204 citations · 784 across the 42 of their papers we have counts for
7 papers · 1 filter
Nonparametric Canonical Correlation Analysis
Tomer Michaeli, Weiran Wang, Karen Livescu
Canonical correlation analysis (CCA) is a classical representation learning technique for finding correlated variables in multi-view data. Several nonlinear extensions of the origi…
Large-Scale Approximate Kernel Canonical Correlation Analysis
Weiran Wang, Karen Livescu
Kernel canonical correlation analysis (KCCA) is a nonlinear multi-view representation learning technique with broad applicability in statistics and machine learning. Although there…
Stochastic Optimization for Deep CCA via Nonlinear Orthogonal Iterations
Weiran Wang, Raman Arora, Karen Livescu +1
Deep CCA is a recently proposed deep neural network extension to the traditional canonical correlation analysis (CCA), and has been successful for multi-view representation learnin…
Deep convolutional acoustic word embeddings using word-pair side information
Herman Kamper, Weiran Wang, Karen Livescu
Recent studies have been revisiting whole words as the basic modelling unit in speech recognition and query applications, instead of phonetic units. Such whole-word segmental syste…
Discriminative Segmental Cascades for Feature-Rich Phone Recognition
Hao Tang, Weiran Wang, Kevin Gimpel +1
Discriminative segmental models, such as segmental conditional random fields (SCRFs) and segmental structured support vector machines (SSVMs), have had success in speech recognitio…
Projection onto the capped simplex
Weiran Wang, Canyi Lu
We provide a simple and efficient algorithm for computing the Euclidean projection of a point onto the capped simplex---a simplex with an additional uniform bound on each coordinat…
An projection operator for weighted -norm regularization with sum constraint
Weiran Wang
We provide a simple and efficient algorithm for the projection operator for weighted -norm regularization subject to a sum constraint, together with an elementary proof. Th…