On the Support Vector Effect in DNNs: Rethinking Data Selection and Attribution Syed Hasan Amin Mahmood, Ming Yin, Rajiv Khanna KDD 2025
The Space Complexity of Approximating Logistic Loss Gregory Dexter, Petros Drineas, Rajiv Khanna Neurips 2024
Approximating Memorization Using Loss Surface Geometry for Dataset Pruning and Summarization Andrea Agiollo*, Young In Kim*, Rajiv Khanna KDD 2024
A Precise Characterization of SGD Stability Using Loss Surface Geometry Gregory Dexter, Borja Ocejo, Sathiya Keerthi, Aman Gupta, Ayan Acharya, Rajiv Khanna ICLR 2024
On Memorization and Privacy risks of Sharpness Aware Minimization Young In Kim, Pratiksha Agrawal, Johannes O Royset, Rajiv Khanna ICML 2023 (Workshop on Data-centric Machine Learning Research)
Generalization Guarantees via Algorithm-dependent Rademacher Complexity Sarah Sachs, Tim van Erven, Liam Hodgkinson, Rajiv Khanna, Umut Simsekli COLT 2023
Fast Feature Selection with Fairness Constraints Francesco Quinzan, Rajiv Khanna, Moshik Hershcovitch, Sarel Cohen, Daniel G. Waddington, Tobias Friedrich, Michael W. Mahoney AISTATS 2023
Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers Liam Hodgkinson, Umut Simsekli, Rajiv Khanna, Michael Mahoney ICML 2022
Geometric Rates of Convergence for Kernel-based Sampling Algorithms Rajiv Khanna, Liam Hodgkinson, Michael Mahoney UAI 2021 (Oral)
LocalNewton: Reducing Communication Bottleneck for Distributed Learning Vipul Gupta, Avishek Ghosh, Michal Derezinski, Rajiv Khanna, Ramchandran Kannan, Michael Mahoney UAI 2021
Bayesian Coresets: An Optimization Perspective Yibo Zhang, Rajiv Khanna, Anastasios Kyrillidis, Oluwasanmi Koyejo. AISTATS 2021 (Oral)
Adversarially-trained deep nets transfer better Francisco Utrera, Evan Kravitz, N Benjamin Erichson, Rajiv Khanna, Michael W Mahoney ICLR 2021
Improved guarantees and a multiple-descent curve for Column Subset Selection and the Nystrom method Michal Derezinski, Rajiv Khanna, Michael W Mahoney Neurips 2020 (Best paper award. Top 3 papers out of over 9400 submissions)
Boundary thickness and robustness in learning models Yaoqing Yang, Rajiv Khanna, Yaodong Yu, Amir Gholami, Kurt Keutzer, Joseph E Gonzalez, Kannan Ramchandran, Michael W Mahoney. Neurips 2020
Learning Sparse Distributions using Iterative Hard Thresholding Yibo Zhang, Rajiv Khanna, Anastasios Kyrillidis, Oluwasanmi Koyejo. Neurips 2019
Interpreting black box predictions using fisher kernels Rajiv Khanna, Been Kim, Joydeep Ghosh, Oluwasanmi Koyejo. AISTATS 2019
Boosting Black Box Variational Inference Francesco Locatello, Gideon Dresdner, Rajiv Khanna, Isabel Valera, Gunnar Rätsch. NIPS 2018 (Spotlight)
Restricted Strong Convexity implies Weak Submodularity Ethan Elenberg, Rajiv Khanna, Alex Dimakis, Sahand Neghaban. Accepted to Annals of Stat. 2018 (A shorter version presented at NIPS 2016 Workshop on Learning in High Dimensions with Structure.) [paper][bibtex]
@ARTICLE{Elenberg:2016rsc,
author = { {Elenberg}, Ethan and {Khanna}, Rajiv and {Dimakis}, Alexandros and {Negahban}, Sahand},
title = {Restricted Strong Convexity Implies Weak Submodularity},
journal = {Annals of Statistics},
year = 2018,
month = Jan,
}
Provable Accelerated Iterative Hard Thresholding. Rajiv Khanna, Anastasios Kyrillidis. AISTATS 2018
Boosting Variational Inference: An Optimization Perspective Francesco Locatello, Rajiv Khanna, Joydeep Ghosh, Gunnar Raetsch ( Preprint )AISTATS 2018 (a shorter version appeared in NIPS 2017 workshop on Approx. Variational Inference)
Co-regularized Monotone Retargeting for Semi-supervised LeTOR Shalmali Joshi, Rajiv Khanna, Joydeep Ghosh SDM 2018
On Approximation Guarantees for Greedy Low Rank Optimization Rajiv Khanna, Ethan Elenberg, Alex Dimakis, Joydeep Ghosh, Sahand Neghaban. ICML 2017 [paper] [bibtex]
@article{Khanna:2017lowrank,
author = {Khanna, Rajiv and Elenberg, Ethan and Dimakis, Alexandros and Ghosh, Joydeep and Neghaban, Sahand},
title = {On Approximation Guarantees for Greedy Low Rank Optimization},
journal={ICML},
year = 2017
}
Scalable Greedy Feature Selection via Weak Submodularity. Rajiv Khanna, Ethan Elenberg, Alex Dimakis, Sahand Neghaban, Joydeep Ghosh. AISTATS 2017 [paper] [bibtex]
@article{Khanna:2016distributed,
author = {Khanna, Rajiv and Elenberg, Ethan and Dimakis, Alexandros and Neghaban, Sahand and Ghosh, Joydeep},
title = {Scalable Greedy Support Selection via Weak Submodularity},
journal={AISTATS},
year = 2017
}
Information Projection and Approximate Inference for Structured Sparse Variables. Rajiv Khanna, Joydeep Ghosh, Russell A. Poldrack, Oluwasanmi Koyejo. AISTATS 2017 [paper] [bibtex]
@article{Khanna:2016structsparse,
author = {Khanna, Rajiv and Ghosh, Joydeep and Poldrack, Russell and Koyejo, Oluwasanmi},
title = {Information Projection and Approximate Inference for Structured Sparse Variables},
journal={AISTATS},
year = 2017
}
A Unified Analysis of Frank Wolfe and Matching Pursuit. Francesco Locatello, Rajiv Khanna, Michael Tschannen, Martin Jaggi AISTATS 2017 [paper] [bibtex]
@article{Locatello:2016fwmp,
author = {Francesco Locatello and Rajiv Khanna and Michael Tschannen and Martin Jaggi},
title = {A Unified Optimization View on Generalized Matching Pursuit and Frank-Wolfe},
journal={AISTATS},
year = 2017
}
A Deflation Method for Structured Probabilistic PCA. Rajiv Khanna, Joydeep Ghosh, Russell A. Poldrack, Oluwasanmi Koyejo. SDM 2017 [paper] [bibtex]
@article{khanna:2016structdeflation,
author = {Khanna, Rajiv and Ghosh, Joydeep and Poldrack, Russell and Koyejo, Oluwasanmi},
title = {A Deflation Method for Structured Probabilistic {PCA}},
journal={SIAM conference on {Data} {Mining}},
year = 2017
}
Examples are not Enough, Learn to Criticize! Criticism for Interpretability Been Kim*, Rajiv Khanna*, Oluwasanmi Koyejo* NIPS 2016 (Oral) [paper] [Talk slides] [code] [bibtex]
@inproceedings{kim:2016MMD,
title={Examples are not Enough, Learn to Criticize! Criticism for Interpretability},
author={Been Kim, Rajiv Khanna and Sanmi Koyejo },
booktitle={Advances in Neural Information Processing Systems},
year={2016}
}
Pursuits in Structured Non-Convex Matrix Factorizations Rajiv Khanna, Francesco Locatello, Michael Tschannen, Martin Jaggi. [paper][bibtex]
@article{khanna:2016pursuits,
author = {Rajiv Khanna AND Francesco Locatello AND Michael Tschannen AND Martin Jaggi},
title = {Pursuits in Structured Non-Convex Matrix Factorizations},
year = 2016,
journal= {arXiv},
note = {1602.04208v1}
}
Towards a Better Understanding of Predict and Count Models. S. Sathiya Keerthi, Tobias Schnabel, Rajiv Khanna. [paper]
Sparse Submodular Probabilistic PCA Rajiv Khanna, Joydeep Ghosh, Russell A. Poldrack, Oluwasanmi O. Koyejo AISTATS 2015 (Oral) [paper][bibtex]
@INPROCEEDINGS{khanna:2015ppca,
author = {Rajiv Khanna and Joydeep Ghosh and Russell A. Poldrack and Oluwasanmi Koyejo},
title = {Sparse Submodular Probabilistic {PCA}},
booktitle = {AISTATS},
year = {2015},
}
A Deflation Method for Probabilistic PCA. Rajiv Khanna, Joydeep Ghosh, Russell A. Poldrack, Oluwasanmi Koyejo. NIPS 2015 Workshop on Advances in Approximate Bayesian Inference [paper]
On Prior Distributions and Approximate Inference for Structured Variables Oluwasanmi O. Koyejo, Rajiv Khanna, Joydeep Ghosh, Russell A. Poldrack NIPS 2014 [paper] [ supplement ] [bibtex]
@INPROCEEDINGS{koyejo:2014priors,
author = {Oluwasanmi Koyejo and Rajiv Khanna and Joydeep Ghosh and Russell A. Poldrack},
title = {On Prior Distributions and Approximate Inference for Structured Variables},
booktitle = {NIPS },
year = {2014},
}
DPM: A State Space Model for Large-Scale Direct Marketing Yubin Park, Rajiv Khanna, Joydeep Ghosh, Daniel Mihalko. CoRR abs/1507.01135
Parallel matrix factorization for binary response. Rajiv Khanna, Liang Zhang, Deepak Agarwal, Bee-Chung Chen. IEEE BigData Conference 2013: 430-438
Estimating rates of rare events with multiple hierarchies through scalable log-linear models. Deepak Agarwal, Rahul Agrawal, Rajiv Khanna, Nagaraj Kota. KDD 2010: 213-222
Translating relevance scores to probabilities for contextual advertising. Deepak Agarwal, Evgeniy Gabrilovich, Robert Hall, Vanja Josifovski, Rajiv Khanna CIKM 2009: 1899-1902
Structured learning for non-smooth ranking losses. Soumen Chakrabarti, Rajiv Khanna, Uma Sawant, Chiru Bhattacharyya. KDD 2008: 88-96
