Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Inderjit S. Dhillon

Inderjit S. Dhillon

Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification

Oct 01, 2021
Jiong Zhang, Wei-cheng Chang, Hsiang-fu Yu, Inderjit S. Dhillon

Figure 1 for Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification

Figure 2 for Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification

Figure 3 for Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification

Figure 4 for Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification

Access Paper or Ask Questions

Label Disentanglement in Partition-based Extreme Multilabel Classification

Jun 24, 2021
Xuanqing Liu, Wei-Cheng Chang, Hsiang-Fu Yu, Cho-Jui Hsieh, Inderjit S. Dhillon

Figure 1 for Label Disentanglement in Partition-based Extreme Multilabel Classification

Figure 2 for Label Disentanglement in Partition-based Extreme Multilabel Classification

Figure 3 for Label Disentanglement in Partition-based Extreme Multilabel Classification

Figure 4 for Label Disentanglement in Partition-based Extreme Multilabel Classification

Access Paper or Ask Questions

Extreme Multi-label Learning for Semantic Matching in Product Search

Jun 23, 2021
Wei-Cheng Chang, Daniel Jiang, Hsiang-Fu Yu, Choon-Hui Teo, Jiong Zhang, Kai Zhong, Kedarnath Kolluri, Qie Hu, Nikhil Shandilya, Vyacheslav Ievgrafov, Japinder Singh, Inderjit S. Dhillon

Figure 1 for Extreme Multi-label Learning for Semantic Matching in Product Search

Figure 2 for Extreme Multi-label Learning for Semantic Matching in Product Search

Figure 3 for Extreme Multi-label Learning for Semantic Matching in Product Search

Figure 4 for Extreme Multi-label Learning for Semantic Matching in Product Search

* Accepted in KDD 2021 Applied Data Science Track

Access Paper or Ask Questions

DP-NormFedAvg: Normalizing Client Updates for Privacy-Preserving Federated Learning

Jun 13, 2021
Rudrajit Das, Abolfazl Hashemi, Sujay Sanghavi, Inderjit S. Dhillon

Figure 1 for DP-NormFedAvg: Normalizing Client Updates for Privacy-Preserving Federated Learning

Figure 2 for DP-NormFedAvg: Normalizing Client Updates for Privacy-Preserving Federated Learning

Figure 3 for DP-NormFedAvg: Normalizing Client Updates for Privacy-Preserving Federated Learning

Figure 4 for DP-NormFedAvg: Normalizing Client Updates for Privacy-Preserving Federated Learning

Access Paper or Ask Questions

Enabling Efficiency-Precision Trade-offs for Label Trees in Extreme Classification

Jun 01, 2021
Tavor Z. Baharav, Daniel L. Jiang, Kedarnath Kolluri, Sujay Sanghavi, Inderjit S. Dhillon

Figure 1 for Enabling Efficiency-Precision Trade-offs for Label Trees in Extreme Classification

Figure 2 for Enabling Efficiency-Precision Trade-offs for Label Trees in Extreme Classification

Figure 3 for Enabling Efficiency-Precision Trade-offs for Label Trees in Extreme Classification

Figure 4 for Enabling Efficiency-Precision Trade-offs for Label Trees in Extreme Classification

Access Paper or Ask Questions

Combinatorial Bandits without Total Order for Arms

Mar 03, 2021
Shuo Yang, Tongzheng Ren, Inderjit S. Dhillon, Sujay Sanghavi

Figure 1 for Combinatorial Bandits without Total Order for Arms

Figure 2 for Combinatorial Bandits without Total Order for Arms

Figure 3 for Combinatorial Bandits without Total Order for Arms

Figure 4 for Combinatorial Bandits without Total Order for Arms

Access Paper or Ask Questions

Linear Bandit Algorithms with Sublinear Time Complexity

Mar 03, 2021
Shuo Yang, Tongzheng Ren, Sanjay Shakkottai, Eric Price, Inderjit S. Dhillon, Sujay Sanghavi

Figure 1 for Linear Bandit Algorithms with Sublinear Time Complexity

Access Paper or Ask Questions

Improved Convergence Rates for Non-Convex Federated Learning with Compression

Dec 12, 2020
Rudrajit Das, Abolfazl Hashemi, Sujay Sanghavi, Inderjit S. Dhillon

Figure 1 for Improved Convergence Rates for Non-Convex Federated Learning with Compression

Access Paper or Ask Questions

Session-Aware Query Auto-completion using Extreme Multi-label Ranking

Dec 09, 2020
Nishant Yadav, Rajat Sen, Daniel N. Hill, Arya Mazumdar, Inderjit S. Dhillon

Figure 1 for Session-Aware Query Auto-completion using Extreme Multi-label Ranking

Figure 2 for Session-Aware Query Auto-completion using Extreme Multi-label Ranking

Figure 3 for Session-Aware Query Auto-completion using Extreme Multi-label Ranking

Figure 4 for Session-Aware Query Auto-completion using Extreme Multi-label Ranking

Access Paper or Ask Questions

PECOS: Prediction for Enormous and Correlated Output Spaces

Oct 12, 2020
Hsiang-Fu Yu, Kai Zhong, Inderjit S. Dhillon

Figure 1 for PECOS: Prediction for Enormous and Correlated Output Spaces

Figure 2 for PECOS: Prediction for Enormous and Correlated Output Spaces

Figure 3 for PECOS: Prediction for Enormous and Correlated Output Spaces

Figure 4 for PECOS: Prediction for Enormous and Correlated Output Spaces

Access Paper or Ask Questions

Non-Exhaustive, Overlapping Co-Clustering: An Extended Analysis

Apr 24, 2020
Joyce Jiyoung Whang, Inderjit S. Dhillon

Figure 1 for Non-Exhaustive, Overlapping Co-Clustering: An Extended Analysis

Figure 2 for Non-Exhaustive, Overlapping Co-Clustering: An Extended Analysis

Figure 3 for Non-Exhaustive, Overlapping Co-Clustering: An Extended Analysis

* "Non-Exhaustive, Overlapping Co-Clustering", Proceedings of the 26th ACM Conference on Information and Knowledge Management (CIKM), pages 2367-2370, November 2017

Access Paper or Ask Questions

Multiresolution Transformer Networks: Recurrence is Not Essential for Modeling Hierarchical Structure

Aug 27, 2019
Vikas K. Garg, Inderjit S. Dhillon, Hsiang-Fu Yu

Figure 1 for Multiresolution Transformer Networks: Recurrence is Not Essential for Modeling Hierarchical Structure

Figure 2 for Multiresolution Transformer Networks: Recurrence is Not Essential for Modeling Hierarchical Structure

Figure 3 for Multiresolution Transformer Networks: Recurrence is Not Essential for Modeling Hierarchical Structure

Figure 4 for Multiresolution Transformer Networks: Recurrence is Not Essential for Modeling Hierarchical Structure

* Initial version

Access Paper or Ask Questions

Inverting Deep Generative models, One layer at a time

Jun 19, 2019
Qi Lei, Ajil Jalal, Inderjit S. Dhillon, Alexandros G. Dimakis

Figure 1 for Inverting Deep Generative models, One layer at a time

Figure 2 for Inverting Deep Generative models, One layer at a time

Figure 3 for Inverting Deep Generative models, One layer at a time

Figure 4 for Inverting Deep Generative models, One layer at a time

Access Paper or Ask Questions

Primal-Dual Block Frank-Wolfe

Jun 06, 2019
Qi Lei, Jiacheng Zhuo, Constantine Caramanis, Inderjit S. Dhillon, Alexandros G. Dimakis

Figure 1 for Primal-Dual Block Frank-Wolfe

Figure 2 for Primal-Dual Block Frank-Wolfe

Figure 3 for Primal-Dual Block Frank-Wolfe

Figure 4 for Primal-Dual Block Frank-Wolfe

Access Paper or Ask Questions

AutoAssist: A Framework to Accelerate Training of Deep Neural Networks

May 08, 2019
Jiong Zhang, Hsiang-fu Yu, Inderjit S. Dhillon

Figure 1 for AutoAssist: A Framework to Accelerate Training of Deep Neural Networks

Figure 2 for AutoAssist: A Framework to Accelerate Training of Deep Neural Networks

Figure 3 for AutoAssist: A Framework to Accelerate Training of Deep Neural Networks

Figure 4 for AutoAssist: A Framework to Accelerate Training of Deep Neural Networks

Access Paper or Ask Questions

SysML: The New Frontier of Machine Learning Systems

May 01, 2019
Alexander Ratner, Dan Alistarh, Gustavo Alonso, David G. Andersen, Peter Bailis, Sarah Bird, Nicholas Carlini, Bryan Catanzaro, Jennifer Chayes, Eric Chung, Bill Dally, Jeff Dean, Inderjit S. Dhillon, Alexandros Dimakis, Pradeep Dubey, Charles Elkan, Grigori Fursin, Gregory R. Ganger, Lise Getoor, Phillip B. Gibbons, Garth A. Gibson, Joseph E. Gonzalez, Justin Gottschlich, Song Han, Kim Hazelwood, Furong Huang, Martin Jaggi, Kevin Jamieson, Michael I. Jordan, Gauri Joshi, Rania Khalaf, Jason Knight, Jakub Konečný, Tim Kraska, Arun Kumar, Anastasios Kyrillidis, Aparna Lakshmiratan, Jing Li, Samuel Madden, H. Brendan McMahan, Erik Meijer, Ioannis Mitliagkas, Rajat Monga, Derek Murray, Kunle Olukotun, Dimitris Papailiopoulos, Gennady Pekhimenko, Theodoros Rekatsinas, Afshin Rostamizadeh, Christopher Ré, Christopher De Sa, Hanie Sedghi, Siddhartha Sen, Virginia Smith, Alex Smola, Dawn Song, Evan Sparks, Ion Stoica, Vivienne Sze, Madeleine Udell, Joaquin Vanschoren, Shivaram Venkataraman, Rashmi Vinayak, Markus Weimer, Andrew Gordon Wilson, Eric Xing, Matei Zaharia, Ce Zhang, Ameet Talwalkar

Access Paper or Ask Questions

The Limitations of Adversarial Training and the Blind-Spot Attack

Jan 15, 2019
Huan Zhang, Hongge Chen, Zhao Song, Duane Boning, Inderjit S. Dhillon, Cho-Jui Hsieh

Figure 1 for The Limitations of Adversarial Training and the Blind-Spot Attack

Figure 2 for The Limitations of Adversarial Training and the Blind-Spot Attack

Figure 3 for The Limitations of Adversarial Training and the Blind-Spot Attack

Figure 4 for The Limitations of Adversarial Training and the Blind-Spot Attack

* Accepted by International Conference on Learning Representations (ICLR) 2019. Huan Zhang and Hongge Chen contributed equally

Access Paper or Ask Questions

Towards Fast Computation of Certified Robustness for ReLU Networks

Oct 02, 2018
Tsui-Wei Weng, Huan Zhang, Hongge Chen, Zhao Song, Cho-Jui Hsieh, Duane Boning, Inderjit S. Dhillon, Luca Daniel

Figure 1 for Towards Fast Computation of Certified Robustness for ReLU Networks

Figure 2 for Towards Fast Computation of Certified Robustness for ReLU Networks

Figure 3 for Towards Fast Computation of Certified Robustness for ReLU Networks

* Tsui-Wei Weng and Huan Zhang contributed equally

Access Paper or Ask Questions

Nonlinear Inductive Matrix Completion based on One-layer Neural Networks

May 26, 2018
Kai Zhong, Zhao Song, Prateek Jain, Inderjit S. Dhillon

Figure 1 for Nonlinear Inductive Matrix Completion based on One-layer Neural Networks

Figure 2 for Nonlinear Inductive Matrix Completion based on One-layer Neural Networks

Figure 3 for Nonlinear Inductive Matrix Completion based on One-layer Neural Networks

Access Paper or Ask Questions

Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization

Mar 25, 2018
Jiong Zhang, Qi Lei, Inderjit S. Dhillon

Figure 1 for Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization

Figure 2 for Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization

Figure 3 for Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization

Figure 4 for Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization

* main text 13 pages, 22 pages including reference and appendix

Access Paper or Ask Questions

Learning Long Term Dependencies via Fourier Recurrent Units

Mar 17, 2018
Jiong Zhang, Yibo Lin, Zhao Song, Inderjit S. Dhillon

Figure 1 for Learning Long Term Dependencies via Fourier Recurrent Units

Figure 2 for Learning Long Term Dependencies via Fourier Recurrent Units

Figure 3 for Learning Long Term Dependencies via Fourier Recurrent Units

Figure 4 for Learning Long Term Dependencies via Fourier Recurrent Units

Access Paper or Ask Questions

Learning Non-overlapping Convolutional Neural Networks with Multiple Kernels

Nov 08, 2017
Kai Zhong, Zhao Song, Inderjit S. Dhillon

Figure 1 for Learning Non-overlapping Convolutional Neural Networks with Multiple Kernels

Figure 2 for Learning Non-overlapping Convolutional Neural Networks with Multiple Kernels

* arXiv admin note: text overlap with arXiv:1706.03175

Access Paper or Ask Questions

Recovery Guarantees for One-hidden-layer Neural Networks

Jun 10, 2017
Kai Zhong, Zhao Song, Prateek Jain, Peter L. Bartlett, Inderjit S. Dhillon

Figure 1 for Recovery Guarantees for One-hidden-layer Neural Networks

Figure 2 for Recovery Guarantees for One-hidden-layer Neural Networks

* ICML 2017

Access Paper or Ask Questions

Similarity Preserving Representation Learning for Time Series Analysis

Mar 09, 2017
Qi Lei, Jinfeng Yi, Roman Vaculin, Lingfei Wu, Inderjit S. Dhillon

Figure 1 for Similarity Preserving Representation Learning for Time Series Analysis

Figure 2 for Similarity Preserving Representation Learning for Time Series Analysis

Figure 3 for Similarity Preserving Representation Learning for Time Series Analysis

Figure 4 for Similarity Preserving Representation Learning for Time Series Analysis

Access Paper or Ask Questions

A Greedy Approach for Budgeted Maximum Inner Product Search

Oct 11, 2016
Hsiang-Fu Yu, Cho-Jui Hsieh, Qi Lei, Inderjit S. Dhillon

Figure 1 for A Greedy Approach for Budgeted Maximum Inner Product Search

Figure 2 for A Greedy Approach for Budgeted Maximum Inner Product Search

Figure 3 for A Greedy Approach for Budgeted Maximum Inner Product Search

Figure 4 for A Greedy Approach for Budgeted Maximum Inner Product Search

Access Paper or Ask Questions

Communication-Efficient Parallel Block Minimization for Kernel Machines

Aug 05, 2016
Cho-Jui Hsieh, Si Si, Inderjit S. Dhillon

Figure 1 for Communication-Efficient Parallel Block Minimization for Kernel Machines

Figure 2 for Communication-Efficient Parallel Block Minimization for Kernel Machines

Figure 3 for Communication-Efficient Parallel Block Minimization for Kernel Machines

Figure 4 for Communication-Efficient Parallel Block Minimization for Kernel Machines

Access Paper or Ask Questions