Timezone: »
Poster
Multi-stage Convex Relaxation for Learning with Sparse Regularization
Tong Zhang
We study learning formulations with non-convex regularizaton that are natural for sparse linear models. There are two approaches to this problem: (1) Heuristic methods such as gradient descent that only find a local minimum. A drawback of this approach is the lack of theoretical guarantee showing that the local minimum gives a good solution. (2) Convex relaxation such as $L_1$-regularization that solves the problem under some conditions. However it often leads to sub-optimal sparsity in reality. This paper tries to remedy the above gap between theory and practice. In particular, we investigate a multi-stage convex relaxation scheme for solving problems with non-convex regularization. Theoretically, we analyze the behavior of a resulting two-stage relaxation scheme for the capped-$L_1$ regularization. Our performance bound shows that the procedure is superior to the standard $L_1$ convex relaxation for learning sparse targets. Experiments confirm the effectiveness of this method on some simulation and real data.
Author Information
Tong Zhang (The Hong Kong University of Science and Technology)
More from the Same Authors
-
2016 Poster: Exact Recovery of Hard Thresholding Pursuit »
Xiaotong Yuan · Ping Li · Tong Zhang -
2016 Poster: Learning Additive Exponential Family Graphical Models via $\ell_{2,1}$-norm Regularized M-Estimation »
Xiaotong Yuan · Ping Li · Tong Zhang · Qingshan Liu · Guangcan Liu -
2015 Poster: Quartz: Randomized Dual Coordinate Ascent with Arbitrary Sampling »
Zheng Qu · Peter Richtarik · Tong Zhang -
2015 Poster: Local Smoothness in Variance Reduced Optimization »
Daniel Vainsencher · Han Liu · Tong Zhang -
2015 Poster: Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding »
Rie Johnson · Tong Zhang -
2015 Spotlight: Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding »
Rie Johnson · Tong Zhang -
2013 Poster: Accelerating Stochastic Gradient Descent using Predictive Variance Reduction »
Rie Johnson · Tong Zhang -
2013 Poster: Accelerated Mini-Batch Stochastic Dual Coordinate Ascent »
Shai Shalev-Shwartz · Tong Zhang -
2012 Workshop: Modern Nonparametric Methods in Machine Learning »
Sivaraman Balakrishnan · Arthur Gretton · Mladen Kolar · John Lafferty · Han Liu · Tong Zhang -
2012 Poster: Selective Labeling via Error Bound Minimization »
Quanquan Gu · Tong Zhang · Chris Ding · Jiawei Han -
2011 Poster: Learning to Search Efficiently in High Dimensions »
Zhen Li · Huazhong Ning · Liangliang Cao · Tong Zhang · Yihong Gong · Thomas S Huang -
2011 Poster: Spectral Methods for Learning Multivariate Latent Tree Structure »
Anima Anandkumar · Kamalika Chaudhuri · Daniel Hsu · Sham M Kakade · Le Song · Tong Zhang -
2011 Poster: Greedy Model Averaging »
Dong Dai · Tong Zhang -
2010 Poster: Deep Coding Network »
Yuanqing Lin · Tong Zhang · Shenghuo Zhu · Kai Yu -
2010 Poster: Agnostic Active Learning Without Constraints »
Alina Beygelzimer · Daniel Hsu · John Langford · Tong Zhang -
2009 Poster: Multi-Label Prediction via Compressed Sensing »
Daniel Hsu · Sham M Kakade · John Langford · Tong Zhang -
2009 Poster: Nonlinear Learning using Local Coordinate Coding »
Kai Yu · Tong Zhang · Yihong Gong -
2009 Oral: Multi-Label Prediction via Compressed Sensing »
Daniel Hsu · Sham M Kakade · John Langford · Tong Zhang -
2008 Poster: Adaptive Forward-Backward Greedy Algorithm for Sparse Learning with Linear Models »
Tong Zhang -
2008 Oral: Adaptive Forward-Backward Greedy Algorithm for Sparse Learning with Linear Models »
Tong Zhang -
2008 Poster: Sparse Online Learning via Truncated Gradient »
John Langford · Lihong Li · Tong Zhang -
2008 Spotlight: Sparse Online Learning via Truncated Gradient »
John Langford · Lihong Li · Tong Zhang -
2007 Poster: A General Boosting Method and its Application to Learning Ranking Functions for Web Search »
Zhaohui Zheng · Hongyuan Zha · Tong Zhang · Olivier Chapelle · Keke Chen · Gordon Sun -
2007 Poster: The Epoch-Greedy Algorithm for Multi-armed Bandits with Side Information »
John Langford · Tong Zhang -
2006 Poster: Learning on Graph with Laplacian Regularization »
Rie Ando · Tong Zhang