Aditi Raghunathan

Ph.D

Stanford University

Show Academic Trajectory

Ego Network

D-Core

Research Interests

Author Statistics

Experience

Education

Bio

I am interested in designing algorithms that are robust to meaningful perturbations, transformations and distribution shifts. I have two different but related motivations and interpretations of this goal.

Papers21 papers

Sort

By YearBy Citation

DROCC: Deep Robust One-Class Classification

Goyal Sachin,Raghunathan Aditi, Jain Moksh,Simhadri Harsha Vardhan,Jain Prateek

ICML, pp.3711-3721, (2020)

Cited by1EIBibtex

Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming

Sumanth Dathathri,Krishnamurthy Dvijotham,Alexey Kurakin,Aditi Raghunathan, Jonathan Uesato, Rudy Bunel, Shreya Shankar,Jacob Steinhardt,Ian Goodfellow,Percy Liang,Pushmeet Kohli

NIPS 2020, (2020)

EIBibtex

Explore then Execute: Adapting without Rewards via Factorized Meta-Reinforcement Learning

Evan Zheran Liu,Aditi Raghunathan,Percy Liang,Chelsea Finn

Bibtex

The Pitfalls of Simplicity Bias in Neural Networks

Shah Harshay,Tamuly Kaustav,Raghunathan Aditi,Jain Prateek,Netrapalli Praneeth

NIPS 2020, (2020)

EIBibtex

An Investigation of Why Overparameterization Exacerbates Spurious Correlations

Shiori Sagawa,Aditi Raghunathan,Pang Wei Koh,Percy Liang

ICML 2020, (2020)

Bibtex

An Investigation of Why Overparameterization Exacerbates Spurious Correlations

Sagawa Shiori,Raghunathan Aditi,Koh Pang Wei,Liang Percy

ICML, pp.8346-8356, (2020)

EIBibtex

Robust Encodings: A Framework for Combating Adversarial Typos

Jones Erik,Jia Robin,Raghunathan Aditi,Liang Percy

ACL, pp.2752-2765, (2020)

EIBibtex

Understanding and Mitigating the Tradeoff Between Robustness and Accuracy

Raghunathan Aditi, Xie Sang Michael,Yang Fanny,Duchi John,Liang Percy

ICML, pp.7909-7919, (2020)

Cited by1EIBibtex

Overparameterization hurts worst-group accuracy with spurious correlations

Shiori Sagawa,Aditi Raghunathan,Pang Wei Koh,Percy Liang

international conference on machine learning, (2020)

Bibtex

Certified Robustness to Adversarial Word Substitutions

Robin Jia,Aditi Raghunathan, Kerem Göksel,Percy Liang

EMNLP/IJCNLP (1), pp.4127-4140, (2019)

Cited by9EIBibtex

Adversarial Training Can Hurt Generalization

Aditi Raghunathan, Sang Michael Xie,Fanny Yang,John C. Duchi,Percy Liang

CoRR, (2019)

Cited by16EIBibtex

Maximum Weighted Loss Discrepancy

Fereshte Khani,Aditi Raghunathan,Percy Liang

CoRR, (2019)

Cited by2EIBibtex

Unlabeled Data Improves Adversarial Robustness

Yair Carmon,Aditi Raghunathan, Ludwig Schmidt,Percy Liang,John C. Duchi

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), (2019)

Cited by86EIBibtex

Unlabeled Data Improves Adversarial Robustness

Yair Carmon,Aditi Raghunathan, Ludwig Schmidt,John Duchi,Percy Liang

neural information processing systems, pp.11190-11201, (2019)

Cited by52EIBibtex

Semidefinite relaxations for certifying robustness to adversarial examples

Aditi Raghunathan,Jacob Steinhardt,Percy Liang

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), (2018)

Cited by83EIBibtex

Certified Defenses against Adversarial Examples

Aditi Raghunathan,Jacob Steinhardt,Percy Liang

ICLR, (2018)

Cited by325EIBibtex

Learning mixture of gaussians with streaming data

Aditi Raghunathan, Prateek Jain, Ravishankar Krishnawamy

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), (2017): 6605-6614

Cited by6Bibtex

Estimating the unseen from multiple populations

Aditi Raghunathan,Gregory Valiant,James Zou

ICML, (2017): 2855-2863

Cited by11EIBibtex

Probabilistic Dependency Networks for Prediction and Diagnostics

Narayanan U Edakunni,Aditi Raghunathan,Abhishek Tripathi,John Handley,Fredric Roulland

CoRR, (2015)

EIBibtex

A Reinforcement Learning Approach to Online Learning of Decision Trees

Abhinav Garlapati,Aditi Raghunathan,Vaishnavh Nagarajan,Balaraman Ravindran

CoRR, (2015)

Cited by4EIBibtex

View All

Base Info Papers Patents Projects