activity
20182020
most citedExploring Interpretable LSTM Neural Networks over Multi-Variable Data

97 citations · 186 across the 3 of their papers we have counts for

collaborators

8 papers

cs.LG202087 cited

Dynamic Model Pruning with Feedback

Tao Lin, Sebastian U. Stich, Luis Barba +2

Deep neural networks often have millions of parameters. This can hinder their deployment to low-end devices, not only due to high memory requirements but also because of increased…

cs.LG20202 cited

Extrapolation for Large-batch Training in Deep Learning

Tao Lin, Lingjing Kong, Sebastian U. Stich +1

Deep learning networks are typically trained by Stochastic Gradient Descent (SGD) methods that iteratively improve the model parameters by estimating a gradient on a very small fra…

cs.LG2020

On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them

Chen Liu, Mathieu Salzmann, Tao Lin +2

We analyze the influence of adversarial training on the loss landscape of machine learning models. To this end, we first provide analytical studies of the properties of adversarial…

cs.LG2020

Ensemble Distillation for Robust Model Fusion in Federated Learning

Tao Lin, Lingjing Kong, Sebastian U. Stich +1

Federated Learning (FL) is a machine learning setting where many devices collaboratively train a machine learning model while keeping the training data decentralized. In most of th…

cs.CL2020

Masking as an Efficient Alternative to Finetuning for Pretrained Language Models

Mengjie Zhao, Tao Lin, Fei Mi +2

We present an efficient method of utilizing pretrained language models, where we learn selective binary masks for pretrained weights in lieu of modifying them through finetuning. E…

cs.LG2019

Decentralized Deep Learning with Arbitrary Communication Compression

Anastasia Koloskova, Tao Lin, Sebastian U. Stich +1

Decentralized training of deep learning models is a key element for enabling data privacy and on-device learning over networks, as well as for efficient scaling to large compute cl…