A Smoother Way to Train Structured Prediction Models

A Smoother Way to Train Structured Prediction Models

8 February 2019

Krishna Pillutla

Zaïd Harchaoui

Papers citing "A Smoother Way to Train Structured Prediction Models"

11 / 11 papers shown

Title
Stochastic Variance Reduction Methods for Saddle-Point Problems B. Palaniappan Francis R. Bach 115 212 0 20 May 2016
SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives Aaron Defazio Francis R. Bach Simon Lacoste-Julien ODL 131 1,823 0 01 Jul 2014
Incremental Majorization-Minimization Optimization with Application to Large-Scale Machine Learning Julien Mairal 144 318 0 18 Feb 2014
Minimizing Finite Sums with the Stochastic Average Gradient Mark Schmidt Nicolas Le Roux Francis R. Bach 304 1,246 0 10 Sep 2013
Loopy Belief Propagation for Approximate Inference: An Empirical Study Kevin P. Murphy Yair Weiss Michael I. Jordan 3DV 121 1,881 0 23 Jan 2013
A simpler approach to obtaining an O(1/t) convergence rate for the projected stochastic subgradient method Simon Lacoste-Julien Mark Schmidt Francis R. Bach 173 260 0 10 Dec 2012
An Efficient Message-Passing Algorithm for the M-Best MAP Problem Dhruv Batra 64 29 0 16 Oct 2012
Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization Shai Shalev-Shwartz Tong Zhang 166 1,032 0 10 Sep 2012
A Stochastic Gradient Method with an Exponential Convergence Rate for Finite Training Sets Nicolas Le Roux Mark Schmidt Francis R. Bach ODL 68 104 0 28 Feb 2012
Natural Language Processing (almost) from Scratch R. Collobert Jason Weston Léon Bottou Michael Karlen Koray Kavukcuoglu Pavel P. Kuksa 165 7,721 0 02 Mar 2011
Learning as Search Optimization: Approximate Large Margin Methods for Structured Prediction Hal Daumé D. Marcu 96 279 0 04 Jul 2009

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.