no code implementations • 17 Aug 2021 • Yu Geng, Liang Lan
Our proposed method can significantly reduce the memory cost of SEFM model.
no code implementations • 24 Nov 2020 • YuHan Wang, Zijian Lei, Liang Lan
This data-oblivious matrix sketching method could produce a bad sketched matrix which will result in low accuracy for subsequent machine learning tasks (e. g. classification); (2) For highly sparse input data, count-sketch could produce a dense sketched data matrix.
no code implementations • 6 Oct 2020 • Zijian Lei, Liang Lan
The analysis shows that the convergence to a local optimum is guaranteed, and the inference complexity of our model is much lower than other competing methods.
no code implementations • 6 Oct 2020 • Weichao Lan, Liang Lan
One popular way to reduce the memory cost of deep CNN model is to train binary CNN where the weights in convolution filters are either 1 or -1 and therefore each weight can be efficiently stored using a single bit.
no code implementations • 5 Feb 2020 • Zijian Lei, Liang Lan
To overcome this limitation, we analyze the effect of using SRHT for random projection in the context of linear SVM classification.