activity
20102014
most citedOn the Computational Efficiency of Training Neural Networks

75 citations · 217 across the 7 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2014★ 75 cited

On the Computational Efficiency of Training Neural Networks

Roi Livni, Shai Shalev-Shwartz, Ohad Shamir

It is well-known that neural networks are computationally hard to train. On the other hand, in practice, modern day neural networks are trained efficiently using SGD and a variety…

cs.LG2014★ 34 cited

Optimal Learners for Multiclass Problems

Amit Daniely, Shai Shalev-Shwartz

The fundamental theorem of statistical learning states that for binary classification problems, any Empirical Risk Minimization (ERM) learning rule has close to optimal sample comp…

cs.LG2012★ 4 cited

Learning the Experts for Online Sequence Prediction

Elad Eban, Aharon Birnbaum, Shai Shalev-Shwartz +1

Online sequence prediction is the problem of predicting the next element of a sequence given previous elements. This problem has been extensively studied in the context of individu…

cs.LG2012★ 5 cited

The Kernelized Stochastic Batch Perceptron

Andrew Cotter, Shai Shalev-Shwartz, Nathan Srebro

We present a novel approach for training kernel Support Vector Machines, establish learning runtime guarantees for our method that are better then those of any other known kerneliz…

cs.LG2012★ 38 cited

Near-Optimal Algorithms for Online Matrix Prediction

Elad Hazan, Satyen Kale, Shai Shalev-Shwartz

In several online prediction problems of recent interest the comparison class is composed of matrices with bounded entries. For example, in the online max-cut problem, the comparis…

cs.LG2010★ 2 cited

Learning Kernel-Based Halfspaces with the Zero-One Loss

Shai Shalev-Shwartz, Ohad Shamir, Karthik Sridharan

We describe and analyze a new algorithm for agnostically learning kernel-based halfspaces with respect to the \emph{zero-one} loss function. Unlike most previous formulations which…