11 years 8 months ago
Learning Low-order Models for Enforcing High-order Statistics
Models such as pairwise conditional random fields (CRFs) are extremely popular in computer vision and various other machine learning disciplines. However, they have limited expre...
Patrick Pletscher, Pushmeet Kohli
11 years 8 months ago
Structured Output Learning with High Order Loss Functions
Often when modeling structured domains, it is desirable to leverage information that is not naturally expressed as simply a label. Examples include knowledge about the evaluation ...
Daniel Tarlow, Richard S. Zemel
12 years 5 months ago
Structured Sparsity in Structured Prediction
Linear models have enjoyed great success in structured prediction in NLP. While a lot of progress has been made on efficient training with several loss functions, the problem of ...
André F. T. Martins, Noah A. Smith, M&aacut...
12 years 9 months ago
Application specific loss minimization using gradient boosting
Gradient boosting is a flexible machine learning technique that produces accurate predictions by combining many weak learners. In this work, we investigate its use in two applica...
Bin Zhang, Abhinav Sethy, Tara N. Sainath, Bhuvana...
135views more  JMLR 2010»
13 years 11 days ago
Structured Prediction Cascades
Structured prediction tasks pose a fundamental trade-off between the need for model complexity to increase predictive power and the limited computational resources for inference i...
David Weiss, Benjamin Taskar
161views more  JMLR 2010»
13 years 12 days ago
Dual Averaging Methods for Regularized Stochastic Learning and Online Optimization
We consider regularized stochastic learning and online optimization problems, where the objective function is the sum of two convex terms: one is the loss function of the learning...
Lin Xiao
105views more  JMLR 2010»
13 years 12 days ago
Classification Methods with Reject Option Based on Convex Risk Minimization
In this paper, we investigate the problem of binary classification with a reject option in which one can withhold the decision of classifying an observation at a cost lower than t...
Ming Yuan, Marten H. Wegkamp
13 years 19 days ago
Efficient Structured Support Vector Regression
Support Vector Regression (SVR) has been a long standing problem in machine learning, and gains its popularity on various computer vision tasks. In this paper, we propose a structu...
Ke Jia, Lei Wang, Nianjun Liu
13 years 4 months ago
Gradient descent optimization of smoothed information retrieval metrics
Abstract Most ranking algorithms are based on the optimization of some loss functions, such as the pairwise loss. However, these loss functions are often different from the criter...
Olivier Chapelle, Mingrui Wu
95views more  TIT 2002»
13 years 5 months ago
On sequential strategies for loss functions with memory
The problem of optimal sequential decision for individual sequences, relative to a class of competing o -line reference strategies, is studied for general loss functions with memo...
Neri Merhav, Erik Ordentlich, Gadiel Seroussi, Mar...