom Goldstein
- 22 Sept 2022 (modified: 14 Jan 2026)
- ICLR 2023 Conference Withdrawn Submission
- Readers: Everyone
K-SAM: Sharpness-Aware Minimization at the Speed of SGD
Renkun Ni, Ping-yeh Chiang, Jonas Geiping, Micah Goldblum, Andrew Gordon Wilson, Tom Goldstein
- Published: 01 Feb 2023, Last Modified: 13 Feb 2023
- Submitted to ICLR 2023
- Readers: Everyone
Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient Descent
Ping-yeh Chiang, Renkun Ni, David Yu Miller, Arpit Bansal, Jonas Geiping, Micah Goldblum, Tom Goldstein
- Published: 01 Feb 2023, Last Modified: 02 Mar 2023
- ICLR 2023 notable top 25%
- Readers: Everyone
Certified Neural Network Watermarks with Randomized Smoothing
Arpit Bansal, Ping-yeh Chiang, Michael J. Curry, Rajiv Jain, Curtis Wigington, Varun Manjunatha, John P. Dickerson, Tom Goldstein
- 2022 (modified: 14 Nov 2022)
- CoRR 2022
- Readers: Everyone
K-SAM: Sharpness-Aware Minimization at the Speed of SGD
Renkun Ni, Ping-yeh Chiang, Jonas Geiping, Micah Goldblum, Andrew Gordon Wilson, Tom Goldstein
- 2022 (modified: 14 Nov 2022)
- CoRR 2022
- Readers: Everyone
Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective
Gowthami Somepalli, Liam Fowl, Arpit Bansal, Ping-Yeh Chiang, Yehuda Dar, Richard G. Baraniuk, Micah Goldblum, Tom Goldstein
- 2022 (modified: 14 Nov 2022)
- CoRR 2022
- Readers: Everyone
Certified Neural Network Watermarks with Randomized Smoothing
Arpit Bansal, Ping-Yeh Chiang, Michael J. Curry, Rajiv Jain, Curtis Wigington, Varun Manjunatha, John P. Dickerson, Tom Goldstein
- 2022 (modified: 14 Nov 2022)
- ICML 2022
- Readers: Everyone
Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective
Gowthami Somepalli, Liam Fowl, Arpit Bansal, Ping-Yeh Chiang, Yehuda Dar, Richard G. Baraniuk, Micah Goldblum, Tom Goldstein
- 2022 (modified: 14 Nov 2022)
- CVPR 2022
- Readers: Everyone

View all 31 publications

Co-Authors

View all 56 co-authors