Timezone: »

 
Poster
Coresets for Data-efficient Training of Machine Learning Models
Baharan Mirzasoleiman · Jeff Bilmes · Jure Leskovec

Thu Jul 16 08:00 AM -- 08:45 AM & Thu Jul 16 07:00 PM -- 07:45 PM (PDT) @ Virtual
in Poster Session 43 »

Incremental gradient (IG) methods, such as stochastic gradient descent and its variants are commonly used for large scale optimization in machine learning. Despite the sustained effort to make IG methods more data-efficient, it remains an open question how to select a training data subset that can theoretically and practically perform on par with the full dataset. Here we develop CRAIG, a method to select a weighted subset (or coreset) of training data that closely estimates the full gradient by maximizing a submodular function. We prove that applying IG to this subset is guaranteed to converge to the (near)optimal solution with the same convergence rate as that of IG for convex optimization. As a result, CRAIG achieves a speedup that is inversely proportional to the size of the subset. To our knowledge, this is the first rigorous method for data-efficient training of general machine learning models. Our extensive set of experiments show that CRAIG, while achieving practically the same solution, speeds up various IG methods by up to 6x for logistic regression and 3x for training deep neural networks.

Keywords: Combinatorial Optimization · Convex Optimization · Large Scale Learning and Big Data · Optimization - General
[ Slides] 

Author Information

Baharan Mirzasoleiman (Stanford University)
Jeff Bilmes (UW)
Jure Leskovec (Stanford University)

More from the Same Authors