Search Results for author: S. Sathiya Keerthi

Found 16 papers, 2 papers with code

Logit Attenuating Weight Normalization

no code implementations12 Aug 2021 Aman Gupta, Rohan Ramanath, Jun Shi, Anika Ramachandran, Sirou Zhou, Mingzhou Zhou, S. Sathiya Keerthi

Over-parameterized deep networks trained using gradient-based optimizers are a popular choice for solving classification and ranking problems.

Image Classification Recommendation Systems

Regression via Implicit Models and Optimal Transport Cost Minimization

1 code implementation3 Mar 2020 Saurav Manchanda, Khoa Doan, Pranjul Yadav, S. Sathiya Keerthi

This paper addresses the classic problem of regression, which involves the inductive learning of a map, $y=f(x, z)$, $z$ denoting noise, $f:\mathbb{R}^n\times \mathbb{R}^k \rightarrow \mathbb{R}^m$.

Targeted display advertising: the case of preferential attachment

no code implementations7 Feb 2020 Saurav Manchanda, Pranjul Yadav, Khoa Doan, S. Sathiya Keerthi

We present an experimental analysis on the historical logs of a major display advertising platform (https://www. criteo. com/).

Domain Adaptation

Benchmarking Regression Methods: A comparison with CGAN

1 code implementation30 May 2019 Karan Aggarwal, Matthieu Kirchmeyer, Pranjul Yadav, S. Sathiya Keerthi, Patrick Gallinari

Such a real world situation is best represented using an implicit model in which an extra noise vector, $z$ is included with $x$ as input.

Distributed Newton Methods for Deep Neural Networks

no code implementations1 Feb 2018 Chien-Chih Wang, Kent Loong Tan, Chun-Ting Chen, Yu-Hsiang Lin, S. Sathiya Keerthi, Dhruv Mahajan, S. Sundararajan, Chih-Jen Lin

First, to reduce the communication cost, we propose a diagonalization method such that an approximate Newton direction can be obtained without communication between machines.

Efficient Estimation of Generalization Error and Bias-Variance Components of Ensembles

no code implementations15 Nov 2017 Dhruv Mahajan, Vivek Gupta, S. Sathiya Keerthi, Sellamanickam Sundararajan, Shravan Narayanamurthy, Rahul Kidambi

We also demonstrate their usefulness in making design choices such as the number of classifiers in the ensemble and the size of a subset of data used for training that is needed to achieve a certain value of generalization error.

Batch-Expansion Training: An Efficient Optimization Framework

no code implementations22 Apr 2017 Michał Dereziński, Dhruv Mahajan, S. Sathiya Keerthi, S. V. N. Vishwanathan, Markus Weimer

We propose Batch-Expansion Training (BET), a framework for running a batch optimizer on a gradually expanding dataset.

Towards a Better Understanding of Predict and Count Models

no code implementations6 Nov 2015 S. Sathiya Keerthi, Tobias Schnabel, Rajiv Khanna

In a recent paper, Levy and Goldberg pointed out an interesting connection between prediction-based word embedding models and count models based on pointwise mutual information.

L2 Regularization

A Distributed Algorithm for Training Nonlinear Kernel Machines

no code implementations18 May 2014 Dhruv Mahajan, S. Sathiya Keerthi, S. Sundararajan

This paper concerns the distributed training of nonlinear kernel machines on Map-Reduce.

A distributed block coordinate descent method for training $l_1$ regularized linear classifiers

no code implementations18 May 2014 Dhruv Mahajan, S. Sathiya Keerthi, S. Sundararajan

In this paper we design a distributed algorithm for $l_1$ regularization that is much better suited for such systems than existing algorithms.

A Structured Prediction Approach for Missing Value Imputation

no code implementations9 Nov 2013 Rahul Kidambi, Vinod Nair, Sundararajan Sellamanickam, S. Sathiya Keerthi

In this paper we propose a structured output approach for missing value imputation that also incorporates domain constraints.

Imputation Structured Prediction

An efficient distributed learning algorithm based on effective local functional approximations

no code implementations31 Oct 2013 Dhruv Mahajan, Nikunj Agrawal, S. Sathiya Keerthi, S. Sundararajan, Leon Bottou

In this paper we give a novel approach to the distributed training of linear classifiers (involving smooth losses and L2 regularization) that is designed to reduce the total communication costs.

L2 Regularization

Cannot find the paper you are looking for? You can Submit a new open access paper.