research
∙
09/18/2023
Understanding Catastrophic Forgetting in Language Models via Implicit Inference
Fine-tuning (via methods such as instruction-tuning or reinforcement lea...
share
research
∙
07/19/2023
Contextual Reliability: When Different Features Matter in Different Contexts
Deep neural networks often fail catastrophically by relying on spurious ...
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...
research
∙
06/16/2023
ALP: Action-Aware Embodied Learning for Perception
Current methods in training and benchmarking vision models exhibit an ov...
research
∙
03/08/2023
Automatically Auditing Large Language Models via Discrete Optimization
Auditing large language models for unexpected behaviors is critical to p...
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...
research
∙
12/05/2022
Learning Representations that Enable Generalization in Assistive Tasks
Recent work in sim2real has successfully enabled robots to act in physic...
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...
research
∙
10/18/2022
Using Language to Extend to Unseen Domains
It is expensive to collect training data for every possible domain that ...
research
∙
07/20/2022
Test-Time Adaptation via Conjugate Pseudo-labels
Test-time adaptation (TTA) refers to adapting neural networks to distrib...
research
∙
07/18/2022
Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift
We often see undesirable tradeoffs in robust machine learning where out-...
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...
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...
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...
research
∙
07/19/2021
Just Train Twice: Improving Group Robustness without Training Group Information
Standard training via empirical risk minimization (ERM) can produce mode...
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...
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...
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...
research
∙
06/13/2020
The Pitfalls of Simplicity Bias in Neural Networks
Several works have proposed Simplicity Bias (SB)—the tendency of standar...
research
∙
05/09/2020
An Investigation of Why Overparameterization Exacerbates Spurious Correlations
We study why overparameterization – increasing model size well beyond th...
research
∙
05/04/2020
Robust Encodings: A Framework for Combating Adversarial Typos
Despite excellent performance on many tasks, NLP systems are easily fool...
research
∙
02/28/2020
DROCC: Deep Robust One-Class Classification
Classical approaches for one-class problems such as one-class SVM (Schol...
research
∙
02/25/2020
Understanding and Mitigating the Tradeoff Between Robustness and Accuracy
Adversarial training augments the training set with perturbations to imp...
research
∙
09/03/2019
Certified Robustness to Adversarial Word Substitutions
State-of-the-art NLP models can often be fooled by adversaries that appl...
research
∙
06/14/2019
Adversarial Training Can Hurt Generalization
While adversarial training can improve robust accuracy (against an adver...
research
∙
06/08/2019
Maximum Weighted Loss Discrepancy
Though machine learning algorithms excel at minimizing the average loss ...
research
∙
05/31/2019
Unlabeled Data Improves Adversarial Robustness
We demonstrate, theoretically and empirically, that adversarial robustne...
research
∙
11/02/2018
Semidefinite relaxations for certifying robustness to adversarial examples
Despite their impressive performance on diverse tasks, neural networks f...
research
∙
01/29/2018
Certified Defenses against Adversarial Examples
While neural networks have achieved high accuracy on standard image clas...
research
∙
07/12/2017
Estimating the unseen from multiple populations
Given samples from a distribution, how many new elements should we expec...
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...
research
∙
08/10/2016