
Hessian based analysis of SGD for Deep Nets: Dynamics and Generalization
While stochastic gradient descent (SGD) and variants have been surprisin...
read it

Twoblock vs. Multiblock ADMM: An empirical evaluation of convergence
Alternating Direction Method of Multipliers (ADMM) has become a widely u...
read it

Sparse Linear Isotonic Models
In machine learning and data mining, linear models have been widely used...
read it

HighDimensional Dependency Structure Learning for Physical Processes
In this paper, we consider the use of structure learning methods for pro...
read it

R2N2: Residual Recurrent Neural Networks for Multivariate Time Series Forecasting
Multivariate timeseries modeling and forecasting is an important proble...
read it

High Dimensional Structured Superposition Models
High dimensional superposition models characterize observations using pa...
read it

Spatial Projection of Multiple Climate Variables using Hierarchical Multitask Learning
Future projection of climate is typically obtained by combining outputs ...
read it

Recommendation under Capacity Constraints
In this paper, we investigate the common scenario where every candidate ...
read it

Theoryguided Data Science: A New Paradigm for Scientific Discovery from Data
Data science models, although successful in a number of commercial domai...
read it

Alternating Estimation for Structured HighDimensional MultiResponse Models
We consider learning highdimensional multiresponse linear models with ...
read it

Structured Stochastic Linear Bandits
The stochastic linear bandit problem proceeds in rounds where at each ro...
read it

Structured Matrix Recovery via the Generalized Dantzig Selector
In recent years, structured matrix recovery problems have gained conside...
read it

The Matrix Generalized Inverse Gaussian Distribution: Properties and Applications
While the Matrix Generalized Inverse Gaussian (MGIG) distribution arises...
read it

Unified View of Matrix Completion under General Structural Constraints
In this paper, we present a unified analysis of matrix completion under ...
read it

Estimating Structured Vector Autoregressive Model
While considerable advances have been made in estimating highdimensiona...
read it

SemiMarkov Switching Vector Autoregressive Modelbased Anomaly Detection in Aviation Systems
In this work we consider the problem of anomaly detection in heterogeneo...
read it

Estimation with Norm Regularization
Analysis of nonasymptotic estimation error and structured statistical r...
read it

A Spectral Algorithm for Inference in Hidden SemiMarkov Models
Hidden semiMarkov models (HSMMs) are latent variable models which allow...
read it

BetheADMM for Tree Decomposition based Parallel MAP Inference
We consider the problem of maximum a posteriori (MAP) inference in discr...
read it

Bregman Alternating Direction Method of Multipliers
The mirror descent algorithm (MDA) generalizes gradient descent by using...
read it

Online Alternating Direction Method
Online optimization has emerged as powerful tool in large scale optimiza...
read it

Gaussian Process Topic Models
We introduce Gaussian Process Topic Models (GPTMs), a new family of topi...
read it

Topic Modeling on Health Journals with Regularized Variational Inference
Topic modeling enables exploration and compact representation of a corpu...
read it

High Dimensional Data Enrichment: Interpretable, Fast, and DataEfficient
High dimensional structured data enriched model describes groups of obse...
read it

Time Series Deinterleaving of DNS Traffic
Stream deinterleaving is an important problem with various applications ...
read it

Adversarial Recommendation: Attack of the Learned Fake Users
Can machine learning models for recommendation be easily fooled? While t...
read it

DAPPER: Scaling Dynamic Author Persona Topic Model to Billion Word Corpora
Extracting common narratives from multiauthor dynamic text corpora requ...
read it

Random Quadratic Forms with Dependence: Applications to Restricted Isometry and Beyond
Several important families of computational and statistical results in m...
read it

Derandomized PACBayes Margin Bounds: Applications to Nonconvex and Nonsmooth Predictors
In spite of several notable efforts, explaining the generalization of de...
read it

Gradient Boosted Flows
Normalizing flows (NF) are a powerful framework for approximating poster...
read it

Structured Linear Contextual Bandits: A Sharp and Geometric Smoothed Analysis
Bandit learning algorithms typically involve the balance of exploration ...
read it
Arindam Banerjee
is this you? claim profile
Associate Professor, Computer Science & Engineering, University of Minnesota, Twin Cities