
Escaping Saddle Points in Distributed Newton's Method with Communication efficiency and Byzantine Resilience
We study the problem of optimizing a nonconvex loss function (with sadd...
read it

SessionAware Query Autocompletion using Extreme Multilabel Ranking
Query autocompletion is a fundamental feature in search engines where t...
read it

Recovery of sparse linear classifiers from mixture of responses
In the problem of learning a mixture of linear classifiers, the aim is t...
read it

Recovery of Sparse Signals from a Mixture of Linear Samples
Mixture of linear regressions is a popular learning theoretic model that...
read it

Multilabel Classification by Hierarchical Partitioning and Datadependent Grouping
In modern multilabel classification problems, each data instance belongs...
read it

Distributed Newton Can Communicate Less and Resist Byzantine Workers
We develop a distributed second order optimization algorithm that is com...
read it

Reliable Distributed Clustering with Redundant Data Assignment
In this paper, we present distributed generalized clustering algorithms ...
read it

A workloadadaptive mechanism for linear queries under local differential privacy
We propose a new mechanism to accurately answer a userprovided set of l...
read it

Algebraic and Analytic Approaches for Parameter Learning in Mixture Models
We present two different approaches for parameter learning in several mi...
read it

CommunicationEfficient and ByzantineRobust Distributed Learning
We develop a communicationefficient distributed learning algorithm that...
read it

vqSGD: Vector Quantized Stochastic Gradient Descent
In this work, we present a family of vector quantization schemes vqSGD (...
read it

Sample Complexity of Learning Mixtures of Sparse Linear Regressions
In the problem of learning mixtures of linear regressions, the goal is t...
read it

Superset Technique for Approximate Recovery in OneBit Compressed Sensing
Onebit compressed sensing (1bCS) is a method of signal acquisition unde...
read it

SameCluster Querying for Overlapping Clusters
Overlapping clusters are common in models of many practical datasegment...
read it

Trace Reconstruction: Generalized and Parameterized
In the beautifully simpletostate problem of trace reconstruction, the ...
read it

Semisupervised Clustering by Queries and Locally Encodable Source Coding
Source coding is the canonical problem of data compression in informatio...
read it

Capacity of Locally Recoverable Codes
Motivated by applications in distributed storage, the notion of a locall...
read it

Linear Programming Approximations for Index Coding
Index coding, a source coding problem over broadcast channels, has been ...
read it

High Dimensional Discrete Integration by Hashing and Optimization
Recently Ermon et al. (2013) pioneered an ingenuous way to practically c...
read it

Robust Gradient Descent via Moment Encoding with LDPC Codes
This paper considers the problem of implementing largescale gradient de...
read it

Connectivity in Random Annulus Graphs and the Geometric Block Model
Random geometric graphs are the simplest, and perhaps the earliest possi...
read it

Representation Learning and Recovery in the ReLU Model
Rectified linear units, or ReLUs, have become the preferred activation f...
read it

Novel Impossibility Results for GroupTesting
In this work we prove nontrivial impossibility results for perhaps the ...
read it

The Geometric Block Model
To capture the inherent geometric features of many community detection p...
read it

Query Complexity of Clustering with Side Information
Suppose, we are given a set of n elements to be clustered into k (unknow...
read it

Clustering with Noisy Queries
In this paper, we initiate a rigorous theoretical study of clustering wi...
read it

A Theoretical Analysis of First Heuristics of Crowdsourced Entity Resolution
Entity resolution (ER) is the task of identifying all records in a datab...
read it

Efficient Rank Aggregation via Lehmer Codes
We propose a novel rank aggregation method based on converting permutati...
read it
Arya Mazumdar
is this you? claim profile