7 citations · 10 across the 4 of their papers we have counts for
4 papers
Multi-node Bert-pretraining: Cost-efficient Approach
Jiahuang Lin, Xin Li, Gennady Pekhimenko
Recently, large scale Transformer-based language models such as BERT, GPT-2, and XLNet have brought about exciting leaps in state-of-the-art results for many Natural Language Proce…
On the Learning Property of Logistic and Softmax Losses for Deep Neural Networks
Xiangrui Li, Xin Li, Deng Pan +1
Deep convolutional neural networks (CNNs) trained with logistic and softmax losses have made significant advancement in visual recognition tasks in computer vision. When training d…
Improve SGD Training via Aligning Mini-batches
Xiangrui Li, Deng Pan, Xin Li +1
Deep neural networks (DNNs) for supervised learning can be viewed as a pipeline of a feature extractor (i.e. last hidden layer) and a linear classifier (i.e. output layer) that is…
Multiple-Population Moment Estimation: Exploiting Inter-Population Correlation for Efficient Moment Estimation in Analog/Mixed-Signal Validation
Chenjie Gu, Manzil Zaheer, Xin Li
Moment estimation is an important problem during circuit validation, in both pre-Silicon and post-Silicon stages. From the estimated moments, the probability of failure and paramet…