AS
Anshumali Shrivastava
cs.LGcs.DScs.IRstat.MLcs.AIcs.DBcs.DCstat.COstat.MEcs.CL
On Valency
published · living versionsW_vgvgybdz·v1 · currentpublished
Stratified Sparse Attention: Reducing the Sparse-to-Dense Gap at Extreme Sparsity
with Sahil Joshi, Prithvi Dixit, Aryan Katiyar, Agniva Chowdhury +3
1 version
Preprints & journals
101 papers in the corpus · 2011–2026Stratified Sparse Attention: Reducing the Sparse-to-Dense Gap at Extreme Sparsity2610.28441v1 · Sahil Joshi, Prithvi Dixit, Aryan Katiyar et al.2026 · 0 citationsarXivon Valency
RACE Attention: A Strictly Linear-Time Attention Layer for Training on Outrageously Large Contexts2510.04008v5 · Sahil Joshi, Agniva Chowdhury, Amar Kanakamedala et al.2025 · 0 citationsarXiv
To Compress or Not? Pushing the Frontier of Lossless GenAI Model Weights Compression with Exponent Concentration2510.02676v1 · Zeyu Yang, Tianyi Zhang, Jianwen Xie et al.2025 · 0 citationsarXiv
REFRAG: Rethinking RAG based Decoding2509.01092v2 · Xiaoqiang Lin, Aritra Ghosh, Bryan Kian Hsiang Low et al.2025 · 0 citationsarXiv
CoVE: Compressed Vocabulary Expansion Makes Better LLM-based Recommender Systems2506.19993v1 · Haochen Zhang, Tianyi Zhang, Junze Yin et al.2025 · 0 citationsarXiv
70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)2504.11651v3 · Tianyi Zhang, Mohsen Hariri, Shaochen Zhong et al.2025 · 1 citationarXiv
Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation2410.06364v3 · Tianyi Zhang, Junda Su, Aditya Desai et al.2024 · 0 citationsarXiv
LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid2407.10032v3 · Tianyi Zhang, Anshumali Shrivastava2024 · 0 citationsarXiv
IDentity with Locality: An ideal hash for gene sequence search2406.14901v1 · Aditya Desai, Gaurav Gupta, Tianyi Zhang et al.2024 · 0 citationsarXiv
KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization2405.03917v1 · Tianyi Zhang, Jonah Yi, Zhaozhuo Xu et al.2024 · 8 citationsarXiv
NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention2403.01273v1 · Tianyi Zhang, Jonah Wonkyu Yi, Bowen Yao et al.2024 · 5 citationsarXiv
Learning Scalable Structural Representations for Link Prediction with Bloom Signatures2312.16784v1 · Tianyi Zhang, Haoteng Yin, Rongzhe Wei et al.2023 · 7 citationsarXiv
Contractive error feedback for gradient compression2312.08538v1 · Bingcong Li, Shuai Zheng, Parameswaran Raman et al.2023 · 0 citationsarXiv
Adaptive Sampling for Deep Learning via Efficient Nonparametric Proxies2311.13583v1 · Shabnam Daghaghi, Benjamin Coleman, Benito Geordie et al.2023 · 0 citationsarXiv
Heterogeneous federated collaborative filtering using FAIR: Federated Averaging in Random Subspaces2311.01722v1 · Aditya Desai, Benjamin Meisburger, Zichang Liu et al.2023 · 0 citationsarXiv
Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time2310.17157v1 · Zichang Liu, Jue Wang, Tri Dao et al.2023 · 51 citationsProceedings of the 40th International Conference on Machine Learning, 2023, 919
In defense of parameter sharing for model-compression2310.11611v1 · Aditya Desai, Anshumali Shrivastava2023 · 0 citationsarXiv
CAPS: A Practical Partition Index for Filtered Similarity Search2308.15014v1 · Gaurav Gupta, Jonah Yi, Benjamin Coleman et al.2023 · 1 citationarXiv
Algorithmic Foundations of Inexact Computing2305.18705v1 · John Augustine, Dror Fried, Krishna V. Palem et al.2023 · 0 citationsarXiv
CARAMEL: A Succinct Read-Only Lookup Table via Compressed Static Functions2305.16545v2 · Benjamin Coleman, David Torres Ramos, Vihan Lakshman et al.2023 · 0 citationsarXiv
BOLT: An Automated Deep Learning Framework for Training and Deploying Large-Scale Search and Recommendation Models on Commodity CPU Hardware2303.17727v4 · Nicholas Meisburger, Vihan Lakshman, Benito Geordie et al.2023 · 1 citationarXiv
A Theoretical Analysis Of Nearest Neighbor Search On Approximate Near Neighbor Graph2303.06210v1 · Anshumali Shrivastava, Zhao Song, Zhaozhuo Xu2023 · 1 citationarXiv
Learning Multimodal Data Augmentation in Feature Space2212.14453v2 · Zichang Liu, Zhiqiang Tang, Xingjian Shi et al.2022 · 12 citationsarXiv
Coordinated Science Laboratory 70th Anniversary Symposium: The Future of Computing2210.08974v1 · Klara Nahrstedt, Naresh Shanbhag, Vikram Adve et al.2022 · 0 citationsarXiv
Efficient model compression with Random Operation Access Specific Tile (ROAST) hashing2207.10702v1 · Aditya Desai, Keren Zhou, Anshumali Shrivastava2022 · 0 citationsarXiv
The trade-offs of model size in large recommendation models : A 10000 compressed criteo-tb DLRM model (100 GB parameters to mere 10MB)2207.10731v1 · Aditya Desai, Anshumali Shrivastava2022 · 0 citationsarXiv
Learning to Retrieve Relevant Experiences for Motion Planning2204.08550v1 · Constantinos Chamzas, Aedan Cullen, Anshumali Shrivastava et al.2022 · 16 citationsarXiv
Distributed SLIDE: Enabling Training Large Neural Networks on Low Bandwidth and Simple CPU-Clusters via Model Parallelism and Sparsity2201.12667v1 · Minghao Yan, Nicholas Meisburger, Tharun Medini et al.2022 · 3 citationsarXiv
Breaking the Linear Iteration Cost Barrier for Some Well-known Conditional Gradient Methods Using MaxIP Data-structures2111.15139v1 · Anshumali Shrivastava, Zhao Song, Zhaozhuo Xu2021 · 3 citationsarXiv
Satellite Images and Deep Learning to Identify Discrepancy in Mailing Addresses with Applications to Census 2020 in Houston2111.06562v1 · Zhaozhuo Xu, Alan Baonan Ji, Andrew Woods et al.2021 · 0 citationsarXiv
Federated Multiple Label Hashing (FedMLH): Communication Efficient Federated Learning on Extreme Classification Tasks2110.12292v1 · Zhenwei Dai, Chen Dun, Yuxin Tang et al.2021 · 4 citationsarXiv
Random Offset Block Embedding Array (ROBE) for CriteoTB Benchmark MLPerf DLRM Model : 1000 Compression and 3.1 Faster Inference2108.02191v2 · Aditya Desai, Li Chou, Anshumali Shrivastava2021 · 2 citationsarXiv
Practical Near Neighbor Search via Group Testing2106.11565v1 · Joshua Engels, Benjamin Coleman, Anshumali Shrivastava2021 · 4 citationsarXiv
Efficient Inference via Universal LSH Kernel2106.11426v1 · Zichang Liu, Benjamin Coleman, Anshumali Shrivastava2021 · 1 citationarXiv
PairConnect: A Compute-Efficient MLP Alternative to Attention2106.08235v1 · Zhaozhuo Xu, Minghao Yan, Junyan Zhang et al.2021 · 1 citationarXiv
Efficient and Less Centralized Federated Learning2106.06627v1 · Li Chou, Zichang Liu, Zhuang Wang et al.2021 · 24 citationsarXiv
Sublinear Least-Squares Value Iteration via Locality Sensitive Hashing2105.08285v2 · Anshumali Shrivastava, Zhao Song, Zhaozhuo Xu2021 · 4 citationsarXiv
IRLI: Iterative Re-partitioning for Learning to Index2103.09944v1 · Gaurav Gupta, Tharun Medini, Anshumali Shrivastava et al.2021 · 0 citationsarXiv
Beyond Convolutions: A Novel Deep Learning Approach for Raw Seismic Data Ingestion2102.13631v1 · Zhaozhuo Xu, Aditya Desai, Menal Gupta et al.2021 · 1 citationarXiv
Density Sketches for Sampling and Estimation2102.12301v1 · Aditya Desai, Benjamin Coleman, Anshumali Shrivastava2021 · 0 citationsarXiv
Semantically Constrained Memory Allocation (SCMA) for Embedding in Efficient Recommendation Systems2103.06124v1 · Aditya Desai, Yanzhou Pan, Kuangyuan Sun et al.2021 · 3 citationsarXiv
A Tale of Two Efficient and Informative Negative Sampling Distributions2012.15843v2 · Shabnam Daghaghi, Tharun Medini, Nicholas Meisburger et al.2020 · 3 citationsarXiv
Neighbor Oblivious Learning (NObLe) for Device Localization and Tracking2011.14954v1 · Zichang Liu, Li Chou, Anshumali Shrivastava2020 · 0 citationsarXiv
Learning Sampling Distributions Using Local 3D Workspace Decompositions for Motion Planning in High Dimensions2010.15335v3 · Constantinos Chamzas, Zachary Kingston, Carlos Quintero-Pena et al.2020 · 36 citationsarXiv
Active Sampling Count Sketch (ASCS) for Online Sparse Estimation of a Trillion Scale Covariance Matrix2010.15951v2 · Zhenwei Dai, Aditya Desai, Reinhard Heckel et al.2020 · 6 citationsarXiv
SOLAR: Sparse Orthogonal Learned and Random Embeddings2008.13225v1 · Tharun Medini, Beidi Chen, Anshumali Shrivastava2020 · 7 citationsarXiv
Distributed Tera-Scale Similarity Search with MPI: Provably Efficient Similarity Search over billions without a Single Distance Computation2008.03260v2 · Nicholas Meisburger, Anshumali Shrivastava2020 · 1 citationarXiv
Bloom Origami Assays: Practical Group Testing2008.02641v1 · Louis Abraham, Gary Becigneul, Benjamin Coleman et al.2020 · 3 citationsarXiv
Climbing the WOL: Training for Cheaper Inference2007.01230v2 · Zichang Liu, Zhaozhuo Xu, Alan Ji et al.2020 · 2 citationsarXiv
STORM: Foundations of End-to-End Empirical Risk Minimization on the Edge2006.14554v1 · Benjamin Coleman, Gaurav Gupta, John Chen et al.2020 · 1 citationarXiv
Career total: 165 works. 101 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.