publications
publications by categories in reversed chronological order. generated by jekyll-scholar.
2026
- Exploiting Missing Data Remediation Strategies Using Adversarial Missingness AttacksIn Fortieth AAAI Conference on Artificial Intelligence, 2026
2025
- Patching LLMs Like Software: A Lightweight Method for Improving Safety Policies in Large Language ModelsWorkshop paper ICLR 2026 Trustworthy AI, 2025arXiv:2511.08484
- Forecasting Fails: Unveiling Evasion Attacks in Weather Prediction ModelsDec 2025
- Group Fair Federated Learning via Stochastic Kernel RegularizationTransactions on Machine Learning Research, Dec 2025
- PEEL the Layers and Find Yourself: Revisiting Inference-Time Data Leakage for Residual Neural NetworksIn 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), Dec 2025
- Replacing Paths with Connection-Biased Attention for Knowledge Graph CompletionIn Proceedings of the AAAI Conference on Artificial Intelligence, Dec 2025
- Utility-Privacy Tradeoff in Federated LearningIn Federated Learning for Medical Imaging, Dec 2025
2024
- Aligners: Decoupling LLMs and AlignmentIn Findings of the Association for Computational Linguistics: EMNLP 2024, Nov 2024
- Adversarial Missingness Attacks on Causal Structure LearningACM Transactions on Intelligent Systems and Technology, Dec 2024
- Iterative Thresholding for Non-Linear Learning in the Strong \(\varepsilon\)-Contamination ModelSep 2024
2023
- Simple Disentanglement of Style and Content in Visual RepresentationsIn International Conference on Machine Learning, ICML 2023, Sep 2023
- Deception by Omission: Using Adversarial Missingness to Poison Causal Structure LearningIn Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023, Sep 2023
- Word Sense Induction with Knowledge Distillation from BERTCoRR, Sep 2023
- Reduced Label Complexity For Tight \(\ell_2\) RegressionCoRR, Sep 2023
- A Cross-Domain Evaluation of Approaches for Causal Knowledge ExtractionCoRR, Sep 2023
- Improving Neural Ranking Models with Traditional IR MethodsCoRR, Sep 2023
- Reprogrammable-FL: Improving Utility-Privacy Tradeoff in Federated Learning via Model ReprogrammingIn 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), Sep 2023
2022
- An Adversarial Perspective on Accuracy, Robustness, Fairness, and Privacy: Multilateral-Tradeoffs in Trustworthy MLIEEE Access, Sep 2022
- SPOCK @ Causal News Corpus 2022: Cause-Effect-Signal Span Detection Using Span-Based and Sequence Tagging ModelsIn Proceedings of the 5th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text, CASE@EMNLP 2022, Sep 2022
- TINKER: A framework for Open source Cyberthreat IntelligenceIn IEEE International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom 2022, Sep 2022
- Extending Model-X Framework to Missing DataFeb 2022
2021
- Sparse Graph Based Sketching for Fast Numerical Linear AlgebraIn IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Feb 2021
- Learning Fair Canonical Polyadical Decompositions using a Kernel Independence CriterionCoRR, Feb 2021
- Reading StackOverflow Encourages Cheating: Adding Question Text Improves Extractive Code GenerationCoRR, Feb 2021
- Output Randomization: A Novel Defense for both White-box and Black-box Adversarial ModelsCoRR, Feb 2021
2020
- Adaptive Sketching for Fast and Convergent Canonical Polyadic DecompositionIn Proceedings of the 37th International Conference on Machine Learning, ICML 2020, Feb 2020
- NoisyCUR: An Algorithm for Two-Cost Budgeted Matrix CompletionIn Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2020, Feb 2020
- MALOnt: An Ontology for Malware Threat IntelligenceCoRR, Feb 2020
2019
- Alchemist: An Apache Spark \(⇔\) MPI interfaceConcurr. Comput. Pract. Exp., Feb 2019
- Group Collaborative Representation for Image Set ClassificationInt. J. Comput. Vis., Feb 2019
- Scalable Kernel K-Means Clustering with Nyström Approximation: Relative-Error BoundsJ. Mach. Learn. Res., Feb 2019
- Fast Fixed Dimension L2-Subspace Embeddings of Arbitrary Accuracy, With Application to L1 and L2 TasksCoRR, Feb 2019
2018
- Accelerating a Distributed CPD Algorithm for Large Dense, Skewed TensorsIn IEEE International Conference on Big Data (IEEE BigData 2018), Seattle, WA, USA, December 10-13, 2018, Feb 2018
- Accelerating Large-Scale Data Analysis by Offloading to High-Performance Computing Libraries using AlchemistIn Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 2018, London, UK, August 19-23, 2018, Feb 2018
2017
- Sketched Ridge Regression: Optimization Perspective, Statistical Perspective, and Model AveragingJ. Mach. Learn. Res., Feb 2017
- Skip-Gram - Zipf + Uniform = Vector AdditivityIn Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, Canada, July 30 - August 4, Volume 1: Long Papers, Feb 2017
- Breaking Locality Accelerates Block Gauss-SeidelIn Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017, Feb 2017
- Sketched Ridge Regression: Optimization Perspective, Statistical Perspective, and Model AveragingIn Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017, Feb 2017
2016
- Revisiting the Nystrom Method for Improved Large-scale Machine LearningJ. Mach. Learn. Res., Feb 2016
- Matrix factorizations at scale: A comparison of scientific data analytics in spark and C+MPI using three case studiesIn 2016 IEEE International Conference on Big Data (IEEE BigData 2016), Washington DC, USA, December 5-8, 2016, Feb 2016
- A Multi-Platform Evaluation of the Randomized CX Low-Rank Matrix Factorization in SparkIn 2016 IEEE International Parallel and Distributed Processing Symposium Workshops, IPDPS Workshops 2016, Chicago, IL, USA, May 23-27, 2016, Feb 2016
2015
- Hardware compliant approximate image codesIn IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, June 7-12, 2015, Feb 2015
- Spectral Clustering via the Power Method - ProvablyIn Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6-11 July 2015, Feb 2015
- Tensor machines for learning target-specific polynomial featuresCoRR, Feb 2015
2014
- Compact Random Feature MapsIn Proceedings of the 31th International Conference on Machine Learning, ICML 2014, Beijing, China, 21-26 June 2014, Feb 2014
- piCholesky: Polynomial Interpolation of Multiple Cholesky Factors for Efficient Approximate Cross-ValidationApr 2014
2013
- Improved Matrix Algorithms via the Subsampled Randomized Hadamard TransformSIAM J. Matrix Anal. Appl., Apr 2013
- Revisiting the Nystrom method for improved large-scale machine learningIn Proceedings of the 30th International Conference on Machine Learning, ICML 2013, Atlanta, GA, USA, 16-21 June 2013, Apr 2013
- Approximate Spectral Clustering via Randomized SketchingCoRR, Apr 2013
- Topics in Randomized Numerical Linear AlgebraCalifornia Institute of Technology, Apr 2013
2012
- The Masked Sample Covariance Estimator: An Analysis Using Matrix Concentration InequalitiesInformation and Inference: A Journal of the IMA, Apr 2012
2011
- The spectral norm error of the naive Nystrom extensionCoRR, Apr 2011
- Tail Bounds for All Eigenvalues of a Sum of Random MatricesApr 2011
2009
- Error Bounds for Random Matrix Approximation SchemesNov 2009