Anshumali Shrivastava

Orcid: 0000-0002-5042-2856

According to our database1, Anshumali Shrivastava authored at least 157 papers between 2011 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
LeanQuant: Accurate Large Language Model Quantization with Loss-Error-Aware Grid.
CoRR, 2024

IDentity with Locality: An ideal hash for gene sequence search.
CoRR, 2024

KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization.
CoRR, 2024

NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention.
CoRR, 2024

Wisdom of Committee: Distilling from Foundation Model to Specialized Application Model.
CoRR, 2024

Learning Scalable Structural Representations for Link Prediction with Bloom Signatures.
Proceedings of the ACM on Web Conference 2024, 2024

Soft Prompt Recovers Compressed LLMs, Transferably.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

In defense of parameter sharing for model-compression.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023
Contractive error feedback for gradient compression.
CoRR, 2023

Adaptive Sampling for Deep Learning via Efficient Nonparametric Proxies.
CoRR, 2023

Heterogeneous federated collaborative filtering using FAIR: Federated Averaging in Random Subspaces.
CoRR, 2023

Zen: Near-Optimal Sparse Tensor Synchronization for Distributed DNN Training.
CoRR, 2023

CAPS: A Practical Partition Index for Filtered Similarity Search.
CoRR, 2023

Algorithmic Foundations of Inexact Computing.
CoRR, 2023

CARAMEL: A Succinct Read-Only Lookup Table via Compressed Static Functions.
CoRR, 2023

Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt.
CoRR, 2023

BOLT: An Automated Deep Learning Framework for Training and Deploying Large-Scale Neural Networks on Commodity CPU Hardware.
CoRR, 2023

A Theoretical Analysis Of Nearest Neighbor Search On Approximate Near Neighbor Graph.
CoRR, 2023

Graph Self-supervised Learning via Proximity Distribution Minimization.
Proceedings of the Uncertainty in Artificial Intelligence, 2023

From Research to Production: Towards Scalable and Sustainable Neural Recommendation Models on Commodity CPU Hardware.
Proceedings of the 17th ACM Conference on Recommender Systems, 2023

One-Pass Distribution Sketch for Measuring Data Heterogeneity in Federated Learning.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

DESSERT: An Efficient Algorithm for Vector Set Search with Vector Set Queries.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time.
Proceedings of the International Conference on Machine Learning, 2023

Hardware-Aware Compression with Random Operation Access Specific Tile (ROAST) Hashing.
Proceedings of the International Conference on Machine Learning, 2023

Learning Multimodal Data Augmentation in Feature Space.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

BOLT: An Automated Deep Learning Framework for Training and Deploying Large-Scale Search and Recommendation Models on Commodity CPU Hardware.
Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, 2023

Near Neighbor Search for Constraint Queries.
Proceedings of the IEEE International Conference on Big Data, 2023

A Tale of Two Efficient Value Iteration Algorithms for Solving Linear MDPs with Large Action Space.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022
Optimizing Learned Bloom Filters: How Much Should Be Learned?
IEEE Embed. Syst. Lett., 2022

Coordinated Science Laboratory 70th Anniversary Symposium: The Future of Computing.
CoRR, 2022

The trade-offs of model size in large recommendation models : A 10000 × compressed criteo-tb DLRM model (100 GB parameters to mere 10MB).
CoRR, 2022

Efficient model compression with Random Operation Access Specific Tile (ROAST) hashing.
CoRR, 2022

Distributed SLIDE: Enabling Training Large Neural Networks on Low Bandwidth and Simple CPU-Clusters via Model Parallelism and Sparsity.
CoRR, 2022

ROSE: Robust Caches for Amazon Product Search.
Proceedings of the Companion of The Web Conference 2022, Virtual Event / Lyon, France, April 25, 2022

Retaining Knowledge for Learning with Dynamic Definition.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

The trade-offs of model size in large recommendation models : 100GB to 10MB Criteo-tb DLRM model.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Graph Reordering for Cache-Efficient Near Neighbor Search.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

HALOS: Hashing Large Output Space for Cheap Inference.
Proceedings of the Fifth Conference on Machine Learning and Systems, 2022

Random Offset Block Embedding (ROBE) for compressed embedding tables in deep learning recommendation systems.
Proceedings of the Fifth Conference on Machine Learning and Systems, 2022

BLISS: A Billion scale Index using Iterative Re-partitioning.
Proceedings of the KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, August 14, 2022

Learning to Retrieve Relevant Experiences for Motion Planning.
Proceedings of the 2022 International Conference on Robotics and Automation, 2022

DRAGONN: Distributed Randomized Approximate Gradients of Neural Networks.
Proceedings of the International Conference on Machine Learning, 2022

One-Pass Diversified Sampling with Application to Terabyte-Scale Genomic Sequence Streams.
Proceedings of the International Conference on Machine Learning, 2022

Structural Contrastive Representation Learning for Zero-shot Multi-label Text Classification.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2022, 2022

2021
Satellite Images and Deep Learning to Identify Discrepancy in Mailing Addresses with Applications to Census 2020 in Houston.
CoRR, 2021

Federated Multiple Label Hashing (FedMLH): Communication Efficient Federated Learning on Extreme Classification Tasks.
CoRR, 2021

Random Offset Block Embedding Array (ROBE) for CriteoTB Benchmark MLPerf DLRM Model : 1000× Compression and 2.7× Faster Inference.
CoRR, 2021

Efficient Inference via Universal LSH Kernel.
CoRR, 2021

PairConnect: A Compute-Efficient MLP Alternative to Attention.
CoRR, 2021

Sublinear Least-Squares Value Iteration via Locality Sensitive Hashing.
CoRR, 2021

Accelerating SLIDE Deep Learning on Modern CPUs: Vectorization, Quantizations, Memory Optimizations, and More.
CoRR, 2021

IRLI: Iterative Re-partitioning for Learning to Index.
CoRR, 2021

Semantically Constrained Memory Allocation (SCMA) for Embedding in Efficient Recommendation Systems.
CoRR, 2021

Beyond Convolutions: A Novel Deep Learning Approach for Raw Seismic Data Ingestion.
CoRR, 2021

Density Sketches for Sampling and Estimation.
CoRR, 2021

Solving hybrid Boolean constraints in continuous space via multilinear Fourier expansions.
Artif. Intell., 2021

SDM-Net: A simple and effective model for generalized zero-shot learning.
Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, 2021

Fast Processing and Querying of 170TB of Genomics Data via a Repeated And Merged BloOm Filter (RAMBO).
Proceedings of the SIGMOD '21: International Conference on Management of Data, 2021

Active Sampling Count Sketch (ASCS) for Online Sparse Estimation of a Trillion Scale Covariance Matrix.
Proceedings of the SIGMOD '21: International Conference on Management of Data, 2021

Efficient and Less Centralized Federated Learning.
Proceedings of the Machine Learning and Knowledge Discovery in Databases. Research Track, 2021

Breaking the Linear Iteration Cost Barrier for Some Well-known Conditional Gradient Methods Using MaxIP Data-structures.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Locality Sensitive Teaching.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Practical Near Neighbor Search via Group Testing.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Raw Nav-merge Seismic Data to Subsurface Properties with MLP based Multi-Modal Information Unscrambler.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Accelerating SLIDE Deep Learning on Modern CPUs: Vectorization, Quantizations, Memory Optimizations, and More.
Proceedings of the Fourth Conference on Machine Learning and Systems, 2021

Learning Sampling Distributions Using Local 3D Workspace Decompositions for Motion Planning in High Dimensions.
Proceedings of the IEEE International Conference on Robotics and Automation, 2021

A Tale of Two Efficient and Informative Negative Sampling Distributions.
Proceedings of the 38th International Conference on Machine Learning, 2021

SOLAR: Sparse Orthogonal Learned and Random Embeddings.
Proceedings of the 9th International Conference on Learning Representations, 2021

MONGOOSE: A Learnable LSH Framework for Efficient Neural Network Training.
Proceedings of the 9th International Conference on Learning Representations, 2021

Learned Bloom Filters in Adversarial Environments: A Malicious URL Detection Use-Case.
Proceedings of the 22nd IEEE International Conference on High Performance Switching and Routing, 2021

Neighbor Oblivious Learning (NObLe) for Device Localization and Tracking.
Proceedings of the Design, Automation & Test in Europe Conference & Exhibition, 2021

A One-Pass Distributed and Private Sketch for Kernel Sums with Applications to Machine Learning at Scale.
Proceedings of the CCS '21: 2021 ACM SIGSAC Conference on Computer and Communications Security, Virtual Event, Republic of Korea, November 15, 2021

Revisiting Consistent Hashing with Bounded Loads.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020
A Constant-time Adaptive Negative Sampling.
CoRR, 2020

Distributed Tera-Scale Similarity Search with MPI: Provably Efficient Similarity Search over billions without a Single Distance Computation.
CoRR, 2020

Bloom Origami Assays: Practical Group Testing.
CoRR, 2020

Climbing the WOL: Training for Cheaper Inference.
CoRR, 2020

STORM: Foundations of End-to-End Empirical Risk Minimization on the Edge.
CoRR, 2020

A One-Pass Private Sketch for Most Machine Learning Tasks.
CoRR, 2020

Sub-linear RACE Sketches for Approximate Kernel Density Estimation on Streaming Data.
Proceedings of the WWW '20: The Web Conference 2020, Taipei, Taiwan, April 20-24, 2020, 2020

Adaptive Learned Bloom Filter (Ada-BF): Efficient Utilization of the Classifier with Application to Real-Time Information Filtering on the Web.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning Systems.
Proceedings of the Third Conference on Machine Learning and Systems, 2020

Mutual Information Estimation using LSH Sampling.
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 2020

Sub-linear Memory Sketches for Near Neighbor Search on Streaming Data.
Proceedings of the 37th International Conference on Machine Learning, 2020

Angular Visual Hardness.
Proceedings of the 37th International Conference on Machine Learning, 2020

FourierSAT: A Fourier Expansion-Based Algebraic Framework for Solving Hybrid Boolean Constraints.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019
Learning Feasibility for Task and Motion Planning in Tabletop Environments.
IEEE Robotics Autom. Lett., 2019

Privacy Adversarial Network: Representation Learning for Mobile Data Privacy.
Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., 2019

Sub-Linear Privacy-Preserving Near-Neighbor Search.
IACR Cryptol. ePrint Arch., 2019

Lsh-sampling Breaks the Computation Chicken-and-egg Loop in Adaptive Stochastic Gradient Estimation.
CoRR, 2019

Adaptive Learned Bloom Filter (Ada-BF): Efficient Utilization of the Classifier.
CoRR, 2019

RAMBO: Repeated And Merged Bloom Filter for Multiple Set Membership Testing (MSMT) in Sub-linear time.
CoRR, 2019

Semantic Similarity Based Softmax Classifier for Zero-Shot Learning.
CoRR, 2019

SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning Systems.
CoRR, 2019

RACE: Sub-Linear Memory Sketches for Approximate Near-Neighbor Search on Streaming Data.
CoRR, 2019

Better accuracy with quantified privacy: representations learned via reconstructive adversarial network.
CoRR, 2019

Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Products.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Cross-Modal Mapping for Generalized Zero-Shot Learning by Soft-Labeling.
Proceedings of the Visually Grounded Interaction and Language (ViGIL), 2019

Fast and Accurate Stochastic Gradient Estimation.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Using Local Experiences for Global Motion Planning.
Proceedings of the International Conference on Robotics and Automation, 2019

Compressing Gradient Optimizers via Count-Sketches.
Proceedings of the 36th International Conference on Machine Learning, 2019

Scaling-Up Split-Merge MCMC with Locality Sensitive Sampling (LSS).
Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, 2019

2018
Extreme Classification in Log Memory.
CoRR, 2018

Want to bring a community together? Create more sub-communities.
CoRR, 2018

Training 100, 000 Classes on a Single Titan X in 7 Hours or 15 Minutes with 25 Titan Xs.
Proceedings of the Companion of the The Web Conference 2018 on The Web Conference 2018, 2018

Arrays of (locality-sensitive) Count Estimators (ACE): Anomaly Detection on the Edge.
Proceedings of the 2018 World Wide Web Conference on World Wide Web, 2018

Densified Winner Take All (WTA) Hashing for Sparse Datasets.
Proceedings of the Thirty-Fourth Conference on Uncertainty in Artificial Intelligence, 2018

Randomized Algorithms Accelerated over CPU-GPU for Ultra-High Dimensional Similarity Search.
Proceedings of the 2018 International Conference on Management of Data, 2018

Probabilistic Blocking with an Application to the Syrian Conflict.
Proceedings of the Privacy in Statistical Databases, 2018

Topkapi: Parallel and Fast Sketches for Finding Top-K Frequent Elements.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

TINET: Learning Invariant Networks via Knowledge Transfer.
Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018

MISSION: Ultra Large-Scale Feature Selection using Count-Sketches.
Proceedings of the 35th International Conference on Machine Learning, 2018

Scalable Estimation via LSH Samplers (LSS).
Proceedings of the 6th International Conference on Learning Representations, 2018

Lsh-Sampling breaks the Computational chicken-and-egg Loop in adaptive stochastic Gradient estimation.
Proceedings of the 6th International Conference on Learning Representations, 2018

Jaccard Affiliation Graph (JAG) Model For Explaining Overlapping Community Behaviors.
Proceedings of the IEEE/ACM 2018 International Conference on Advances in Social Networks Analysis and Mining, 2018

2017
Unique Entity Estimation with Application to the Syrian Conflict.
CoRR, 2017

FLASH: Randomized Algorithms Accelerated over CPU-GPU for Ultra-High Dimensional Similarity Search.
CoRR, 2017

Accelerating Dependency Graph Learning from Heterogeneous Categorical Event Streams via Knowledge Transfer.
CoRR, 2017

A New Unbiased and Efficient Class of LSH-Based Samplers and Estimators for Partition Function Computation in Log-Linear Models.
CoRR, 2017

Arrays of (locality-sensitive) Count Estimators (ACE): High-Speed Anomaly Detection via Cache Lookups.
CoRR, 2017

Scalable and Sustainable Deep Learning via Randomized Hashing.
Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Halifax, NS, Canada, August 13, 2017

RHash: Robust Hashing via L_infinity-norm Distortion.
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017

Optimal Densification for Fast and Accurate Minwise Hashing.
Proceedings of the 34th International Conference on Machine Learning, 2017

Location detection for navigation using IMUs with a map through coarse-grained machine learning.
Proceedings of the Design, Automation & Test in Europe Conference & Exhibition, 2017

2016
Exact Weighted Minwise Hashing in Constant Time.
CoRR, 2016

Sub-linear Privacy-preserving Search with Untrusted Server and Semi-honest Parties.
CoRR, 2016

Revisiting Winner Take All (WTA) Hashing for Sparse Datasets.
CoRR, 2016

Near-Isometric Binary Hashing for Large-scale Datasets.
CoRR, 2016

2-Bit Random Projections, NonLinear Estimators, and Approximate Near Neighbor Search.
CoRR, 2016

CaPSuLe: A camera-based positioning system using learning.
Proceedings of the 29th IEEE International System-on-Chip Conference, 2016

Time Adaptive Sketches (Ada-Sketches) for Summarizing Data Streams.
Proceedings of the 2016 International Conference on Management of Data, 2016

Simple and Efficient Weighted Minwise Hashing.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

SSH (Sketch, Shingle, & Hash) for Indexing Massive-Scale Time Series.
Proceedings of the NIPS 2016 Time Series Workshop, 2016

2015
Probabilistic Hashing Techniques for Big Data.
PhD thesis, 2015

Blocking Methods Applied to Casualty Records from the Syrian Conflict.
CoRR, 2015

Asymmetric Minwise Hashing for Indexing Binary Inner Products and Set Containment.
Proceedings of the 24th International Conference on World Wide Web, 2015

Improved Asymmetric Locality Sensitive Hashing (ALSH) for Maximum Inner Product Search (MIPS).
Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence, 2015

2014
Asymmetric Minwise Hashing.
CoRR, 2014

An Improved Scheme for Asymmetric LSH.
CoRR, 2014

Graph Kernels via Functional Embedding.
CoRR, 2014

Coding for Random Projections and Approximate Near Neighbor Search.
CoRR, 2014

Improved Densification of One Permutation Hashing.
Proceedings of the Thirtieth Conference on Uncertainty in Artificial Intelligence, 2014

Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS).
Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Densifying One Permutation Hashing via Rotation for Fast Near Neighbor Search.
Proceedings of the 31th International Conference on Machine Learning, 2014

Coding for Random Projections.
Proceedings of the 31th International Conference on Machine Learning, 2014

A new space for comparing graphs.
Proceedings of the 2014 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, 2014

In Defense of Minhash over Simhash.
Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, 2014

2013
Beyond Pairwise: Provably Fast Algorithms for Approximate <i>k</i>-Way Similarity Search.
Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

b-bit minwise hashing in practice.
Proceedings of the 5th Asia-Pacific Symposium on Internetware, 2013

2012
b-Bit Minwise Hashing in Practice: Large-Scale Batch and Online Learning and Using GPUs for Fast Preprocessing with Simple Hash Functions.
CoRR, 2012

Query spelling correction using multi-task learning.
Proceedings of the 21st World Wide Web Conference, 2012

GPU-based minwise hashing: GPU-based minwise hashing.
Proceedings of the 21st World Wide Web Conference, 2012

Fast Near Neighbor Search in High-Dimensional Binary Data.
Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2012

Fast multi-task learning for query spelling correction.
Proceedings of the 21st ACM International Conference on Information and Knowledge Management, 2012

2011
Training Logistic Regression and SVM on 200GB Data Using b-Bit Minwise Hashing and Comparisons with Vowpal Wabbit (VW)
CoRR, 2011

Hashing Algorithms for Large-Scale Learning.
Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011


  Loading...