204 citations · 784 across the 42 of their papers we have counts for
20 papers · 1 filter
Representation Learning for Sequence Data with Deep Autoencoding Predictive Components
Junwen Bai, Weiran Wang, Yingbo Zhou +1
We propose Deep Autoencoding Predictive Components (DAPC) -- a self-supervised representation learning method for sequence data, based on the intuition that useful representations…
Everything old is new again: A multi-view learning approach to learning using privileged information and distillation
Weiran Wang
We adopt a multi-view approach for analyzing two knowledge transfer settings---learning using privileged information (LUPI) and distillation---in a common framework. Under reasonab…
Stochastic Nonconvex Optimization with Large Minibatches
Weiran Wang, Nathan Srebro
We study stochastic optimization of nonconvex loss functions, which are typical objectives for training neural networks. We propose stochastic approximation algorithms which optimi…
Stochastic Canonical Correlation Analysis
Chao Gao, Dan Garber, Nathan Srebro +2
We study the sample complexity of canonical correlation analysis (CCA), \ie, the number of samples needed to estimate the population canonical correlation and directions up to arbi…
Memory and Communication Efficient Distributed Stochastic Optimization with Minibatch-Prox
Jialei Wang, Weiran Wang, Nathan Srebro
We present and analyze an approach for distributed stochastic optimization which is statistically optimal and achieves near-linear speedups (up to logarithmic factors). Our approac…
Deep Variational Canonical Correlation Analysis
Weiran Wang, Xinchen Yan, Honglak Lee +1
We present deep variational canonical correlation analysis (VCCA), a deep multi-view learning model that extends the latent variable model interpretation of linear CCA to nonlinear…
Efficient Globally Convergent Stochastic Optimization for Canonical Correlation Analysis
Weiran Wang, Jialei Wang, Dan Garber +1
We study the stochastic optimization of canonical correlation analysis (CCA), whose objective is nonconvex and does not decouple over training samples. Although several stochastic…
On Column Selection in Approximate Kernel Canonical Correlation Analysis
Weiran Wang
We study the problem of column selection in large-scale kernel canonical correlation analysis (KCCA) using the Nyström approximation, where one approximates two positive semi-defin…
On Deep Multi-View Representation Learning: Objectives and Optimization
Weiran Wang, Raman Arora, Karen Livescu +1
We consider learning representations (features) in the setting in which we have access to multiple unlabeled views of the data for learning while only one view is available for dow…
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…
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…
The Laplacian K-modes algorithm for clustering
Weiran Wang, Miguel Á. Carreira-Perpiñán
In addition to finding meaningful clusters, centroid-based clustering algorithms such as K-means or mean-shift should ideally find centroids that are valid patterns in the input sp…
The role of dimensionality reduction in linear classification
Weiran Wang, Miguel Á. Carreira-Perpiñán
Dimensionality reduction (DR) is often used as a preprocessing step in classification, but usually one first fixes the DR mapping, possibly using label information, and then learns…
LASS: a simple assignment model with Laplacian smoothing
Miguel Á. Carreira-Perpiñán, Weiran Wang
We consider the problem of learning soft assignments of items to categories given two sources of information: an item-category similarity matrix, which encourages items to…
Projection onto the probability simplex: An efficient algorithm with a simple proof, and an application
Weiran Wang, Miguel Á. Carreira-Perpiñán
We provide an elementary proof of a simple, efficient algorithm for computing the Euclidean projection of a point onto the probability simplex. We also show an application in Lapla…
The K-modes algorithm for clustering
Miguel Á. Carreira-Perpiñán, Weiran Wang
Many clustering algorithms exist that estimate a cluster centroid, such as K-means, K-medoids or mean-shift, but no algorithm seems to exist that clusters data by returning exactly…
Distributed optimization of deeply nested systems
Miguel Á. Carreira-Perpiñán, Weiran Wang
In science and engineering, intelligent processing of complex signals such as images, sound or language is often performed by a parameterized hierarchy of nonlinear processing laye…