4 papers
Memory-Efficient Factorization Machines via Binarizing both Data and Model Coefficients
Yu Geng, Liang Lan
Factorization Machines (FM), a general predictor that can efficiently model feature interactions in linear time, was primarily proposed for collaborative recommendation and have be…
Effective and Sparse Count-Sketch via k-means clustering
Yuhan Wang, Zijian Lei, Liang Lan
Count-sketch is a popular matrix sketching algorithm that can produce a sketch of an input data matrix X in O(nnz(X))time where nnz(X) denotes the number of non-zero entries in X.…
Compressing Deep Convolutional Neural Networks by Stacking Low-dimensional Binary Convolution Filters
Weichao Lan, Liang Lan
Deep Convolutional Neural Networks (CNN) have been successfully applied to many real-life problems. However, the huge memory cost of deep CNN models poses a great challenge of depl…
Memory and Computation-Efficient Kernel SVM via Binary Embedding and Ternary Model Coefficients
Zijian Lei, Liang Lan
Kernel approximation is widely used to scale up kernel SVM training and prediction. However, the memory and computation costs of kernel approximation models are still too high if w…