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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Sanjiv Kumar

On the Reproducibility of Neural Network Predictions


Feb 05, 2021
Srinadh Bhojanapalli, Kimberly Wilber, Andreas Veit, Ankit Singh Rawat, Seungyeon Kim, Aditya Menon, Sanjiv Kumar

* 19 pages, 7 figures 

  Access Paper or Ask Questions

Kernelized Classification in Deep Networks


Dec 08, 2020
Sadeep Jayasumana, Srikumar Ramalingam, Sanjiv Kumar


  Access Paper or Ask Questions

Modifying Memories in Transformer Models


Dec 01, 2020
Chen Zhu, Ankit Singh Rawat, Manzil Zaheer, Srinadh Bhojanapalli, Daliang Li, Felix Yu, Sanjiv Kumar


  Access Paper or Ask Questions

Coping with Label Shift via Distributionally Robust Optimisation


Oct 23, 2020
Jingzhao Zhang, Aditya Menon, Andreas Veit, Srinadh Bhojanapalli, Sanjiv Kumar, Suvrit Sra


  Access Paper or Ask Questions

Semantic Label Smoothing for Sequence to Sequence Problems


Oct 15, 2020
Michal Lukasik, Himanshu Jain, Aditya Krishna Menon, Seungyeon Kim, Srinadh Bhojanapalli, Felix Yu, Sanjiv Kumar


  Access Paper or Ask Questions

Learning discrete distributions: user vs item-level privacy


Jul 28, 2020
Yuhan Liu, Ananda Theertha Suresh, Felix Yu, Sanjiv Kumar, Michael Riley

* 36 pages 

  Access Paper or Ask Questions

Learning discrete distributions: user-lever vs item-level privacy


Jul 27, 2020
Yuhan Liu, Ananda Theertha Suresh, Felix Yu, Sanjiv Kumar, Michael Riley

* 36 pages 

  Access Paper or Ask Questions

Multi-Stage Influence Function


Jul 17, 2020
Hongge Chen, Si Si, Yang Li, Ciprian Chelba, Sanjiv Kumar, Duane Boning, Cho-Jui Hsieh


  Access Paper or Ask Questions

Long-tail learning via logit adjustment


Jul 14, 2020
Aditya Krishna Menon, Sadeep Jayasumana, Ankit Singh Rawat, Himanshu Jain, Andreas Veit, Sanjiv Kumar


  Access Paper or Ask Questions

$O(n)$ Connections are Expressive Enough: Universal Approximability of Sparse Transformers


Jun 08, 2020
Chulhee Yun, Yin-Wen Chang, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar

* 32 pages 

  Access Paper or Ask Questions

Evaluations and Methods for Explanation through Robustness Analysis


May 31, 2020
Cheng-Yu Hsieh, Chih-Kuan Yeh, Xuanqing Liu, Pradeep Ravikumar, Seungyeon Kim, Sanjiv Kumar, Cho-Jui Hsieh


  Access Paper or Ask Questions

Why distillation helps: a statistical perspective


May 21, 2020
Aditya Krishna Menon, Ankit Singh Rawat, Sashank J. Reddi, Seungyeon Kim, Sanjiv Kumar


  Access Paper or Ask Questions

Doubly-stochastic mining for heterogeneous retrieval


Apr 23, 2020
Ankit Singh Rawat, Aditya Krishna Menon, Andreas Veit, Felix Yu, Sashank J. Reddi, Sanjiv Kumar


  Access Paper or Ask Questions

Federated Learning with Only Positive Labels


Apr 21, 2020
Felix X. Yu, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar


  Access Paper or Ask Questions

Robust Large-Margin Learning in Hyperbolic Space


Apr 11, 2020
Melanie Weber, Manzil Zaheer, Ankit Singh Rawat, Aditya Menon, Sanjiv Kumar

* Under Review 

  Access Paper or Ask Questions

Does label smoothing mitigate label noise?


Mar 05, 2020
Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon, Sanjiv Kumar


  Access Paper or Ask Questions

Adaptive Federated Optimization


Feb 29, 2020
Sashank Reddi, Zachary Charles, Manzil Zaheer, Zachary Garrett, Keith Rush, Jakub Konečný, Sanjiv Kumar, H. Brendan McMahan


  Access Paper or Ask Questions

Low-Rank Bottleneck in Multi-head Attention Models


Feb 17, 2020
Srinadh Bhojanapalli, Chulhee Yun, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar

* 17 pages, 4 figures 

  Access Paper or Ask Questions

Pre-training Tasks for Embedding-based Large-scale Retrieval


Feb 10, 2020
Wei-Cheng Chang, Felix X. Yu, Yin-Wen Chang, Yiming Yang, Sanjiv Kumar

* Accepted by ICLR 2020 

  Access Paper or Ask Questions

Are Transformers universal approximators of sequence-to-sequence functions?


Dec 20, 2019
Chulhee Yun, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar

* Accepted to ICLR 2020 

  Access Paper or Ask Questions

Why ADAM Beats SGD for Attention Models


Dec 06, 2019
Jingzhao Zhang, Sai Praneeth Karimireddy, Andreas Veit, Seungyeon Kim, Sashank J Reddi, Sanjiv Kumar, Suvrit Sra


  Access Paper or Ask Questions

Learning to Learn by Zeroth-Order Oracle


Oct 21, 2019
Yangjun Ruan, Yuanhao Xiong, Sashank Reddi, Sanjiv Kumar, Cho-Jui Hsieh


  Access Paper or Ask Questions

Online Hierarchical Clustering Approximations


Sep 20, 2019
Aditya Krishna Menon, Anand Rajagopalan, Baris Sumengen, Gui Citovsky, Qin Cao, Sanjiv Kumar

* 17 pages, 3 figures 

  Access Paper or Ask Questions

New Loss Functions for Fast Maximum Inner Product Search


Sep 11, 2019
Ruiqi Guo, Quan Geng, David Simcha, Felix Chern, Sanjiv Kumar, Xiang Wu


  Access Paper or Ask Questions

AdaCliP: Adaptive Clipping for Private SGD


Aug 20, 2019
Venkatadheeraj Pichapati, Ananda Theertha Suresh, Felix X. Yu, Sashank J. Reddi, Sanjiv Kumar

* 18 pages 

  Access Paper or Ask Questions

Sampled Softmax with Random Fourier Features


Jul 24, 2019
Ankit Singh Rawat, Jiecao Chen, Felix Yu, Ananda Theertha Suresh, Sanjiv Kumar


  Access Paper or Ask Questions

Neural SDE: Stabilizing Neural ODE Networks with Stochastic Noise


Jun 05, 2019
Xuanqing Liu, Tesi Xiao, Si Si, Qin Cao, Sanjiv Kumar, Cho-Jui Hsieh


  Access Paper or Ask Questions

On the Convergence of Adam and Beyond


Apr 19, 2019
Sashank J. Reddi, Satyen Kale, Sanjiv Kumar

* Appeared in ICLR 2018 

  Access Paper or Ask Questions

Local Orthogonal Decomposition for Maximum Inner Product Search


Mar 25, 2019
Xiang Wu, Ruiqi Guo, Sanjiv Kumar, David Simcha


  Access Paper or Ask Questions