activity
20172025
most citedFine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution

160 citations · 231 across the 8 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG202229 cited

Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?

Rishi Bommasani, Kathleen A. Creel, Ananya Kumar +2

As the scope of machine learning broadens, we observe a recurring theme of algorithmic monoculture: the same systems, or systems that share components (e.g. training data), are dep…

cs.LG20222 cited

Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations

Jeff Z. HaoChen, Colin Wei, Ananya Kumar +1

Contrastive learning is a highly effective method for learning representations from unlabeled data. Recent works show that contrastive representations can transfer across domains,…

cs.LG2022160 cited

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

Ananya Kumar, Aditi Raghunathan, Robbie Jones +2

When transferring a pretrained model to a downstream task, two popular methods are full fine-tuning (updating all the model parameters) and linear probing (updating only the last l…

cs.LG20218 cited

No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets

Fahim Tajwar, Ananya Kumar, Sang Michael Xie +1

Out-of-distribution detection is an important component of reliable ML systems. Prior literature has proposed various methods (e.g., MSP (Hendrycks & Gimpel, 2017), ODIN (Liang et…

cs.LG20209 cited

In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness

Sang Michael Xie, Ananya Kumar, Robbie Jones +3

Consider a prediction setting with few in-distribution labeled examples and many unlabeled examples both in- and out-of-distribution (OOD). The goal is to learn a model which perfo…

cs.LG2020

Selective Classification Can Magnify Disparities Across Groups

Erik Jones, Shiori Sagawa, Pang Wei Koh +2

Selective classification, in which models can abstain on uncertain predictions, is a natural approach to improving accuracy in settings where errors are costly but abstentions are…