My name is Rattana Pukdee. I am a fourth year PhD student in the Machine Learning Department at Carnegie Mellon University working with Prof. Nina Balcan and Prof. Pradeep Ravikumar. My PhD is supported by the Bloomberg Data Science PhD fellowship. I am particularly interested in the theoretical aspect of learning with side information e.g. domain knowledge, unlabeled data, explanations. Previously, I obtained a master degree in Mathematics from the University of Oxford. I do photography in my free time and you can find some of my works here.

Papers

Spectrally Transformed Kernel Regression
Runtian Zhai, Rattana Pukdee, Roger Jin, Maria-Florina Balcan, Pradeep Ravikumar
ICLR 2024 (Spotlight), Paper

Reliable Learning in Challenging Environments
Maria-Florina Balcan, Steve Hanneke, Rattana Pukdee, Dravyansh Sharma
NeurIPS 2023, Paper

Learning with Explanation Constraints
Rattana Pukdee, Dylan Sam, J. Zico Kolter, Maria-Florina Balcan, Pradeep Ravikumar
NeurIPS 2023 Paper

Bayesian Neural Networks with Domain Knowledge
Dylan Sam, Rattana Pukdee, Daniel P. Jeong, Yewon Byun, J. Zico Kolter
ICML KLR Workshop 2023 (Oral)

Nash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Games
Maria-Florina Balcan, Rattana Pukdee, Pradeep Ravikumar, Hongyang Zhang
AISTATS 2023 Paper

Label Propagation with Weak Supervision
Rattana Pukdee, Dylan Sam, Maria-Florina Balcan, Pradeep Ravikumar
ICLR 2023 Paper

Sharp Asymptotics on the Compression of Two-layer Neural Networks
Mohammad Hossein Amani, Simone Bombari, Marco Mondelli, Rattana Pukdee, Stefano Rini
ITW 2022 Paper

Improving Transformation Invariance in Contrastive Representation Learning
Adam Foster, Rattana Pukdee, Tom Rainforth
ICLR 2021, Paper, Code, Dataset