research
∙
07/12/2023
Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution
The ubiquitous and demonstrably suboptimal choice of resizing images to ...
share
research
∙
05/22/2023
Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design
Scaling laws have been recently employed to derive compute-optimal model...
research
∙
12/21/2022
Adapting to Latent Subgroup Shifts via Concepts and Proxies
We address the problem of unsupervised domain adaptation when the source...
research
∙
12/15/2022
FlexiViT: One Model for All Patch Sizes
Vision Transformers convert images to sequences by slicing them into pat...
research
∙
11/18/2022
Layer-Stack Temperature Scaling
Recent works demonstrate that early layers in a neural network contain u...
research
∙
09/13/2022
Revisiting Neural Scaling Laws in Language and Vision
The remarkable progress in deep learning in recent years is largely driv...
research
∙
05/31/2022
A Reduction to Binary Approach for Debiasing Multiclass Datasets
We propose a novel reduction-to-binary (R2B) approach that enforces demo...
research
∙
02/02/2022
Maintaining fairness across distribution shift: do we have viable solutions for real-world applications?
Fairness and robustness are often considered as orthogonal dimensions wh...
research
∙
01/31/2022
Fair Wrapping for Black-box Predictions
We introduce a new family of techniques to post-process ("wrap") a black...
research
∙
09/01/2021
The Impact of Reinitialization on Generalization in Convolutional Neural Networks
Recent results suggest that reinitializing a subset of the parameters of...
research
∙
06/06/2021
A Generalization of Classical Formulas in Numerical Integration and Series Convergence Acceleration
Summation formulas, such as the Euler-Maclaurin expansion or Gregory's q...
research
∙
06/18/2020
What Do Neural Networks Learn When Trained With Random Labels?
We study deep neural networks (DNNs) trained on natural image data with ...
research
∙
05/21/2020
Fair Classification via Unconstrained Optimization
Achieving the Bayes optimal binary classification rule subject to group ...
research
∙
08/22/2016
Uniform Generalization, Concentration, and Adaptive Learning
One fundamental goal in any learning algorithm is to mitigate its risk f...
research
∙
05/07/2014