Mayank Baranwal

Mayank Baranwal


Contact Me

About Me

I am a postdoctoral scholar in the Department of Electrical and Computer Engineering at the University of Michigan, Ann-Arbor in Prof. Alfred Hero's lab. I received my PhD in Mechanical Engineering at the University of Illinois at Urbana-Champaign, under the supervision of Prof. Srinivasa Salapaka. I develop techniques and technologies that help in comprehensive modeling, analysis and control of complex network systems. Using my expertise in combinatorial and discrete optimization, mean field inference, robust and distributed control, distributed optimization and machine learning, I address a range of problems in network systems, including, but not limited to, power systems, large scale machine learning, medical sciences, and transportation networks.

I graduated with Masters in Mechanical Science and Engineering in Summer 2014 and Masters in Mathematics in Spring 2015, both from UIUC.

An ardent Cricket fan, I enjoy watching and playing Cricket a lot. I also have an inclination towards painting.

Latest News/Preprints:
  • I have accepted the role of scientist with the research division of TATA Consultancy Services, in Mumbai (India).
  • Check out our recent work on new accelerated proximal point algorithm for sparse recovery. [arXiv]
  • Our work on sparse identification of chemical reaction networks has been accepted at Fuel. Available at: [PDF]
  • Our work on analyzing metric properties of GCNs has been accepted for presentation at the ISIT, 2020. Available at: [PDF]. A journal version of this work is available at: [PDF]
  • Our work on predicting metabolic pathways for unknown compounds has been accepted at Bioinformatics. Available at: [PDF]

Latest Projects

Chemical Reaction Network

Reduction of Chemical Networks

This project aims at developing theory and algorithms for network inference in the physical sciences and engineering with particular emphasis on dynamical chemical and biological reaction networks. Hybrid methods using machine learning (black-box) and mechanistic state space modeling (white-box) are of special interest. The project involves developing sparse learning algorithms for discovering new principles for predicting network dynamics.

Find out more

FxTS Optimization

Fixed-Time Distributed Optimization

We investigate the fixed-time distributed convex optimization problem for continuous time multi-agent systems under time-invariant topology. A novel type of nonlinear protocol coupled with tools from Lyapunov theory is proposed to minimize the sum of convex objective functions of each agent in fixed-time, i.e., convergence time is independent of initial conditions. Our algorithm is the first such protocol for achieving distributed optimization in fixed-time.

True Clusters

Determination of True Number of Clusters

Typically clustering algorithms provide clustering solutions with prespecified number of clusters. The lack of a priori knowledge on the true number of underlying clusters in the dataset makes it important to have a metric to compare the clustering solutions with different number of clusters. We show that the datasets where natural clusters are a priori known, the clustering solutions that identify the natural clusters are most persistent - in this way, this notion can be used to identify solutions with true number of clusters.

Find out more

Combinatorial Optimization

Combinatorial Optimization Problems

This project aims at extending mean-field based approach to several NP-hard problems, such as, data clustering, traveling salesman problem and its variants, image segmentation, mixed-integer linear programming, shape clustering, vehicle routing problems, graph clustering, minimum multiway k-cut, graph coloring and maximum independent set problems. The key idea is to lift the solution space to a space of probability distributions and employ maximum entropy principle to efficiently constrain the solutions. Below are some of the results of our approach to a variety of optimization problems.

Future Grid

Enabling the Grid of the Future

This project aims at developing innovative hardware and software solutions to integrate and coordinate generation, transmission, and end-use energy systems at various points on the electric grid. These control systems will enable real-time coordination between distributed generation, such as rooftop and community solar assets and bulk power generation, while proactively shaping electric load.

Find out more

Neural Coding

Neural coding in barrel cortex

The project explores neural coding in the barrel cortex of head-fixed mice that tracks walls with their whiskers in tactile virtual reality. The goal is to obtain correlations among activities of different neuron units.

Other Projects

Fast and Robust Control of Nanopositioning Systems

This project was my Masters work with Prof. Salapaka. We had implemented fast and robust 2DOF analog controllers using Field Programmable Analog Arrays (FPAAs) to achieve a ~200% improvement in tracking bandwidth of the nanopositioning stage in a MFP-3D AFM. Please refer to my thesis for more details:

[Link to thesis]

Physics based Modeling of Natural Bodies

This project is related to my work with Dr. Marco B. Quadrelli at Jet Propulsion Laboratory (JPL), NASA, during a three-months summer internship program. We had derived equations of motion for a general variable mass system in a coordinate-free form and developed several benchmarks involving balloon dynamics, motion of a double pendulum, asteroid dynamics, etc. We had also developed statistical shape models for asteroids that could explain the various light scattering phenomena.

Deflating Balloon Animation

Abnormal Motion Detection

I had worked on this project during a summer internship at the University of British Columbia, Vancouver with Dr. Clarence de Silva. We had developed a fusion scheme that relies on the data from surveillance camera and wearable body sensors to detect abnormal motion such as fall, run, jump, etc.

Inverted Pendulum

This was a hobby project with an aim to design and control a low-cost inverted pendulum. There are two control modes: (i) swing-up control, and (ii) control around unstable equilibrium. I was assisted by Dan Block in this project.

View on YouTube


Journal publications
  • CAPPA: Continuous-time Accelerated Proximal Point Algorithm for Sparse Recovery, (under review) 2020. [arXiv]
  • On Sparse Identification of Complex Dynamical Systems: A Study on Discovering Influential Reactions in Chemical Reaction Networks, Fuel, Elsevier 2020. [PDF]
  • Struct2Graph: A graph attention network for structure based predictions of protein-protein interactions, (under review) 2020.
  • Distributed Fixed-Time Economic Dispatch under Time-Varying Topology and Uncertain Information, (under review) 2019. [arXiv]
  • The Power of Graph Convolutional Networks to Distinguish Random Graph Models, (under review) 2019. [arXiv]
  • Fixed-Time Stable Proximal Dynamical System for Solving Mixed Variational Inequality Problems, (under review) 2019. [arXiv]
  • Distributed Optimization in Fixed-Time under Time-Varying Communication Topology, (under review) 2019. [arXiv]
  • A deep learning architecture for metabolic pathway prediction, Bioinformatics, Oxford University Press 2019. [PDF]
  • Clustering and Supervisory Voltage Control in Power Systems, Elsevier International Journal of Electrical Power & Energy Systems (IJEPES) 2019. [PDF]
  • Distributed Architecture for Robust and Optimal Control of DC Microgrids, IEEE Transactions on Industrial Electronics (TIE) 2018. [PDF]
  • Robust Atomic Force Microscopy using Multiple Sensors, AIP Review of Scientific Instruments (RSI) 2016. [PDF]
  • Fast and Robust Control of Nanopositioning Systems: Performance Limits Enabled by Field Programmable Analog Arrays, AIP Review of Scientific Instruments (RSI) 2015. [PDF]
  • Abnormal Motion Detection in Real Time using Video Surveillance and Body Sensors, International Journal of Information Acquisition (IJIA) 2011. [PDF]
Conference publications
  • A Fixed-Time Convergent Distributed Algorithm for Strongly Convex Function in a Time-Varying Network, IEEE CDC 2020. [Under review]
  • The Power of Graph Convolutional Networks to Distinguish Random Graph Models, IEEE ISIT 2020. [To appear] [PDF]
  • Multiway k-Cut in Static and Dynamic Graphs: A Maximum Entropy Principle Approach, IEEE CDC 2019. [PDF]
  • On the Persistence of Clustering Solutions and True Number of Clusters in a Dataset, AAAI 2019. [PDF]
  • Droopless Active and Reactive Power Sharing in Parallel Operated Inverters in Islanded Microgrids, IEEE CDC 2018. [PDF]
  • Weighted Kernel Deterministic Annealing: A Maximum-Entropy Principle Approach for Shape Clustering, IEEE ICC 2018. [PDF]
  • A Decentralized Scalable Control Architecture for Islanded Operation of Parallel DC/AC Inverters with Prescribed Power Sharing, IEEE ACC 2017. [PDF]
  • A Robust Scheme for Distributed Control of Power Converters in DC Microgrids with Time-Varying Power Sharing, IEEE ACC 2017. [PDF]
  • Multiple Traveling Salesmen and Related Problems: A Maximum-Entropy Principle based Approach, IEEE ACC 2017. [PDF]
  • Clustering of Power Networks: An Information-Theoretic Perspective, IEEE ACC 2017. [PDF]
  • DC Bus Voltage Regulation Using Photovoltaic Module: A Non-Iterative Method, IEEE ACC 2017. [PDF]
  • Clustering with Capacity and Size Constraints: A Deterministic Approach, IEEE ICC 2017. [PDF]
  • Vehicle Routing Problem with Time Windows: A Deterministic Annealing Approach, IEEE ACC 2016. [PDF]
  • Robust Decentralized Voltage Control of DC-DC Converters with Applications to Power Sharing and Ripple Sharing, IEEE ACC 2016. [PDF]
  • Modeling and Simulation of Flight Dynamics of Variable Mass Systems, AIAA/AAS Astrodynamics Specialist Conference, 2014. [PDF]