Alert button
Picture for Tharun Medini

Tharun Medini

Alert button

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

Mar 30, 2023
Nicholas Meisburger, Vihan Lakshman, Benito Geordie, Joshua Engels, David Torres Ramos, Pratik Pranav, Benjamin Coleman, Benjamin Meisburger, Shubh Gupta, Yashwanth Adunukota, Tharun Medini, Anshumali Shrivastava

Figure 1 for BOLT: An Automated Deep Learning Framework for Training and Deploying Large-Scale Neural Networks on Commodity CPU Hardware
Figure 2 for BOLT: An Automated Deep Learning Framework for Training and Deploying Large-Scale Neural Networks on Commodity CPU Hardware
Figure 3 for BOLT: An Automated Deep Learning Framework for Training and Deploying Large-Scale Neural Networks on Commodity CPU Hardware
Figure 4 for BOLT: An Automated Deep Learning Framework for Training and Deploying Large-Scale Neural Networks on Commodity CPU Hardware
Viaarxiv icon

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

Jan 29, 2022
Minghao Yan, Nicholas Meisburger, Tharun Medini, Anshumali Shrivastava

Viaarxiv icon

IRLI: Iterative Re-partitioning for Learning to Index

Mar 17, 2021
Gaurav Gupta, Tharun Medini, Anshumali Shrivastava, Alexander J Smola

Figure 1 for IRLI: Iterative Re-partitioning for Learning to Index
Figure 2 for IRLI: Iterative Re-partitioning for Learning to Index
Figure 3 for IRLI: Iterative Re-partitioning for Learning to Index
Figure 4 for IRLI: Iterative Re-partitioning for Learning to Index
Viaarxiv icon

A Constant-time Adaptive Negative Sampling

Dec 31, 2020
Shabnam Daghaghi, Tharun Medini, Beidi Chen, Mengnan Zhao, Anshumali Shrivastava

Figure 1 for A Constant-time Adaptive Negative Sampling
Figure 2 for A Constant-time Adaptive Negative Sampling
Figure 3 for A Constant-time Adaptive Negative Sampling
Figure 4 for A Constant-time Adaptive Negative Sampling
Viaarxiv icon

SOLAR: Sparse Orthogonal Learned and Random Embeddings

Aug 30, 2020
Tharun Medini, Beidi Chen, Anshumali Shrivastava

Figure 1 for SOLAR: Sparse Orthogonal Learned and Random Embeddings
Figure 2 for SOLAR: Sparse Orthogonal Learned and Random Embeddings
Figure 3 for SOLAR: Sparse Orthogonal Learned and Random Embeddings
Figure 4 for SOLAR: Sparse Orthogonal Learned and Random Embeddings
Viaarxiv icon

Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Products

Oct 28, 2019
Tharun Medini, Qixuan Huang, Yiqiu Wang, Vijai Mohan, Anshumali Shrivastava

Figure 1 for Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Products
Figure 2 for Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Products
Figure 3 for Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Products
Figure 4 for Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Products
Viaarxiv icon

Semantic Similarity Based Softmax Classifier for Zero-Shot Learning

Sep 10, 2019
Shabnam Daghaghi, Tharun Medini, Anshumali Shrivastava

Figure 1 for Semantic Similarity Based Softmax Classifier for Zero-Shot Learning
Figure 2 for Semantic Similarity Based Softmax Classifier for Zero-Shot Learning
Figure 3 for Semantic Similarity Based Softmax Classifier for Zero-Shot Learning
Figure 4 for Semantic Similarity Based Softmax Classifier for Zero-Shot Learning
Viaarxiv icon

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

Mar 07, 2019
Beidi Chen, Tharun Medini, Anshumali Shrivastava

Figure 1 for SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning Systems
Figure 2 for SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning Systems
Figure 3 for SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning Systems
Figure 4 for SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning Systems
Viaarxiv icon

Extreme Classification in Log Memory

Oct 09, 2018
Qixuan Huang, Yiqiu Wang, Tharun Medini, Anshumali Shrivastava

Figure 1 for Extreme Classification in Log Memory
Figure 2 for Extreme Classification in Log Memory
Figure 3 for Extreme Classification in Log Memory
Viaarxiv icon