Kurt Keutzer

Unsupervised Domain Adaptation: from Simulation Engine to the RealWorld

2018 · arXiv (Cornell University)

Large-scale labeled training datasets have enabled deep neural networks to excel on a wide range of benchmark vision tasks. However, in many applications it is prohibitively expensive or time-consuming to obtain large quantities of labeled …

Inefficiency of K-FAC for Large Batch Size Training

2019 · arXiv (Cornell University)

In stochastic optimization, using large batch sizes during training can leverage parallel resources to produce faster wall-clock training times per training epoch. However, for both training loss and testing error, recent results analyzing large batch …

Cross-Domain Sentiment Classification with In-Domain Contrastive Learning

2020 · arXiv (Cornell University)

Contrastive learning (CL) has been successful as a powerful representation learning method. In this paper, we propose a contrastive learning framework for cross-domain sentiment classification. We aim to induce domain invariant optimal classifiers rather than …

Towards Unified and Effective Domain Generalization

2023 · arXiv (Cornell University)

We propose $\textbf{UniDG}$, a novel and $\textbf{Uni}$fied framework for $\textbf{D}$omain $\textbf{G}$eneralization that is capable of significantly enhancing the out-of-distribution generalization performance of foundation models regardless of their architectures. The core idea of UniDG is to …

Simple and Effective Input Reformulations for Translation

2023 · arXiv (Cornell University)

Foundation language models learn from their finetuning input context in different ways. In this paper, we reformulate inputs during finetuning for challenging translation tasks, leveraging model strengths from pretraining in novel ways to improve downstream …