News Research Experience Publications Technical Skills Academic Projects

Amit Sarker

Email:

I am a first-year PhD student at the University of Massachusetts Amherst. I am advised by Dr. Ali Sarvghad and Dr. Narges Mahyar in the HCI-VIS Lab at UMass. Prior to that, I worked as a research assistant at the Cognitive Agents and Interaction Lab (CAIL), where I worked under the supervision of Dr. Md. Mosaddek Khan. My research activities at CAIL spanned a broad range of real-world problem solving, ranging from multi-agent coordination and optimization to planning and scheduling.

I started my professional career as a Software Engineer at TigerIT Bangladesh Limited, where I worked as a quality assurance engineer under the Software Quality Assurance (SQA) team. I received my bachelor's degree from the Department of Computer Science and Engineering, University of Dhaka. [Undergraduate Curriculum]

My research interests are:

  • Human-Computer Interaction
  • Interaction between Human and Robot/AI
  • Multi-agent System

CV  /  Google Scholar  /  LinkedIn  /  GitHub  /  ORCiD

profile photo
News

  • September 2022: Started my PhD in Computer Scinece at UMass Amherst!
  • May 2021: I will present my paper at AAMAS 2021. I will also be volunteering at the conference.
  • January 2021: AAMAS paper on A Local Search Based Approach to Solve Continuous DCOPs accepted.
  • October 2020: New preprint on A Particle Swarm Inspired Approach for Continuous Distributed Constraint Optimization Problems is now available.
  • May 2020: I will present my paper at AAMAS 2020. I have also received the conference scholarship!
  • April 2020: Started working as a Software Engineer at TigerIT Bangladesh Limited.
  • January 2020: AAMAS extended abstract on C-CoCoA: A Continuous Cooperative Constraint Approximation Algorithm to Solve Functional DCOPs accepted.
  • January 2020: OptLearnMAS workshop paper on C-CoCoA: A Continuous Cooperative Constraint Approximation Algorithm to Solve Functional DCOPs accepted.
  • January 2020: Successfully defended my undergraduate thesis!
  • November 2019: First runner up on Code Samurai 2019 - Hackathon by BJIT.

Research Experience

  • Applying Local Search-Based Algorithms for solving Continuous DCOPs

    Abstract: Distributed Constraint Optimization Problems (DCOPs) are a suitable formulation for coordinating interactions (i.e. constraints) in cooperative multi-agent systems. The traditional DCOP model assumes that variables owned by the agents can take only discrete values and constraints' cost functions are defined for every possible value assignment of a set of variables. While this formulation is often reasonable, there are many applications where the decision variables are continuous-valued and constraints are in functional form. To overcome this limitation, Continuous DCOPs (C-DCOPs), an extension of the DCOPs model has been proposed that is able to formulate problems having continuous variables. The existing methods for solving C-DCOPs come with a huge computation and communication overhead. In this paper, we apply continuous non-linear optimization methods on Cooperative Constraint Approximation (CoCoA) algorithm, which is a non-iterative, fast incomplete local search approach for solving DCOPs. We empirically show that our algorithm is able to provide high-quality solutions at the expense of smaller communication cost and execution time compared to the state-of-the-art C-DCOP algorithms.

    [AAMAS 2021][AAMAS 2020]

  • Applying Population-Based Algorithms to Solve Large C-DCOPs

    Abstract: Distributed Constraint Optimization Problems (DCOPs) are a widely studied framework for coordinating interactions in cooperative multi-agent systems. In classical DCOPs, variables owned by agents are assumed to be discrete. However, in many applications, such as target tracking or sleep scheduling in sensor networks, continuous-valued variables are more suitable than discrete ones. To better model such applications, researchers have proposed Continuous DCOPs (C-DCOPs), an extension of DCOPs, that can explicitly model problems with continuous variables. The state-of-the-art approaches for solving C-DCOPs experience either onerous memory or computation overhead and unsuitable for non-differentiable optimization problems. To address this issue, we propose a new C-DCOP algorithm, namely Particle Swarm Optimization Based C-DCOP (PCD), which is inspired by Particle Swarm Optimization (PSO), a well-known centralized population-based approach for solving continuous optimization problems. In recent years, population-based algorithms have gained significant attention in classical DCOPs due to their ability in producing high-quality solutions. Nonetheless, to the best of our knowledge, this class of algorithms has not been utilized to solve C-DCOPs and there has been no work evaluating the potential of PSO in solving classical DCOPs or C-DCOPs. In light of this observation, we adapted PSO, a centralized algorithm, to solve C-DCOPs in a decentralized manner. The resulting PCD algorithm not only produces good-quality solutions but also finds solution without any requirement for derivative calculations. Moreover, we design a crossover operator that can be used by PCD to further improve the quality of solutions found. Finally, we theoretically prove that PCD is an anytime algorithm and empirically evaluate PCD against the state-of-the-art C-DCOP algorithms in a wide variety of benchmarks.

    [arXiv]

Ongoing Research Projects

Publications

  • A Local Search Based Approach to Solve Continuous DCOPs
    Amit Sarker, Moumita Choudhury, and Md. Mosaddek Khan
    In Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 1127–1135, 2021. [ACM][Slides][Code]

  • C-CoCoA: A Continuous Cooperative Constraint Approximation Algorithm to Solve Functional DCOPs
    Amit Sarker, Abdullahil Baki Arif, Moumita Choudhury, and Md. Mosaddek Khan
    In Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 1990–1992, 2020. (Extended Abstract)
    11th International Workshop on Optimization and Learning in Multiagent Systems (OptLearnMAS) @ AAMAS, 2020. (Full Paper)

  • Applying Local Search Algorithms for solving Functional Distributed Constraint Optimization problems (F-DCOPs) in Multi-Agent Systems
    Amit Sarker, Abdullahil Baki Arif, and Md. Mosaddek Khan
    Undergraduate Thesis, Computer Science and Engineering, University of Dhaka, 2019.

Technical Skills

  • Programming Languages: C/C++, Python, Java
  • Databases: MySQL, Oracle, MongoDB
  • Libraries: PyTorch, Pandas, NumPy, Matplotlib
  • Web Technologies: JavaScript, Python Flask
  • Cloud Platform: Google Firebase

Academic Projects
My Food Diary Poster

My Food Diary

[GitHub][YouTube][Poster]
  • An android app implemented in Java for food tracking and health management.
  • A user-friendly way to track daily calorie intake, water consumption and weight.
  • AI (Genetic Algorithm) based automated food suggestions and goal oriented motivation.
  • Applied data visualization techniques (pie chart, bar chart, line chart) to show the analytics.

Track Me Poster

Track Me

[GitHub][YouTube][Poster]
  • An android app implemented in Java for tracking personal vehicles on road by using Google Maps API.
  • Clustering based approach to detect anomaly in driving pattern and notify the car owner.
  • Can be used to visualize the traffic information by generating heatmaps.

Stick hero gif

Stick-Hero

[GitHub][YouTube]
  • A desktop version of the famous android game Stick Hero implemented using C++ and Simple and Fast Multimedia Library (SFML).

CSEDU Book Club

CSEDU Book Club

[GitHub (Web)] [GitHub (Android)]
  • A website and an android app for book sharing and reviews for the reading club of department of CSE, University of Dhaka.