Anshumali Shrivastava Professor Computer Science and Ken Kennedy Institute, Rice University I am currently at Meta Superintelligence Labs (on Leave from Rice) Founder: ThirdAI Corp. (Acquired in August 2025) xmad.ai (Sept 2024) --> Workato (July 2025) In past I have had positions at Amazon, AWS, Blackstone, and FICO Office: Duncan Hall 2083 Email: anshumali AT rice.edu Phone: 713 348 3049 Follow @Anshumali_

Blogs

• I write about AI, Businesses, LLMs.[Medium Articles]
• Deep Learning Breakthrough: a sub-linear deep learning algorithm that does not need a GPU KDNuggets (Invited Blog) 2020 [blog]

Recent Preprints

• Replacing Softmax Similarity with a Sharpened Angular Similarity: Theory and Practice of Scaling To Billion-Context Attention.
  Sahil Joshi, Agniva Chowdhury, Amar Kanakamedala, Ekam Singh, Evan Tu, Anshumali Shrivastava
  Arxiv:[Paper]
• To Compress or Not? Pushing the Frontier of Lossless GenAI Model Weights Compression with Exponent Concentration .
  Zeyu Yang, Tianyi Zhang, Jianwen Xie, Chuan Li, Zhaozhuo Xu, Anshumali Shrivastava
  Arxiv:[Paper]
• REFRAG: Rethinking RAG based Decoding .
  Xiaoqiang Lin, Aritra Ghosh, Bryan Kian Hsiang Low, Anshumali Shrivastava, Vijai Mohan
  Arxiv:[Paper]

Commercial Deployments

• Amazon Product Search: We depoyed our hashing algorithm based on FLASH Engine (SIGMOD 2018) in the Amazon Search Engine. Every query on amazon.com benefits from our research work! [Details]
• BOLT Engine At ThirdAI Corp. we are developing spasity and hash tables to democratise AI on CPUs [Details]

Selected Talks

• AI Journey Keynote: Scalable and Sustainable AI for Everyone [video]
• SLIDE A Sub-Linear Deep Learning Algorithm That Does Not Need a GPU [Intel-HPC-AI]
• Zero-Communication Model Parallelism for Distributed Extreme-Scale Deep Learning [YouTube]
• Locality Sensitive Hashing for Adaptive Sampling and Unbiased Estimation(Beating Random Sampling in O(1) amortized) [YouTube]
• Designing Next Generation Resource-Frugal Deep Learning Algorithms [YouTube]
• Hashing Algorithms for Large-Scale Machine Learning[YouTube]
• Randomized Algorithms Accelerated over CPU-GPU for Ultra-High Dimensional Similarity Search [YouTube]
• Hashing for Maximum Inner Product Search (MIPS)[YouTube]
• An Efficient Replacement for Minwise Hashing[ICML17][KDNuggetsBlog]

Research

• Large Scale Machine Learning
• Scalable and Sustainable Deep Learning
• Randomized Algorithms for AI/LLMs
• Information Retreival

More details on my research can be found at RUSHLab

RUSH Lab GitHub Page RUSH Lab GitHub

Fundings The VMware University Research Fund, Intel Research, Total Research, Adobe, ONR DURIP, SHELL, NSF BIGDATA, ONR BRC, AFOSR YIP, NSF CAREER, NSF-IIS-1718478, Amazon Research Awards, NVIDIA GPU Grant

Multiple Postdocs/Research Scientist Positions Avaiable. Drop an email with your CV
Research Focus: Large-Scale Machine Learning, Deep Learning, Randomized Algorithms, High-Performance Computing

Awards/Honors

• Charles W. Duncan Jr. Achievement Award for Outstanding Faculty 2023
• IIT Kharagpur, Young Alumni Achiever Award (YAAA), 2023
• Outstanding Paper Award, MLSys 2022
• Awarded Tenure at Rice (Early) [Link]
• George R. Brown School of Enginnering, Rice University, 2021 Young Faculty Research Award 2021[Link]
• Adobe Data Science Research Awards 2021[Link]
• National Academy of Engineers (NAE) 2019 US Frontiers of Engineering Alum [Link]
• ACM SIGMOD 2018 Most Reproducible Paper Award [Link]
• Science News 10 Scientist to Watch, 2018 [Science News][Rice News]
• Best Student Paper Competition Award at IISA, 2018
• Amazon Research Awards, 2017 [News]
• AFOSR Young Investigator Award (YIP), 2017 [News]
• NSF CAREER AWARD, 2017 [News]
• NIPS Best Paper, 2014 [News]
• IEEE/ACM ASONAM Best Paper, 2014
• Institute Silver Medal, IIT Kharagpur, 2008

Selected Press Coverage and Live Broadcast

• ThirdAI Founder Works to Make Artificial Intelligence More Efficient. [Wall Street Journal]
• ThirdAI raises $6M to democratize AI to any hardware. [TechCrunch]
• Scientist discovers new way to filter fake news 2020 [Tribune]
• Two Big, New Threats to NVDA Stock That Should Worry Investors Investorplace 2020 [article]
• How to test for COVID-19 efficiently Amazon Science (Invited Blog) 2020 [blog]
• An algorithm could make CPUs a cheap way to train AI Engadget, Science Daily, InsideHPC, and many more 2020 [article]
• Deep Learning breakthrough made by Rice University scientists ArsTechnica 2019 [article]
• Hash Your Way To a Better Neural Network IEEE Spectrum 2019 [article]
• Anshumali Shrivastava uses AI to wrangle torrents of data Science News, SN10 article 2018 [article]
• Using New Data Techniques To Estimate The Number Syrian Of War Dead Houston Matters, Live Broadcast 2018 [Radio Interview]
• Making Friends Online is a Number Game Irish Times, Document Journal, and many more. 2018 [News]
• Fundamental Breakthrough in 2-Decade Old Algorithm Redefines Big-Data Benchmarks KDNuggets 2017 [Blog]
• Deep learning breakthrough could slash computation and time by 95 percent World News Network, ScienceMagzine, NSF, Innovationtoronto, and many more. 2017 [Article]
• Beyond Silicon: Squeezing More Out of Chips New York Times 2016 [NYTimes Article]

Teaching

• Fall 2025: Probabilistic Algorithms and Data Structures(COMP 480/580)
• Spring 2025: Machine Learning (COMP 642)
• Fall 2024: Probabilistic Algorithms and Data Structures(COMP 480/580)
• Spring 2024: Machine Learning (COMP 642)
• Fall 2023: Probabilistic Algorithms and Data Structures(COMP 480/580)
• Spring 2023: Machine Learning (COMP 642)
• Fall 2022: Probabilistic Algorithms and Data Structures(COMP 480/580)
• Spring 2022: Machine Learning (COMP 642)
• Fall 2021: Graduate Seminar in Machine Learning (COMP 640)
• Spring 2021: Probabilistic Algorithms and Data Structures(COMP 480/580)
• Fall 2020: Graduate Seminar in Machine Learning (COMP 640)
• Spring 2020: Probabilistic Algorithms and Data Structures(COMP 480/580)
• Fall 2019: Graduate Seminar in Machine Learning (COMP 640)
• Spring 2019: Probabilistic Algorithms and Data Structures(COMP 480/580)
• Fall 2017: Graduate Seminar in Machine Learning (COMP 640)
• Spring 2017: Large Scale Machine Learning (COMP 441/COMP 552)
• Fall 2016: Graduate Seminar in Machine Learning (COMP 640)
• Spring 2016: Large Scale Machine Learning (COMP 441)
• Fall 2015: Graduate Seminar in Machine Learning (COMP 640)

Thesis

• Probabilistic Hashing Techniques for Big-Data. [pdf]
  Cornell University, 2015.
  

Publications (Full Papers Only)

2025

• 70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float. [To appear]
  Tianyi Zhang, Shaochen (Henry) Zhong, Mohsen Hariri, Vipin Chaudhary, Yang Sui, Xia Hu, Anshumali Shrivastava
  Neural Information Processing Systems (NeurIPS) 2025.
  
• Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining. [To appear]
  Haochen Zhang, Junze Yin, Guanchu Wang, Zirui Liu, Lin Yang, Tianyi Zhang, Anshumali Shrivastava, Vladimir Braverman
  Neural Information Processing Systems (NeurIPS) 2025.
  
• Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation. [pdf coming soon]
  Tianyi Zhang, Junda Su, Aditya Desai, Oscar Wu, Zhaozhuo Xu, Anshumali Shrivastava
  International Conference on Machine Learning (ICML) 2025.
  
• CoVE: Compressed Vocabulary Expansion Makes Better LLM-based Recommender Systems. [pdf coming soon]
  Haochen Zhang, Tianyi Zhang, Junze Yin, Oren Gal, Anshumali Shrivastava, Vladimir Braverman
  Annual Meeting of the Association for Computational Linguistics (ACL) 2025.
  
• Empowering Distributed Training with Sparsity-driven Data Synchronization. [pdf coming soon]
  Zhuang Wang, Yuke Wang, Zhaozhuo Xu, Jingyi Xi, Anshumali Shrivastava, T. S. Eugene Ng
  USENIX Symposium on Operating Systems Design and Implementation (OSDI) 2025.
  
• LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid.[To appear]
  Tianyi Zhang and Anshumali Shrivastava
  International Conference on Learning Representations (ICLR) 2025.
  
• IDentity with Locality: An ideal hash for gene sequence search. [To appear]
  Tianyi Zhang, Gaurav Gupta, Aditya Desai, Anshumali Shrivastava
  SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD) 2025.
  

  2024

• KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization. [To appear]
  Tianyi Zhang, Jonah Wonkyu Yi, Zhaozhuo Xu, Anshumali Shrivastava
  Neural Information Processing Systems (NeurIPS) 2024.
  
• NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention. [To appear]
  Tianyi Zhang, Jonah Wonkyu Yi, Bowen Yao, Zhaozhuo Xu, Anshumali Shrivastava
  Neural Information Processing Systems (NeurIPS) 2023.
  
• Accelerating Inference with Fast and Expressive Sketch Structured Transform. [To appear]
  Aditya Desai, Kimia Saedi, Apoorv Walia, Jihyeong Lee, Keren Zhou, Anshumali Shrivastava
  Neural Information Processing Systems (NeurIPS) 2024.
  
• Soft Prompt Recovers Compressed LLMs, Transferably. [pdf coming soon]
  Zhaozhuo Xu, Zirui Liu, Beidi Chen, Shaochen Zhong, Yuxin Tang, Jue WANG, Kaixiong Zhou, Xia Hu, Anshumali Shrivastava
  International Conference on Machine Learning (ICML) 2024.
  
• In defense of parameter sharing for model-compression .
  Aditya Desai and Anshumali Shrivastava
  International Conference on Learning Representations (ICLR) 2024.
  
• Learning Scalable Structural Representations for Link Prediction with Bloom Signatures [To appear]
  Tianyi Zhang, Haoteng Yin, Rongzhe Wei, Pan Li, and Anshumali Shrivastava
  International World Wide Web Conference (WWW) 2024.
  

  2023

• One-Pass Distribution Sketch for Measuring Data Heterogeneity in Federated Learning. [To appear]
  Zichang Liu, Zhaozhuo Xu, Benjamin Coleman, Anshumali Shrivastava
  Neural Information Processing Systems (NeurIPS) 2023.
  
• DESSERT: An Efficient Algorithm for Vector Set Search with Vector Set Queries. [To appear]
  Joshua Engels, Benjamin Coleman, Vihan Lakshman, Anshumali Shrivastava
  Neural Information Processing Systems (NeurIPS) 2023.
  
• Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time. [To appear]
  Zichang Liu, Aditya Desai, Fangshuo Liao, Weitao Wang, Victor Xie, Zhaozhuo Xu, Anastasios Kyrillidis, Anshumali Shrivastava
  Neural Information Processing Systems (NeurIPS) 2023.
  
• BOLT: An Automated Deep Learning Framework for Training and Deploying Large-Scale Search and Recommendation Models on Commodity CPU Hardware. [To appear]
  Vihan Lakshman, Nicholas Meisburger, Benito Geordie, David Torres Ramos, Joshua Engels, Pratik Pranav, Benjamin Coleman, Benjamin Meisburger, Shubh Gupta, Yashwanth Adunukota, Tharun Medini, Anshumali Shrivastava
  ACM International Conference on Information and Knowledge Management (CIKM) 2023.
  
• Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time. [pdf coming soon]
  Zichang Liu, Jue WANG, Tri Dao, Tianyi Zhou, Binhang Yuan, Zhao Song, Anshumali Shrivastava, Ce Zhang, Yuandong Tian, Christopher Re, Beidi Chen
  International Conference on Machine Learning (ICML) 2023. Oral.
  
• Hardware-aware compression with Random Operation Access Specific Tile (ROAST) hashing. [pdf coming soon]
  Aditya Desai, Keren Zhou, and Anshumali Shrivastava
  International Conference on Machine Learning (ICML) 2023.
  
• Learning Multimodal Data Augmentation in Feature Space .
  Zichang Liu, Zhiqiang Tang, Xingjian Shi, Aston Zhang, Mu Li, Anshumali Shrivastava, Andrew Gordon Wilson
  International Conference on Learning Representations (ICLR) 2023.
  
• From Research to Production: Towards Scalable and Sustainable Neural Recommendation Models on Commodity CPU Hardware .
  Vihan Lakshman, Anshumali Shrivastava, Tharun Medini, Nicholas Meisburger, Joshua Engels, David Torres Ramos, Benito Geordie, Pratik Pranav, Shubh Gupta, Yashwanth Adunukota, Siddharth Jain
  Conference series On Recommendation Systems (RecSys) 2023.
  
• Graph Self-supervised Learning via Proximity Divergence Minimization .
  Tianyi Zhang, Zhenwei DAI, Zhaozhuo Xu, Anshumali Shrivastava
  Conference on Uncertainty in Artificial Intelligence (UAI) 2023.
  
• A Tale of Two Efficient Value Iteration Algorithms for Solving Linear MDPs with Large Action Space .
  Zhaozhuo Xu, Zhao Song, Anshumali Shrivastava
  International Conference on Artificial Intelligence and Statistics (AISTATS) 2023.
  

  2022

• Structural Contrastive Representation Learning for Zero-shot Multi-label Text Classification . [To appear]
  Tianyi Zhang, Zhaozhuo Xu, Tharun Medini, Anshumali Shrivastava
  Empirical Methods in Natural Language Processing (EMNLP) 2022.
• The trade-offs of model size in large recommendation models : A 10000x compressed criteo-TB DLRM model (100 GB parameters to mere 10MB) . [To appear]
  Aditya Desai, Anshumali Shrivastava
  Neural Information Processing Systems (NeurIPS) 2022.
  
• Retaining Knowledge for Learning with Dynamic Definition . [To appear]
  Zichang Liu, Benjamin Coleman, Tianyi Zhang, Anshumali Shrivastava
  Neural Information Processing Systems (NeurIPS) 2022.
  
• Graph Reordering for Cache-Efficient Near Neighbor Search . [To appear]
  Benjamin Coleman, Santiago Segarra, Alex Smola, Anshumali Shrivastava
  Neural Information Processing Systems (NeurIPS) 2022.
  
• One-Pass Diversified Sampling with Application to Terabyte-Scale Genomic Sequence Streams. [pdf coming soon]
  Benjamin Coleman, Benito Geordie, Li Chou, R. A. Leo Elworth, Todd J. Treangen, and Anshumali Shrivastava
  International Conference on Machine Learning (ICML) 2022.
  
• DRAGONN: Distributed Randomized Approximate Gradients of Neural Networks . [pdf coming soon]
  Zhaozhuo Xu, Zhuang Wang, Xinyu Crystal Wu, Anshumali Shrivastava, and Eugene Ng
  International Conference on Machine Learning (ICML) 2022.
  
• BLISS: A Billion scale Index using Iterative Re-partitioning.[To appear]
  Gaurav Gupta, Tharun Medini, Anshumali Shrivastava, and Alex Smola
  SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD) 2022.
  
• HALOS: Hashing Large Output Space for Cheap Inference. [To appear]
  Zichang Liu, Zhaozhuo Xu, Alan Ji, Junyan Zhang, Jonathan Li, Beidi Chen, Anshumali Shrivastava
  Conference on Machine Learning and Systems (MLSys) 2022.
  
• Random Offset Block Embedding Array (ROBE) for CriteoTB Benchmark MLPerf DLRM Model : 1000X Compression and 3.1X Faster Inference. [To appear]
  Aditya Desai, Li Chou, Anshumali Shrivastava
  Conference on Machine Learning and Systems (MLSys) 2022. Outstanding Paper Award
  
• ROSE: Robust Caches for Amazon Product Search [To appear]
  Chen Luo, Vihan Lakshman, Anshumali Shrivastava, Tianyu Cao, Sreyashi Nag, Rahul Goutam, Hanqing Lu, Yiwei Song and Yin Bing
  International World Wide Web Conference (WWW) 2022.
  
• Learning to Retrieve Relevant Experiences for Motion Planning [To appear]
  Constantinos Chamzas, Aedan Cullen, Anshumali Shrivastava and Lydia Kavraki
  IEEE International Conference on Robotics and Automation (ICRA) 2022.
  

  2021

• Breaking the Linear Iteration Cost Barrier for Some Well-known Conditional Gradient Methods Using MaxIP Data-structures. [To appear]
  Zhaozhuo Xu, Zhao Song, and Anshumali Shrivastava
  Neural Information Processing Systems (NeurIPS) 2021.
  
• Raw Nav-merge Seismic Data to Subsurface Properties with MLP based Multi-Modal Information Unscrambler. [To appear]
  Aditya Desai, Zhaozhuo Xu, Menal Gupta, Anu Chandran, Antoine Vial-Aussavy and Anshumali Shrivastava
  Neural Information Processing Systems (NeurIPS) 2021.
  
• Locality Sensitive Teaching. [To appear]
  Zhaozhuo Xu, Beidi Chen, Chaojian Li, Weiyang Liu, Le Song, Yingyan Lin, and Anshumali Shrivastava
  Neural Information Processing Systems (NeurIPS) 2021.
  
• Practical Near Neighbor Search via Group Testing. [to appear]
  Joshua Engels, Benjamin Coleman, and Anshumali Shrivastava
  Neural Information Processing Systems (NeurIPS) 2021. Spotlight
  
• A Tale of Two Efficient and Informative Negative Sampling Distributions. [pdf coming soon]
  Shabnam Daghaghi, Nicholas Meisburger, Mengnan Zhao, Beidi Chen, Tharun Medini, and Anshumali Shrivastava
  International Conference on Machine Learning (ICML) 2021. Long Talk.
  
• Efficient and Less Centralized Federated Learning. [pdf coming soon]
  Li Chou, Zichang Liu, Zhuang Wang, and Anshumali Shrivastava
  European Conference on Machine Learning (ECML-PKDD) 2021.
  
• SDM-Net: A Simple and Effective Model for Generalized Zero-Shot Learning [pdf coming soon]
  Shabnam Daghaghi, Tharun Medini, and Anshumali Shrivastava
  Conference on Uncertainty in Artificial Intelligence(UAI) 2021.
  
• A One-Pass Distributed and Private Sketch for Most Machine Learning at Scale. [pdf coming soon]
  Ben Coleman and Anshumali Shrivastava
  ACM Conference on Computer and Communications Security ACM (CCS) 2021.
  
• Active Sampling Count Sketch (ASCS) for Online SparseEstimation of a Trillion Scale Covariance Matrix. [pdf coming soon]
  Zhenwei Dai, Aditya Desai, and Anshumali Shrivastava
  International Conference on Management of Data (SIGMOD) 2021.
  
• Fast Processing and Querying of 170TB of Genomics Data via a Repeated And Merged BloOm Filter (RAMBO). [pdf coming soon]
  Gaurav Gupta, Minghao Yan, Ben Coleman, Tharun Medini, Bryce Kyllis, Leo Elworth, Todd Treangen, Anshumali Shrivastava
  International Conference on Management of Data (SIGMOD) 2021.
  
• Accelerating SLIDE Deep Learning on Modern CPUs: Vectorization, Quantizations, Memory Optimizations, and More. [pdf]
  Shabnam Daghaghi, Nicholas Meisburger, Mengnan Zhao, Yong Wu, Gobrial Sameh, Charlie Tai, and Anshumali Shrivastava
  Conference on Machine Learning and Systems (MLSys) 2021.
  
• Learning Sampling Distributions Using Local 3D Workspace Decompositions for Motion Planning in High Dimensions.[Coming Soon]
  C. Chamzas, Z. Kingston, C. Quintero-Pena, A. Shrivastava, and L. E. Kavraki
  International Conference on Robotics and Automation (ICRA) 2021 Nominated for Best Paper in Cognitive Robotics
  
• MONGOOSE: A Learnable LSH Framework for Efficient Neural Network Training . [pdf]
  Beidi Chen, Zichang Liu, Binghui Peng, Zhaozhuo Xu, Jonathan Lingjie Li, Tri Dao, Zhao Song, Anshumali Shrivastava, Christopher Re
  International Conference on Learning Representations (ICLR) 2021. Oral.
  
• SOLAR: Sparse Orthogonal Learned and Random Embeddings . [pdf]
  Tharun Medini, Beidi Chen, Anshumali Shrivastava
  International Conference on Learning Representations (ICLR) 2021.
  
• Revisiting Consistent Hashing with Bounded Loads . [pdf]
  John Chen, Ben Coleman, and Anshumali Shrivastava
  AAAI Conference on Artificial Intelligence (AAAI) 2021.
  
• Neighbor Oblivious Learning(NObLe) for Device Localization and Tracking. [pdf]
  Zichang Liu, Li Chou, and Anshumali Shrivastava
  Design, Automation and Test in Europe Conference (DATE) 2021.
  

  2020

• Adaptive Learned Bloom Filter (Ada-BF): Efficient Utilization of the Classifier with Application to Real-Time Information Filtering on the Web. [pdf]
  Zhenwei Dai and Anshumali Shrivastava
  Neural Information Processing Systems (NeurIPS) 2020.
  
• RACE: Sub-Linear Memory Sketches for Approximate Near-Neighbor Search on Streaming Data [arxiv]
  Ben Coleman, Richard Baraniuk, and Anshumali Shrivastava
  International Conference on Machine Learning (ICML) 2020.
  
• Angular Visual Hardness. [preprint]
  Beidi Chen, Weiyang Liu, Animesh Garg, Zhiding Yu, Anshumali Shrivastava, Jan Kautz, Anima Anandkumar
  International Conference on Machine Learning (ICML) 2020.
  
• Mutual Information Estimation using LSH Sampling. [pdf]
  Ryan Spring and Anshumali Shrivastava
  International Joint Conference on Artificial Intelligence (IJCAI) 2020.
  
• SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large Scale Deep Learning Systems. [pdf]
  Beidi Chen, Tharun Medini, James Farwell, Gobrial Sameh, Charlie Tai, and Anshumali Shrivastava
  Conference on Machine Learning and Systems (MLSys) 2020.
  
• To Petabytes and Beyond: Recent advances in probabilistic and signal processing algorithms and their application to metagenomics. [pdf]
  R A Leo Elworth, Qi Wang, Pavan K Kota, C J Barberan, Benjamin Coleman, Advait Balaji, Gaurav Gupta, Richard G Baraniuk, Anshumali Shrivastava, Todd J Treangen
  Nucleic Acids Research (NAR) 2020.
  
• Sub-linear Memory Sketches for Approximate Kernel Density Estimation on Streaming Data [pdf]
  Ben Coleman and Anshumali Shrivastava.
  International World Wide Web Conference (WWW) 2020.
  
• FourierSAT: A Fourier Expansion-Based Algebraic Framework for Solving Hybrid Boolean Constraints. [pdf]
  Anastasios Kyrillidis, Anshumali Shrivastava, Moshe Y. Vardi, and Zhiwei Zhang
  AAAI Conference on Artificial Intelligence (AAAI) 2020.Oral.
  

  2019

• Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Products . [pdf]
  Tharun Medini, Qixuan Huang, Yiqiu Wang, Vijai Mohan, Anshumali Shrivastava
  Neural Information Processing Systems (NeurIPS) 2019.
  (Earlier Version in WWW 2018 Extreme Classification Workshop)
  
• Fast and Accurate Stochastic Gradient Estimation. [pdf]
  Beidi Chen, Yingchen Xu, Anshumali Shrivastava
  Neural Information Processing Systems (NeurIPS) 2019.
  (Earlier Version in ICLR 2018 Workshop)
  
• Compressing Gradient Optimizers via Count-Sketches. [preprint]
  Ryan Spring, Anastasios Kyrillidis, Vijai Mohan, Anshumali Shrivastava
  International Conference on Machine Learning (ICML) 2019.
  
• Using Local Experiences For Global Motion Planning.
  C. Chamzas, A. Shrivastava, and L. E. Kavraki
  International Conference on Robotics and Automation (ICRA) 2019
  
• Scaling-up Split-Merge MCMC with Locality Sensitive Sampling (LSS). [pdf]
  Chen Luo and Anshumali Shrivastava
  AAAI Conference on Artificial Intelligence (AAAI) 2019.Oral.
  
• Privacy Adversarial Network: Representation Learning for Mobile Data Privacy. [pdf]
  Sicong Liu, Junzhao Du, Anshumali Shrivastava, Lin Zhong
  Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous TechnologiesIMWUT 2019.
  
• Learning Feasibility for Task and Motion Planning in Tabletop Environments [pdf].
  A. Wells, N. Dantam, A. Shrivastava, and L. E. Kavraki
  IEEE Robotics and Automation Letters (RA-L) 2019
  

  2018

• Topkapi: Parallel and Fast Algorithm for Finding Top-K Frequent Elements. [pdf]
  Ankush Mandal, Cary Jiang, Anshumali Shrivastava, Vivek Sarkar
  Neural Information Processing Systems (NeurIPS) 2018.
  
• MISSION: Ultra-Large Scale Feature Selection using Count-Sketches. [pdf]
  Amirali Aghazadeh, Ryan Spring, Daniel LeJeune, Gautam Dasarathy, Anshumali Shrivastava, Richard G. Baraniuk
  International Conference on Machine Learning (ICML) 2018.
  
• Densified Winner Take All (WTA) Hashing for Sparse Datasets. [pdf]
  Beidi Chen and Anshumali Shrivastava.
  Conference on Uncertainty in Artificial Intelligence (UAI) 2018.
  
• TINET: Learning Invariant Networks via Knowledge Transfer. [pdf]
  Chen Luo, Zhengzhang Chen, Lu-An Tang, Anshumali Shrivastava, Zhichun Li,Haifeng Chen, Jieping Ye
  SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD) 2018. Oral.
  
• FLASH: Randomized Algorithms Accelerated over CPU-GPU for Ultra-High Dimensional Similarity Search. [pdf]
  Yiqiu Wang, Anshumali Shrivastava, Jonathan Wang, Junghee Ryu
  International Conference on Management of Data (SIGMOD) 2018.
  Most Reproducible Paper Award of ACM SIGMOD 2018.
  
• Unique Entity Estimation with Application to the Syrian Conflict. [pdf]
  Beidi Chen, Anshumali Shrivastava, Rebecca Steorts
  Annals of Applied Statisitcs(AoAS) 2018.
  Best Student Paper Award at IISA 2018.
  
• Jaccard Affiliation Graph (JAG) Model For Explaining Overlapping Community Behaviors. [pdf] [slides]
  Chen Luo and Anshumali Shrivastava
  IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) 2018. Oral.
  
• Probabilistic Blocking with An Application to the Syrian Conflict. [pdf]
  Rebecca Steorts and Anshumali Shrivastava
  Privacy in Statistical Databases (PSD) 2018.
  
• Arrays of (locality-sensitive) Count Estimators (ACE): High-Speed Anomaly Detection on the Edge [pdf]
  Chen Luo and Anshumali Shrivastava.
  International World Wide Web Conference (WWW) 2018.
  

  2017

• Scalable and Sustainable Deep Learning via Randomized Hashing [pdf]
  Ryan Spring and Anshumali Shrivastava
  SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD) 2017. Oral.
  
• Optimal Densification for Fast and Accurate Minwise Hashing . [pdf]
  Anshumali Shrivastava
  International Conference on Machine Learning (ICML) 2017.
  
• RHash: Robust Hashing via \ell_{\infty}-norm Distortion. [pdf]
  Amirali Aghazadeh, Andrew Lan, Anshumali Shrivastava, Richard G. Baraniuk
  International Joint Conferences on Artificial Intelligence (IJCAI) 2017.
  
• Location Detection for Navigation, Using IMUs with a Map, Through Coarse-Grained Machine Learning. [pdf]
  E. J. Jose Gonzalez, Chen Luo, Anshumali Shrivastava, Krishna Palem, Yongshik Moon, Soonhyun Noh, Daedong Park, Seongsoo Hong
  Design, Automation & Test in Europe Conference (DATE) 2017.
  
• SSH (Sketch, Shingle, & Hash) for Indexing Massive-Scale Time Series [pdf]
  Chen Luo and Anshumali Shrivastava.
  Journal of Machine Learning Research Vol 55 (JMLR) 2018.
  Invited for JMLR.
  

  2016

• Simple And Efficient Weighted Minwise Hashing. [pdf]
  Anshumali Shrivastava
  Neural Information Processing Systems (NIPS) 2016.
  
• Time Adaptive Sketches (Ada-Sketches) for Summarizing Data Streams.. [pdf]
  Anshumali Shrivastava, Christian Konig, Misha Bilenko
  International Conference on Management of Data (SIGMOD) 2016.
  
• CaPSuLe: Camera Based Positioning System Using Learning. [pdf]
  Yongshik Moon, Soonhyun Noh, Daedong Park, Chen Luo, Anshumali Shrivastava, Krishna Palem, Seongsoo Hong
  IEEE International System-on-Chip Conference (SOCC) 2016.
  
  • [NYTIMES ARTICLE], [ACM TechNews], [FUTURITY]

  2015 and Earlier

• Improved Asymmetric Locality Sensitive Hashing (ALSH) for Maximum Inner Product Search (MIPS). [pdf]
  Anshumali Shrivastava and Ping Li.
  Conference on Uncertainty in Artificial Intelligence (UAI) 2015.
  
• Asymmetric Minwise Hashing for Indexing Binary Inner Products and Set Containment. [pdf][slides]
  Anshumali Shrivastava and Ping Li.
  International World Wide Web Conference (WWW) 2015.
  
• Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS). [pdf][slides][video]
  Anshumali Shrivastava and Ping Li.
  Neural Information Processing Systems (NIPS) 2014.
  Best Paper Award.
  
• A New Space for Comparing Graphs. [pdf] [slides]
  Anshumali Shrivastava and Ping Li.
  IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) 2014.
  Best Paper Award.
  
• Improved Densification of One Permutation Hashing. [pdf]
  Anshumali Shrivastava and Ping Li.
  Conference on Uncertainty in Artificial Intelligence (UAI) 2014.
  
• In Defense of Minhash over Simhash. [pdf] [slides]
  Anshumali Shrivastava and Ping Li.
  International Conference on Artificial Intelligence and Statistics (AISTATS) 2014.
  
• Densifying One Permutation Hashing via Rotation for Fast Near Neighbor Search. [pdf][slides][video]
  Anshumali Shrivastava and Ping Li.
  International Conference on Machine Learning (ICML) 2014.
  
• Codings for Random Projections. [pdf]
  Ping Li, Michael Mitzenmacher and Anshumali Shrivastava .
  International Conference on Machine Learning (ICML) 2014.
  
• Beyond Pairwise: Provably Fast Algorithms for Approximate k-Way Similarity Search. [pdf] [slides]
  Anshumali Shrivastava and Ping Li.
  Neural Information Processing Systems (NIPS) 2013.
  
• Fast Near Neighbor Search in High-Dimensional Binary Data. [pdf] [slides]
  Anshumali Shrivastava and Ping Li.
  European Conference on Machine Learning (ECML) 2012.
  Top few papers invited for journal submission
  
• Fast multi-task learning for query spelling correction. [pdf]
  Xu Sun, Anshumali Shrivastava and Ping Li.
  ACM International Conference on Information and Knowledge Management (CIKM) 2012.
  
• Hashing Algorithms for Large Scale Learning [pdf]
  Ping Li, Anshumali Shrivastava, Joshua Moore and Christian Konig.
  Neural Information Processing Systems (NIPS) 2011.