Aditi Raghunathan

research

∙ 09/18/2023

Understanding Catastrophic Forgetting in Language Models via Implicit Inference

Fine-tuning (via methods such as instruction-tuning or reinforcement lea...

0 Suhas Kotha, et al. ∙

research

∙ 07/19/2023

Contextual Reliability: When Different Features Matter in Different Contexts

Deep neural networks often fail catastrophically by relying on spurious ...

0 Gaurav Ghosal, et al. ∙

research

∙ 07/06/2023

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

Large web-sourced multimodal datasets have powered a slew of new methods...

0 Pratyush Maini, et al. ∙

research

∙ 06/16/2023

ALP: Action-Aware Embodied Learning for Perception

Current methods in training and benchmarking vision models exhibit an ov...

0 Xinran Liang, et al. ∙

research

∙ 03/08/2023

Automatically Auditing Large Language Models via Discrete Optimization

Auditing large language models for unexpected behaviors is critical to p...

0 Erik Jones, et al. ∙

research

∙ 02/06/2023

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

Training machine learning models robust to distribution shifts is critic...

0 Amrith Setlur, et al. ∙

research

∙ 12/05/2022

Learning Representations that Enable Generalization in Assistive Tasks

Recent work in sim2real has successfully enabled robots to act in physic...

0 Jerry Zhi-Yang He, et al. ∙

research

∙ 12/01/2022

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

Finetuning image-text models such as CLIP achieves state-of-the-art accu...

0 Sachin Goyal, et al. ∙

research

∙ 10/18/2022

Using Language to Extend to Unseen Domains

It is expensive to collect training data for every possible domain that ...

3 Lisa Dunlap, et al. ∙

research

∙ 07/20/2022

Test-Time Adaptation via Conjugate Pseudo-labels

Test-time adaptation (TTA) refers to adapting neural networks to distrib...

4 Sachin Goyal, et al. ∙

research

∙ 07/18/2022

Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift

We often see undesirable tradeoffs in robust machine learning where out-...

0 Ananya Kumar, et al. ∙

research

∙ 06/27/2022

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

Recently, Miller et al. showed that a model's in-distribution (ID) accur...

0 Christina Baek, et al. ∙

research

∙ 02/21/2022

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

When transferring a pretrained model to a downstream task, two popular m...

0 Ananya Kumar, et al. ∙

research

∙ 11/03/2021

An Explanation of In-context Learning as Implicit Bayesian Inference

Large pretrained language models such as GPT-3 have the surprising abili...

7 Sang Michael Xie, et al. ∙

research

∙ 07/19/2021

Just Train Twice: Improving Group Robustness without Training Group Information

Standard training via empirical risk minimization (ERM) can produce mode...

12 Evan Zheran Liu, et al. ∙

research

∙ 07/09/2021

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

For machine learning systems to be reliable, we must understand their pe...

0 John Miller, et al. ∙

research

∙ 10/22/2020

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

Convex relaxations have emerged as a promising approach for verifying de...

6 Sumanth Dathathri, et al. ∙

research

∙ 08/06/2020

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

We seek to efficiently learn by leveraging shared structure between diff...

6 Evan Zheran Liu, et al. ∙

research

∙ 06/13/2020

The Pitfalls of Simplicity Bias in Neural Networks

Several works have proposed Simplicity Bias (SB)—the tendency of standar...

0 Harshay Shah, et al. ∙

research

∙ 05/09/2020

An Investigation of Why Overparameterization Exacerbates Spurious Correlations

We study why overparameterization – increasing model size well beyond th...

0 Shiori Sagawa, et al. ∙

research

∙ 05/04/2020

Robust Encodings: A Framework for Combating Adversarial Typos

Despite excellent performance on many tasks, NLP systems are easily fool...

0 Erik Jones, et al. ∙

research

∙ 02/28/2020

DROCC: Deep Robust One-Class Classification

Classical approaches for one-class problems such as one-class SVM (Schol...

13 Sachin Goyal, et al. ∙

research

∙ 02/25/2020

Understanding and Mitigating the Tradeoff Between Robustness and Accuracy

Adversarial training augments the training set with perturbations to imp...

42 Aditi Raghunathan, et al. ∙

research

∙ 09/03/2019

Certified Robustness to Adversarial Word Substitutions

State-of-the-art NLP models can often be fooled by adversaries that appl...

0 Robin Jia, et al. ∙

research

∙ 06/14/2019

Adversarial Training Can Hurt Generalization

While adversarial training can improve robust accuracy (against an adver...

0 Aditi Raghunathan, et al. ∙

research

∙ 06/08/2019

Maximum Weighted Loss Discrepancy

Though machine learning algorithms excel at minimizing the average loss ...

0 Fereshte Khani, et al. ∙

research

∙ 05/31/2019

Unlabeled Data Improves Adversarial Robustness

We demonstrate, theoretically and empirically, that adversarial robustne...

0 Yair Carmon, et al. ∙

research

∙ 11/02/2018

Semidefinite relaxations for certifying robustness to adversarial examples

Despite their impressive performance on diverse tasks, neural networks f...

0 Aditi Raghunathan, et al. ∙

research

∙ 01/29/2018

Certified Defenses against Adversarial Examples

While neural networks have achieved high accuracy on standard image clas...

0 Aditi Raghunathan, et al. ∙

research

∙ 07/12/2017

Estimating the unseen from multiple populations

Given samples from a distribution, how many new elements should we expec...

0 Aditi Raghunathan, et al. ∙

research

∙ 07/08/2017

Learning Mixture of Gaussians with Streaming Data

In this paper, we study the problem of learning a mixture of Gaussians w...

0 Aditi Raghunathan, et al. ∙

research

∙ 08/10/2016

Estimation from Indirect Supervision with Linear Moments

In structured prediction problems where we have indirect supervision of ...

0 Aditi Raghunathan, et al. ∙

Aditi Raghunathan

Featured Co-authors