16 citations · 40 across the 8 of their papers we have counts for
8 papers
Distributed Newton Methods for Deep Neural Networks
Chien-Chih Wang, Kent Loong Tan, Chun-Ting Chen +5
Deep learning involves a difficult non-convex optimization problem with a large number of weights between any two adjacent layers of a deep structure. To handle large data sets or…
A Sparse Nonlinear Classifier Design Using AUC Optimization
Vishal Kakkar, Shirish K. Shevade, S Sundararajan +1
AUC (Area under the ROC curve) is an important performance measure for applications where the data is highly imbalanced. Learning to maximize AUC performance is thus an important r…
A Distributed Algorithm for Training Nonlinear Kernel Machines
Dhruv Mahajan, S. Sathiya Keerthi, S. Sundararajan
This paper concerns the distributed training of nonlinear kernel machines on Map-Reduce. We show that a re-formulation of Nyström approximation based solution which is solved using…
A distributed block coordinate descent method for training regularized linear classifiers
Dhruv Mahajan, S. Sathiya Keerthi, S. Sundararajan
Distributed training of regularized classifiers has received great attention recently. Most existing methods approach this problem by taking steps obtained from approximating…
An Empirical Evaluation of Sequence-Tagging Trainers
P. Balamurugan, Shirish Shevade, S. Sundararajan +1
The task of assigning label sequences to a set of observed sequences is common in computational linguistics. Several models for sequence labeling have been proposed over the last f…
A Parallel SGD method with Strong Convergence
Dhruv Mahajan, S. Sathiya Keerthi, S. Sundararajan +1
This paper proposes a novel parallel stochastic gradient descent (SGD) method that is obtained by applying parallel sets of SGD iterations (each set operating on one node using the…
An efficient distributed learning algorithm based on effective local functional approximations
Dhruv Mahajan, Nikunj Agrawal, S. Sathiya Keerthi +2
Scalable machine learning over big data is an important problem that is receiving a lot of attention in recent years. On popular distributed environments such as Hadoop running on…
Mechanism Design for Cost Optimal PAC Learning in the Presence of Strategic Noisy Annotators
Dinesh Garg, Sourangshu Bhattacharya, S. Sundararajan +1
We consider the problem of Probably Approximate Correct (PAC) learning of a binary classifier from noisy labeled examples acquired from multiple annotators (each characterized by a…