
A Constanttime Adaptive Negative Sampling
Softmax classifiers with a very large number of classes naturally occur ...
read it

Active Sampling Count Sketch (ASCS) for Online Sparse Estimation of a Trillion Scale Covariance Matrix
Estimating and storing the covariance (or correlation) matrix of highdi...
read it

Learning Sampling Distributions Using Local 3D Workspace Decompositions for Motion Planning in High Dimensions
Earlier work has shown that reusing experience from prior motion plannin...
read it

SOLAR: Sparse Orthogonal Learned and Random Embeddings
Dense embedding models are commonly deployed in commercial search engine...
read it

Distributed TeraScale Similarity Search with MPI: Provably Efficient Similarity Search over billions without a Single Distance Computation
We present SLASH (Sketched LocAlity Sensitive Hashing), an MPI (Message ...
read it

Bloom Origami Assays: Practical Group Testing
We study the problem usually referred to as group testing in the context...
read it

Climbing the WOL: Training for Cheaper Inference
Efficient inference for wide output layers (WOLs) is an essential yet ch...
read it

STORM: Foundations of EndtoEnd Empirical Risk Minimization on the Edge
Empirical risk minimization is perhaps the most influential idea in stat...
read it

A OnePass Private Sketch for Most Machine Learning Tasks
Differential privacy (DP) is a compelling privacy definition that explai...
read it

Privacy Adversarial Network: Representation Learning for Mobile Data Privacy
The remarkable success of machine learning has fostered a growing number...
read it

Sublinear RACE Sketches for Approximate Kernel Density Estimation on Streaming Data
Kernel density estimation is a simple and effective method that lies at ...
read it

Angular Visual Hardness
Although convolutional neural networks (CNNs) are inspired by the mechan...
read it

FourierSAT: A Fourier ExpansionBased Algebraic Framework for Solving Hybrid Boolean Constraints
The Boolean SATisfiability problem (SAT) is of central importance in com...
read it

Lshsampling Breaks the Computation Chickenandegg Loop in Adaptive Stochastic Gradient Estimation
Stochastic Gradient Descent or SGD is the most popular optimization algo...
read it

Extreme Classification in Log Memory using CountMin Sketch: A Case Study of Amazon Search with 50M Products
In the last decade, it has been shown that many hard AI tasks, especiall...
read it

Adaptive Learned Bloom Filter (AdaBF): Efficient Utilization of the Classifier
Recent work suggests improving the performance of Bloom filter by incorp...
read it

RAMBO: Repeated And Merged Bloom Filter for Multiple Set Membership Testing (MSMT) in Sublinear time
Approximate set membership is a common problem with wide applications in...
read it

Semantic Similarity Based Softmax Classifier for ZeroShot Learning
ZeroShot Learning (ZSL) is a classification task where we do not have e...
read it

Revisiting Consistent Hashing with Bounded Loads
Dynamic load balancing lies at the heart of distributed caching. Here, t...
read it

Using Local Experiences for Global Motion Planning
Samplingbased planners are effective in many realworld applications su...
read it

SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for LargeScale Deep Learning Systems
Deep Learning (DL) algorithms are the central focus of modern machine le...
read it

RACE: SubLinear Memory Sketches for Approximate NearNeighbor Search on Streaming Data
We demonstrate the first possibility of a sublinear memory sketch for s...
read it

Compressing Gradient Optimizers via CountSketches
Many popular firstorder optimization methods (e.g., Momentum, AdaGrad, ...
read it

Better accuracy with quantified privacy: representations learned via reconstructive adversarial network
The remarkable success of machine learning, especially deep learning, ha...
read it

Probabilistic Blocking with An Application to the Syrian Conflict
Entity resolution seeks to merge databases as to remove duplicate entrie...
read it

Extreme Classification in Log Memory
We present MergedAveraged Classifiers via Hashing (MACH) for Kclassifi...
read it

MISSION: Ultra LargeScale Feature Selection using CountSketches
Feature selection is an important challenge in machine learning. It play...
read it

Scalingup SplitMerge MCMC with Locality Sensitive Sampling (LSS)
SplitMerge MCMC (Monte Carlo Markov Chain) is one of the essential and ...
read it

Unique Entity Estimation with Application to the Syrian Conflict
Entity resolution identifies and removes duplicate entities in large, no...
read it

FLASH: Randomized Algorithms Accelerated over CPUGPU for UltraHigh Dimensional Similarity Search
We present FLASH ( Fast LSH Algorithm for Similarity search accelerat...
read it

Accelerating Dependency Graph Learning from Heterogeneous Categorical Event Streams via Knowledge Transfer
Dependency graph, as a heterogeneous graph representing the intrinsic re...
read it

Arrays of (localitysensitive) Count Estimators (ACE): HighSpeed Anomaly Detection via Cache Lookups
Anomaly detection is one of the frequent and important subroutines deplo...
read it

A New Unbiased and Efficient Class of LSHBased Samplers and Estimators for Partition Function Computation in LogLinear Models
Loglinear models are arguably the most successful class of graphical mo...
read it

Revisiting Winner Take All (WTA) Hashing for Sparse Datasets
WTA (Winner Take All) hashing has been successfully applied in many larg...
read it

Scalable and Sustainable Deep Learning via Randomized Hashing
Current deep learning architectures are growing larger in order to learn...
read it

2Bit Random Projections, NonLinear Estimators, and Approximate Near Neighbor Search
The method of random projections has become a standard tool for machine ...
read it

Asymmetric Minwise Hashing
Minwise hashing (Minhash) is a widely popular indexing scheme in practic...
read it

Improved Asymmetric Locality Sensitive Hashing (ALSH) for Maximum Inner Product Search (MIPS)
Recently it was shown that the problem of Maximum Inner Product Search (...
read it

In Defense of MinHash Over SimHash
MinHash and SimHash are the two widely adopted Locality Sensitive Hashin...
read it

Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS)
We present the first provably sublinear time algorithm for approximate M...
read it

Graph Kernels via Functional Embedding
We propose a representation of graph as a functional object derived from...
read it

A New Space for Comparing Graphs
Finding a new mathematical representations for graph, which allows direc...
read it

Training Logistic Regression and SVM on 200GB Data Using bBit Minwise Hashing and Comparisons with Vowpal Wabbit (VW)
We generated a dataset of 200 GB with 10^9 features, to test our recent ...
read it

Hashing Algorithms for LargeScale Learning
In this paper, we first demonstrate that bbit minwise hashing, whose es...
read it
Anshumali Shrivastava
is this you? claim profile
Assistant Professor of Department of Computer Science at Rice University since 2015, Professor at Rice University since 2015, Ph.D. in Computer Science at Cornell University from20102015, Analytic Software Scientist at Fair Isaac from 20082010