Timezone: »
We consider the problem of learning high-dimensional multi-response linear models with structured parameters. By exploiting the noise correlations among different responses, we propose an alternating estimation (AltEst) procedure to estimate the model parameters based on the generalized Dantzig selector (GDS). Under suitable sample size and resampling assumptions, we show that the error of the estimates generated by AltEst, with high probability, converges linearly to certain minimum achievable level, which can be tersely expressed by a few geometric measures, such as Gaussian width of sets related to the parameter structure. To the best of our knowledge, this is the first non-asymptotic statistical guarantee for such AltEst-type algorithm applied to estimation with general structures.
Author Information
Sheng Chen (University of Minnesota)
Arindam Banerjee (Voleon)
Arindam Banerjee is a Professor at the Department of Computer & Engineering and a Resident Fellow at the Institute on the Environment at the University of Minnesota, Twin Cities. His research interests are in machine learning, data mining, and applications in complex real-world problems in different areas including climate science, ecology, recommendation systems, text analysis, and finance. He has won several awards, including the NSF CAREER award (2010), the IBM Faculty Award (2013), and six best paper awards in top-tier conferences.
More from the Same Authors
-
2020 Poster: Gradient Boosted Normalizing Flows »
Robert Giaquinto · Arindam Banerjee -
2019 Poster: Random Quadratic Forms with Dependence: Applications to Restricted Isometry and Beyond »
Arindam Banerjee · Qilong Gu · Vidyashankar Sivakumar · Steven Wu -
2018 Poster: An Improved Analysis of Alternating Minimization for Structured Multi-Response Regression »
Sheng Chen · Arindam Banerjee -
2016 Poster: High Dimensional Structured Superposition Models »
Qilong Gu · Arindam Banerjee -
2016 Poster: Structured Matrix Recovery via the Generalized Dantzig Selector »
Sheng Chen · Arindam Banerjee -
2015 Poster: Unified View of Matrix Completion under General Structural Constraints »
Suriya Gunasekar · Arindam Banerjee · Joydeep Ghosh -
2015 Poster: Beyond Sub-Gaussian Measurements: High-Dimensional Structured Estimation with Sub-Exponential Designs »
Vidyashankar Sivakumar · Arindam Banerjee · Pradeep Ravikumar -
2015 Poster: Structured Estimation with Atomic Norms: General Bounds and Applications »
Sheng Chen · Arindam Banerjee -
2014 Poster: Bregman Alternating Direction Method of Multipliers »
Huahua Wang · Arindam Banerjee -
2014 Poster: Estimation with Norm Regularization »
Arindam Banerjee · Sheng Chen · Farideh Fazayeli · Vidyashankar Sivakumar -
2014 Poster: Generalized Dantzig Selector: Application to the k-support norm »
Soumyadeep Chatterjee · Sheng Chen · Arindam Banerjee -
2014 Poster: Parallel Direction Method of Multipliers »
Huahua Wang · Arindam Banerjee · Zhi-Quan Luo -
2014 Tutorial: Climate Change: Challenges for Machine Learning »
Arindam Banerjee · Claire Monteleoni -
2013 Poster: Large Scale Distributed Sparse Precision Estimation »
Huahua Wang · Arindam Banerjee · Cho-Jui Hsieh · Pradeep Ravikumar · Inderjit Dhillon