activity
20092023
most citedStructured Sparse Principal Component Analysis

295 citations · 663 across the 20 of their papers we have counts for

collaborators

27 papers

cs.LG2023

Pi-DUAL: Using Privileged Information to Distinguish Clean from Noisy Labels

Ke Wang, Guillermo Ortiz-Jimenez, Rodolphe Jenatton +3

Label noise is a pervasive problem in deep learning that often compromises the generalization performance of trained models. Recently, leveraging privileged information (PI) -- inf…

cs.CV2023★ 4 cited

Three Towers: Flexible Contrastive Learning with Pretrained Image Models

Jannik Kossen, Mark Collier, Basil Mustafa +7

We introduce Three Towers (3T), a flexible method to improve the contrastive learning of vision-language models by incorporating pretrained image classifiers. While contrastive mod…

cs.LG2023

When does Privileged Information Explain Away Label Noise?

Guillermo Ortiz-Jimenez, Mark Collier, Anant Nawalgaria +4

Leveraging privileged information (PI), or features available during training but not at test time, has recently been shown to be an effective method for addressing label noise. Ho…

cs.CV2023★ 118 cited

Scaling Vision Transformers to 22 Billion Parameters

Mostafa Dehghani, Josip Djolonga, Basil Mustafa +39

The scaling of Transformers has driven breakthrough capabilities for language models. At present, the largest large language models (LLMs) contain upwards of 100B parameters. Visio…

cs.LG2023★ 1 cited

Massively Scaling Heteroscedastic Classifiers

Mark Collier, Rodolphe Jenatton, Basil Mustafa +3

Heteroscedastic classifiers, which learn a multivariate Gaussian distribution over prediction logits, have been shown to perform well on image classification problems with hundreds…

cs.LG2022★ 1 cited

On the Adversarial Robustness of Mixture of Experts

Joan Puigcerver, Rodolphe Jenatton, Carlos Riquelme +2

Adversarial robustness is a key desirable property of neural networks. It has been empirically shown to be affected by their sizes, with larger networks being typically more robust…