Follow
Tharun Medini
Title
Cited by
Cited by
Year
Slide: In defense of smart algorithms over hardware acceleration for large-scale deep learning systems
B Chen, T Medini, J Farwell, C Tai, A Shrivastava
Proceedings of Machine Learning and Systems 2, 291-306, 2020
1152020
Extreme classification in log memory using count-min sketch: A case study of amazon search with 50m products
TKR Medini, Q Huang, Y Wang, V Mohan, A Shrivastava
Advances in Neural Information Processing Systems 32, 2019
762019
Fast processing and querying of 170tb of genomics data via a repeated and merged bloom filter (rambo)
G Gupta, M Yan, B Coleman, B Kille, RAL Elworth, T Medini, T Treangen, ...
Proceedings of the 2021 International Conference on Management of Data, 2226 …, 2021
142021
A tale of two efficient and informative negative sampling distributions
S Daghaghi, T Medini, N Meisburger, B Chen, M Zhao, A Shrivastava
International conference on machine learning, 2319-2329, 2021
112021
Bliss: A billion scale index using iterative re-partitioning
G Gupta, T Medini, A Shrivastava, AJ Smola
Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and …, 2022
92022
sameh gobriel, Charlie Tai, and Anshumali Shrivastava. Slide: In defense of smart algorithms over hardware acceleration for large-scale deep learning systems
B Chen, T Medini, J Farwell
Proceedings of Machine Learning and Systems 2, 291-306, 2020
92020
Solar: Sparse orthogonal learned and random embeddings
T Medini, B Chen, A Shrivastava
arXiv preprint arXiv:2008.13225, 2020
82020
Distributed SLIDE: Enabling training large neural networks on low bandwidth and simple CPU-clusters via model parallelism and sparsity
M Yan, N Meisburger, T Medini, A Shrivastava
arXiv preprint arXiv:2201.12667, 2022
62022
RAMBO: Repeated And Merged BloOm filter for ultra-fast Multiple Set Membership Testing (MSMT) on large-scale data
G Gupta, M Yan, B Coleman, RA Elworth, T Medini, T Treangen, ...
arXiv preprint arXiv:1910.02611, 2019
62019
Sdm-net: a simple and effective model for generalized zero-shot learning
S Daghaghi, T Medini, A Shrivastava
Uncertainty in Artificial Intelligence, 2103-2113, 2021
42021
BOLT: An Automated Deep Learning Framework for Training and Deploying Large-Scale Neural Networks on Commodity CPU Hardware
N Meisburger, V Lakshman, B Geordie, J Engels, DT Ramos, P Pranav, ...
arXiv preprint arXiv:2303.17727, 2023
32023
Structural contrastive representation learning for zero-shot multi-label text classification
T Zhang, Z Xu, T Medini, A Shrivastava
Findings of the Association for Computational Linguistics: EMNLP 2022, 4937-4947, 2022
32022
Semantic similarity based softmax classifier for zero-shot learning
S Daghaghi, T Medini, A Shrivastava
arXiv preprint arXiv:1909.04790, 2019
32019
Extreme classification in log memory
Q Huang, Y Wang, T Medini, A Shrivastava
arXiv preprint arXiv:1810.04254, 2018
32018
From Research to Production: Towards Scalable and Sustainable Neural Recommendation Models on Commodity CPU Hardware
A Shrivastava, V Lakshman, T Medini, N Meisburger, J Engels, ...
Proceedings of the 17th ACM Conference on Recommender Systems, 1071-1074, 2023
12023
IRLI: Iterative Re-partitioning for Learning to Index
G Gupta, T Medini, A Shrivastava, AJ Smola
arXiv preprint arXiv:2103.09944, 2021
12021
Simultaneous matching and ranking as end-to-end deep classification: A case study of information retrieval with 50M Documents
TKR Medini, Q Huang, Y Wang, V Mohan, A Shrivastava
12019
A4c: Anticipatory asynchronous advantage actor-critic
T Medini, X Luan, A Shrivastava
12018
BOLT: An Automated Deep Learning Framework for Training and Deploying Large-Scale Search and Recommendation Models on Commodity CPU Hardware
N Meisburger, V Lakshman, B Geordie, J Engels, DT Ramos, P Pranav, ...
Proceedings of the 32nd ACM International Conference on Information and …, 2023
2023
Randomized Algorithms for Training Deep Models with Large Outputs
T Medini
2022
The system can't perform the operation now. Try again later.
Articles 1–20