48 citations · 77 across the 10 of their papers we have counts for
11 papers
BOLT: An Automated Deep Learning Framework for Training and Deploying Large-Scale Search and Recommendation Models on Commodity CPU Hardware
Nicholas Meisburger, Vihan Lakshman, Benito Geordie +9
Efficient large-scale neural network training and inference on commodity CPU hardware is of immense practical significance in democratizing deep learning (DL) capabilities. Present…
Distributed SLIDE: Enabling Training Large Neural Networks on Low Bandwidth and Simple CPU-Clusters via Model Parallelism and Sparsity
Minghao Yan, Nicholas Meisburger, Tharun Medini +1
More than 70% of cloud computing is paid for but sits idle. A large fraction of these idle compute are cheap CPUs with few cores that are not utilized during the less busy hours. T…
IRLI: Iterative Re-partitioning for Learning to Index
Gaurav Gupta, Tharun Medini, Anshumali Shrivastava +1
Neural models have transformed the fundamental information retrieval problem of mapping a query to a giant set of items. However, the need for efficient and low latency inference f…
A Tale of Two Efficient and Informative Negative Sampling Distributions
Shabnam Daghaghi, Tharun Medini, Nicholas Meisburger +3
Softmax classifiers with a very large number of classes naturally occur in many applications such as natural language processing and information retrieval. The calculation of full…
SOLAR: Sparse Orthogonal Learned and Random Embeddings
Tharun Medini, Beidi Chen, Anshumali Shrivastava
Dense embedding models are commonly deployed in commercial search engines, wherein all the document vectors are pre-computed, and near-neighbor search (NNS) is performed with the q…
Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Products
Tharun Medini, Qixuan Huang, Yiqiu Wang +2
In the last decade, it has been shown that many hard AI tasks, especially in NLP, can be naturally modeled as extreme classification problems leading to improved precision. However…
Fast Processing and Querying of 170TB of Genomics Data via a Repeated And Merged BloOm Filter (RAMBO)
Gaurav Gupta, Minghao Yan, Benjamin Coleman +5
DNA sequencing, especially of microbial genomes and metagenomes, has been at the core of recent research advances in large-scale comparative genomics. The data deluge has resulted…
RAMBO: Repeated And Merged BloOm Filter for Ultra-fast Multiple Set Membership Testing (MSMT) on Large-Scale Data
Gaurav Gupta, Minghao Yan, Benjamin Coleman +4
Multiple Set Membership Testing (MSMT) is a well-known problem in a variety of search and query applications. Given a dataset of K different sets and a query q, it aims to find all…
SDM-Net: A Simple and Effective Model for Generalized Zero-Shot Learning
Shabnam Daghaghi, Tharun Medini, Anshumali Shrivastava
Zero-Shot Learning (ZSL) is a classification task where we do not have even a single training labeled example from a set of unseen classes. Instead, we only have prior information…
SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning Systems
Beidi Chen, Tharun Medini, James Farwell +3
Deep Learning (DL) algorithms are the central focus of modern machine learning systems. As data volumes keep growing, it has become customary to train large neural networks with hu…
Extreme Classification in Log Memory
Qixuan Huang, Yiqiu Wang, Tharun Medini +1
We present Merged-Averaged Classifiers via Hashing (MACH) for K-classification with ultra-large values of K. Compared to traditional one-vs-all classifiers that require O(Kd) memor…