Jayant Kalagnanam - Academia.edu (original) (raw)

Uploads

Papers by Jayant Kalagnanam

INFORMS Journal on Applied Analytics

In this paper, we propose a site-wide lead advisor, which is an artificial intelligence–based pre... more In this paper, we propose a site-wide lead advisor, which is an artificial intelligence–based prediction and set-point recommendation engine, by combining the use of machine learning with optimization techniques. It provides operational set-point recommendations to continuously improve site-wide operations for throughput measured in additional barrels of oil produced per day. A key contribution and differentiator is the utilization of sensor data to continuously learn the behavior of all the subsystems of an oil-producing plant and use this within an optimization framework to provide advisory control in near real time. This is novel in that it does not require a model of the plant to be provided as input. The predictive model is learned automatically and continuously from data. This work required the development of a new prediction-optimization modeling framework that optimizes throughput while staying in the vicinity of the historical process behavior and employing the model’s stru...

2017 IEEE International Conference on Data Mining (ICDM)

ArXiv, 2021

Clustering is a popular unsupervised learning tool often used to discover groups within a larger ... more Clustering is a popular unsupervised learning tool often used to discover groups within a larger population such as customer segments, or patient subtypes. However, despite its use as a tool for subgroup discovery and description few stateof-the-art algorithms provide any rationale or description behind the clusters found. We propose a novel approach for interpretable clustering that both clusters data points and constructs polytopes around the discovered clusters to explain them. Our framework allows for additional constraints on the polytopes including ensuring that the hyperplanes constructing the polytope are axis-parallel or sparse with integer coefficients. We formulate the problem of constructing clusters via polytopes as a Mixed-Integer Non-Linear Program (MINLP). To solve our formulation we propose a two phase approach where we first initialize clusters and polytopes using alternating minimization, and then use coordinate descent to boost clustering performance. We benchmar...

2017 IEEE International Conference on Data Mining Workshops (ICDMW), 2017

We propose a novel diminishing learning rate scheme, coined Decreasing-Trend-Nature (DTN), which ... more We propose a novel diminishing learning rate scheme, coined Decreasing-Trend-Nature (DTN), which allows us to prove fast convergence of the Stochastic Gradient Descent (SGD) algorithm to a first-order stationary point for smooth general convex and some class of nonconvex including neural network applications for classification problems. We are the first to prove that SGD with diminishing learning rate achieves a convergence rate of O(1/t) for these problems. Our theory applies to neural network applications for classification problems in a straightforward way.

Lecture Notes in Computer Science, 2019

AI, machine learning, and deep learning tools have now become easily accessible on the cloud. How... more AI, machine learning, and deep learning tools have now become easily accessible on the cloud. However, the adoption of these cloud-based services for heavy industries has been limited due to the gap between general purpose AI tools and operational requirements for production industries. There are three fundamentals gaps. The first is the lack of purpose built solution pipelines designed for common industrial problem types, the second is the lack of tools for automating the learning from noisy sensor data and the third is the lack of platforms which help practitioners leverage cloud-based environment for building and deploying custom modeling pipelines. In this paper, we present ThunderML, a toolkit that addresses these gaps by providing powerful programming model that allows rapid authoring, training and deployment for Industry 4.0 applications. Importantly, the system also facilitates cloud-based deployments by providing a vendor agnostic pipeline execution and deployment layer.

Computer Methods in Applied Mechanics and Engineering, 2019

INFORMS Journal on Applied Analytics

In this paper, we propose a site-wide lead advisor, which is an artificial intelligence–based pre... more In this paper, we propose a site-wide lead advisor, which is an artificial intelligence–based prediction and set-point recommendation engine, by combining the use of machine learning with optimization techniques. It provides operational set-point recommendations to continuously improve site-wide operations for throughput measured in additional barrels of oil produced per day. A key contribution and differentiator is the utilization of sensor data to continuously learn the behavior of all the subsystems of an oil-producing plant and use this within an optimization framework to provide advisory control in near real time. This is novel in that it does not require a model of the plant to be provided as input. The predictive model is learned automatically and continuously from data. This work required the development of a new prediction-optimization modeling framework that optimizes throughput while staying in the vicinity of the historical process behavior and employing the model’s stru...

2017 IEEE International Conference on Data Mining (ICDM)

ArXiv, 2021

Clustering is a popular unsupervised learning tool often used to discover groups within a larger ... more Clustering is a popular unsupervised learning tool often used to discover groups within a larger population such as customer segments, or patient subtypes. However, despite its use as a tool for subgroup discovery and description few stateof-the-art algorithms provide any rationale or description behind the clusters found. We propose a novel approach for interpretable clustering that both clusters data points and constructs polytopes around the discovered clusters to explain them. Our framework allows for additional constraints on the polytopes including ensuring that the hyperplanes constructing the polytope are axis-parallel or sparse with integer coefficients. We formulate the problem of constructing clusters via polytopes as a Mixed-Integer Non-Linear Program (MINLP). To solve our formulation we propose a two phase approach where we first initialize clusters and polytopes using alternating minimization, and then use coordinate descent to boost clustering performance. We benchmar...

2017 IEEE International Conference on Data Mining Workshops (ICDMW), 2017

We propose a novel diminishing learning rate scheme, coined Decreasing-Trend-Nature (DTN), which ... more We propose a novel diminishing learning rate scheme, coined Decreasing-Trend-Nature (DTN), which allows us to prove fast convergence of the Stochastic Gradient Descent (SGD) algorithm to a first-order stationary point for smooth general convex and some class of nonconvex including neural network applications for classification problems. We are the first to prove that SGD with diminishing learning rate achieves a convergence rate of O(1/t) for these problems. Our theory applies to neural network applications for classification problems in a straightforward way.

Lecture Notes in Computer Science, 2019

AI, machine learning, and deep learning tools have now become easily accessible on the cloud. How... more AI, machine learning, and deep learning tools have now become easily accessible on the cloud. However, the adoption of these cloud-based services for heavy industries has been limited due to the gap between general purpose AI tools and operational requirements for production industries. There are three fundamentals gaps. The first is the lack of purpose built solution pipelines designed for common industrial problem types, the second is the lack of tools for automating the learning from noisy sensor data and the third is the lack of platforms which help practitioners leverage cloud-based environment for building and deploying custom modeling pipelines. In this paper, we present ThunderML, a toolkit that addresses these gaps by providing powerful programming model that allows rapid authoring, training and deployment for Industry 4.0 applications. Importantly, the system also facilitates cloud-based deployments by providing a vendor agnostic pipeline execution and deployment layer.

Computer Methods in Applied Mechanics and Engineering, 2019

Log In