18 citations · 36 across the 9 of their papers we have counts for
9 papers
Synthetic Data for any Differentiable Target
Tristan Thrush, Sung Min Park, Herman Brunborg +5
What are the limits of controlling language models via synthetic training data? We develop a reinforcement learning (RL) primitive, the Dataset Policy Gradient (DPG), which can pre…
Attribute-to-Delete: Machine Unlearning via Datamodel Matching
Kristian Georgiev, Roy Rinberg, Sung Min Park +4
Machine unlearning -- efficiently removing the effect of a small "forget set" of training data on a pre-trained machine learning model -- has recently attracted significant researc…
The Journey, Not the Destination: How Data Guides Diffusion Models
Kristian Georgiev, Joshua Vendrow, Hadi Salman +2
Diffusion models trained on large datasets can synthesize photo-realistic images of remarkable quality and diversity. However, attributing these images back to the training data-th…
FFCV: Accelerating Training by Removing Data Bottlenecks
Guillaume Leclerc, Andrew Ilyas, Logan Engstrom +3
We present FFCV, a library for easy and fast machine learning model training. FFCV speeds up model training by eliminating (often subtle) data bottlenecks from the training process…
TRAK: Attributing Model Behavior at Scale
Sung Min Park, Kristian Georgiev, Andrew Ilyas +2
The goal of data attribution is to trace model predictions back to training data. Despite a long line of work towards this goal, existing approaches to data attribution tend to for…
ModelDiff: A Framework for Comparing Learning Algorithms
Harshay Shah, Sung Min Park, Andrew Ilyas +1
We study the problem of (learning) algorithm comparison, where the goal is to find differences between models trained with two different learning algorithms. We begin by formalizin…
A Data-Based Perspective on Transfer Learning
Saachi Jain, Hadi Salman, Alaa Khaddaj +3
It is commonly believed that in transfer learning including more pre-training data translates into better performance. However, recent evidence suggests that removing data from the…
Datamodels: Predicting Predictions from Training Data
Andrew Ilyas, Sung Min Park, Logan Engstrom +2
We present a conceptual framework, datamodeling, for analyzing the behavior of a model class in terms of the training data. For any fixed "target" example , training set , an…
On Distinctive Properties of Universal Perturbations
Sung Min Park, Kuo-An Wei, Kai Xiao +2
We identify properties of universal adversarial perturbations (UAPs) that distinguish them from standard adversarial perturbations. Specifically, we show that targeted UAPs generat…