Search Results for author:
Found 9 papers, 6 papers with code
The Journey, Not the Destination: How Data Guides Diffusion Models
Then, we provide a method for computing these attributions efficiently.
FFCV: Accelerating Training by Removing Data Bottlenecks
For example, we are able to train an ImageNet ResNet-50 model to 75\% in only 20 mins on a single machine.
TRAK: Attributing Model Behavior at Scale
That is, computationally tractable methods can struggle with accurately attributing model predictions in non-convex settings (e. g., in the context of deep neural networks), while methods that are effective in such regimes require training thousands of models, which makes them impractical for large models or datasets.
ModelDiff: A Framework for Comparing Learning Algorithms
We study the problem of (learning) algorithm comparison, where the goal is to find differences between models trained with two different learning algorithms.
A Data-Based Perspective on Transfer Learning
It is commonly believed that in transfer learning including more pre-training data translates into better performance.
Datamodels: Predicting Predictions from Training Data
We present a conceptual framework, datamodeling, for analyzing the behavior of a model class in terms of the training data.
On Distinctive Properties of Universal Perturbations
We identify properties of universal adversarial perturbations (UAPs) that distinguish them from standard adversarial perturbations.
Non-robust Features through the Lens of Universal Perturbations
We study universal adversarial perturbations and demonstrate that the above picture is more nuanced.
Sparse PCA from Sparse Linear Regression
Sparse Principal Component Analysis (SPCA) and Sparse Linear Regression (SLR) have a wide range of applications and have attracted a tremendous amount of attention in the last two decades as canonical examples of statistical problems in high dimension.
