115 citations · 162 across the 14 of their papers we have counts for
6 papers · 1 filter
OP-LoRA: The Blessing of Dimensionality
Piotr Teterwak, Kate Saenko, Bryan A. Plummer +1
Low-rank adapters (LoRA) enable finetuning of large models with only a small number of parameters. However, they often suffer from an ill-conditioned loss landscape, leading to dif…
MixtureGrowth: Growing Neural Networks by Recombining Learned Parameters
Chau Pham, Piotr Teterwak, Soren Nelson +1
Most deep neural networks are trained under fixed network architectures and require retraining when the architecture changes. If expanding the network's size is needed, it is neces…
ERM++: An Improved Baseline for Domain Generalization
Piotr Teterwak, Kuniaki Saito, Theodoros Tsiligkaridis +2
Domain Generalization (DG) aims to develop classifiers that can generalize to new, unseen data distributions, a critical capability when collecting new domain-specific data is impr…
VisDA-2021 Competition Universal Domain Adaptation to Improve Performance on Out-of-Distribution Data
Dina Bashkirova, Dan Hendrycks, Donghyun Kim +5
Progress in machine learning is typically measured by training and testing a model on the same distribution of data, i.e., the same domain. This over-estimates future accuracy on o…
Understanding Invariance via Feedforward Inversion of Discriminatively Trained Classifiers
Piotr Teterwak, Chiyuan Zhang, Dilip Krishnan +1
A discriminatively trained neural net classifier can fit the training data perfectly if all information about its input other than class membership has been discarded prior to the…
Supervised Contrastive Learning
Prannay Khosla, Piotr Teterwak, Chen Wang +6
Contrastive learning applied to self-supervised representation learning has seen a resurgence in recent years, leading to state of the art performance in the unsupervised training…