Aditi Raghunathan

发表

Certified Defenses against Adversarial Examples pdf

Aditi Raghunathan, Percy Liang, Jacob Steinhardt, 2018, ICLR.

Estimating the unseen from multiple populations

James Zou, Gregory Valiant, Aditi Raghunathan, 2017, ICML.

Unlabeled Data Improves Adversarial Robustness

Ludwig Schmidt, Yair Carmon, Aditi Raghunathan, 2019, NeurIPS.

Estimation from Indirect Supervision with Linear Moments pdf

Aditi Raghunathan, Percy Liang, John C. Duchi, 2016, ICML.

Semidefinite relaxations for certifying robustness to adversarial examples

Aditi Raghunathan, Percy Liang, Jacob Steinhardt, 2018, NeurIPS.

When Covariate-shifted Data Augmentation Increases Test Error And How to Fix It

John C. Duchi, Sang Michael Xie, Percy Liang, 2019 .

The Pitfalls of Simplicity Bias in Neural Networks

Prateek Jain, Praneeth Netrapalli, Aditi Raghunathan, 2020, NeurIPS.

Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices

Percy Liang, Chelsea Finn, E. Liu, 2020, ICML.

An Investigation of Why Overparameterization Exacerbates Spurious Correlations

Pang Wei Koh, Percy Liang, Aditi Raghunathan, 2020, ICML.

An Explanation of In-context Learning as Implicit Bayesian Inference

Sang Michael Xie, Percy Liang, Aditi Raghunathan, 2021, ArXiv.

Task-Agnostic Robust Encodings for Combating Adversarial Typos

Aditi Raghunathan, Robin Jia, Percy Liang, 2019 .

An Explanation of In-context Learning as Implicit Bayesian Inference

Sang Michael Xie, Percy Liang, Aditi Raghunathan, 2021, ICLR.

Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift

Aditi Raghunathan, Yiding Jiang, Zico Kolter, 2022, ArXiv.

Finetune like you pretrain: Improved finetuning of zero-shot vision models

Ananya Kumar, Aditi Raghunathan, Zico Kolter, 2022, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Test-Time Adaptation via Conjugate Pseudo-labels

Aditi Raghunathan, Mingjie Sun, Zico Kolter, 2022, NeurIPS.

On the Opportunities and Risks of Foundation Models

Michael S. Bernstein, Juan Carlos Niebles, Christopher D. Manning, 2021, ArXiv.

Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution

Percy Liang, Ananya Kumar, Aditi Raghunathan, 2022, ICLR.

Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization pdf

Yair Carmon, Aditi Raghunathan, Percy Liang, 2021, ICML.

Certified Robustness to Adversarial Word Substitutions pdf

Aditi Raghunathan, Percy Liang, Robin Jia, 2019, EMNLP.

Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices

Chelsea Finn, Aditi Raghunathan, Percy Liang, 2020, ICML.

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

Chelsea Finn, Aditi Raghunathan, Percy Liang, 2020, ArXiv.

Robust Encodings: A Framework for Combating Adversarial Typos pdf

Aditi Raghunathan, Robin Jia, Percy Liang, 2020, ACL.

Just Train Twice: Improving Group Robustness without Training Group Information

Chelsea Finn, Aditi Raghunathan, Percy Liang, 2021, ICML.

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

Ian Goodfellow, Pushmeet Kohli, Sumanth Dathathri, 2020, NeurIPS.

Adversarial Training Can Hurt Generalization pdf

Aditi Raghunathan, Percy Liang, John C. Duchi, 2019, ArXiv.

Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift

Percy Liang, Ananya Kumar, Aditi Raghunathan, 2022, UAI.

Understanding and Mitigating the Tradeoff Between Robustness and Accuracy pdf

John Duchi, Aditi Raghunathan, Percy Liang, 2020, ICML.

DROCC: Deep Robust One-Class Classification

Harsha Vardhan Simhadri, Aditi Raghunathan, Prateek Jain, 2020, ICML.

Learning Representations that Enable Generalization in Assistive Tasks

Zackory M. Erickson, Daniel S. Brown, A. Dragan, 2022, CoRL.

Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift

Aditi Raghunathan, Yiding Jiang, Zico Kolter, 2022, NeurIPS.

Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts

Amrith Rajagopal Setlur, S. Levine, Chelsea Finn, 2023, ICLR.

Maximum Weighted Loss Discrepancy pdf

Aditi Raghunathan, Percy Liang, Fereshte Khani, 2019, ArXiv.

A Reinforcement Learning Approach to Online Learning of Decision Trees pdf

Balaraman Ravindran, Aditi Raghunathan, Vaishnavh Nagarajan, 2015, ArXiv.

T-MARS: Improving Visual Representations by Circumventing Text Feature Learning

J. Z. Kolter, Zachary Chase Lipton, Aditi Raghunathan, 2023, ArXiv.

ALP: Action-Aware Embodied Learning for Perception

P. Abbeel, Aditi Raghunathan, Wilson Yan, 2023, 2306.10190.

Automatically Auditing Large Language Models via Discrete Optimization

A. Dragan, J. Steinhardt, Aditi Raghunathan, 2023, ICML.

Contextual Reliability: When Different Features Matter in Different Contexts

Amrith Rajagopal Setlur, Gaurav R. Ghosal, Daniel S. Brown, 2023, ICML.

Understanding Catastrophic Forgetting in Language Models via Implicit Inference

Jacob M. Springer, Aditi Raghunathan, Suhas Kotha, 2023, ArXiv.

DROCC: Deep Robust One-Class Classification

Prateek Jain, H. Simhadri, Aditi Raghunathan, 2020, ICML.

On the Opportunities and Risks of Foundation Models

Michael S. Bernstein, Juan Carlos Niebles, Christopher D. Manning, 2021, ArXiv.