PhD position on Sparse Training for Deep Reinforcement Learning

This doctoral research will be at the intersection of sparsity and artificial intelligence. The research will investigate the potential of sparse-to-sparse training of deep neural networks within reinforcement learning frameworks. This innovative approach holds promise for creating highly efficient and scalable AI systems capable of learning with limited data and computational resources, pertinent in areas such as autonomous systems, online resource allocation, and complex decision-making processes.

Main Responsibilities:

Conduct original research on sparse-to-sparse training techniques, exploring new frontiers in algorithmic development for DRL.

Investigate the mathematical underpinnings of sparsity in deep reinforcement learning and its effects on learning dynamics, and generalization.

Design and evaluate experiments to validate the effectiveness of sparse- to-sparse training in various scenarios and benchmarks.

Publish and present research findings in top-tier conferences (e.g., Machine Learning, JMLR) and journals (e.g., NeurIPS, ICLR, ICML, IJCAI, AAMAS, ECMLPKDD).

Collaborate with a international team of researchers and industry partners.

The successful candidate will be embedded in the DMB research group, and the supervision will be ensured by Dr. Elena Mocanu and Prof. dr. Maurice van Keulen. This PhD position is part of the Modular Integrated Sustainable Datacenter (MISD) project and will have ample collaboration opportunities. As part of the MISD project effort led by Elena Mocanu, we are opening multiple positions (two Ph.D. candidates and one PostDoc) to join us and work at the intersection of dynamic sparse training in neural networks on various tasks.

Useful links:

Elena Mocanu webpage

DMB research group

MISD project

Sample of our work on sparsity

Your profile

The candidate is expected to have

A master degree (or will shortly, acquire) in Artificial Intelligence, Computer Science, Mathematics, Engineering, or a related discipline.

Excellent skills in machine learning and deep learning (experience with deep reinforcement learning is a plus).

Excellent programming skills (e.g. Python, PyTorch).

Experience with sparsity in computational models is a plus.

Good communication skills, with proficiency in English (written and oral).

Our offer

As a PhD candidate at UT, you will be appointed to a full-time position for four years, with a qualifier in the first year, within a very stimulating and exciting scientific environment;

The University offers a dynamic ecosystem with enthusiastic colleagues;

Your salary and associated conditions are in accordance with the collective labour agreement for Dutch universities (CAO-NU);

You will receive a gross monthly salary ranging from € 2.770,- (first year) to € 3.539,- (fourth year);

There are excellent benefits including a holiday allowance of 8% of the gross annual salary, an end-of-year bonus of 8.3%, and a solid pension scheme;

The flexibility to work (partially) from home;

A minimum of 232 leave hours in case of full-time employment based on a formal workweek of 38 hours. A full-time employment in practice means 40 hours a week, therefore resulting in 96 extra leave hours on an annual basis.

Free access to sports facilities on campus

A family-friendly institution that offers parental leave (both paid and unpaid);

You will have a training programme as part of the Twente Graduate School where you and your supervisors will determine a plan for a suitable education and supervision;

We encourage a high degree of responsibility and independence, while collaborating with close colleagues, researchers and other staff.

Information and application

Are you interested in this position? Please send your application via the 'Apply now' button below before 15 May 2024 , and include:

A brief motivation letter (maximum 2 pages), emphasizing (a) your individual reasons for desiring this role, (b) a reflective evaluation of your most and least developed skills (optional), and (c) your personal research interests and goals (optional).

A Curriculum Vitae, including your contact details, educational background, work experience (if any), publications (if any), and English proficiency test scores (optional).

Certified copies of degree certificates, with an accompanying detailed list of courses completed and corresponding grades.

Names and contact details of 2-3 referees (they will be approached only if the candidate is shortlisted).

For more information regarding this position, you are welcome to contact Dr. Elena Mocanu at [email protected]

About the department

Our DMB collective stands by its diversity, inclusivity, and interdisciplinary composition. We are doing research at the forefront of advancements in machine learning, deep learning, and computer vision to advance scientific knowledge and societal welfare in a large spectrum of data science applications. We disseminate our research findings through publications in leading conferences (such as NeurIPS, ICLR, ICML, AAMAS, and CVPR) and prestigious journals (e.g. Nature Communications, Machine Learning, etc.).

About the organisation

The faculty of Electrical Engineering, Mathematics and Computer Science (EEMCS) uses mathematics, electronics and computer technology to contribute to the development of Information and Communication Technology (ICT). With ICT present in almost every device and product we use nowadays, we embrace our role as contributors to a broad range of societal activities and as pioneers of tomorrow's digital society. As part of a people-first tech university that aims to shape society, individuals and connections, our faculty works together intensively with industrial partners and researchers in the Netherlands and abroad, and conducts extensive research for external commissioning parties and funders. Our research has a high profile both in the Netherlands and internationally. It has been accommodated in three multidisciplinary UT research institutes: Mesa+ Institute, TechMed Centre and Digital Society Institute.

Want to know more? Mocanu, E. (Elena)

Assistant Professor

Mocanu, E. (Elena)

Assistant Professor

Do you have questions about this vacancy? Then you can contact Elena for all substantive questions about this position and the application procedure. For general questions about working for the UT, please refer to the chatbot.

Contact

Phone:+31534898596

Email:[email protected]

How to apply Step 1

Apply. When you see a vacancy that appeals to you, you can apply online. We ask you to upload a CV and motivation letter and/or list of publications. You will receive a confirmation of receipt by e-mail.

Step 2

Selection. The selection committee will review your application and you will receive a response within 2 weeks after the vacancy has been closed.

Step 3

1st interview. The 1st (online or in person) meeting serves as an introduction where we introduce ourselves to you and you to us. You may be asked to give a short presentation. This will be further explained in the invitation.

Step 4

2nd interview. In the second interview, we will further discuss the job content, your skills and your talents.

Step 5

The offer. If the conversations are positive, you will be made a suitable offer. If applicable, we will sign you up for screening.

Your Colleagues Smit-van Veen, F.A.M. (Fiona)

Personal page

Rijken, J. (Jitske)

Personal page

Kok, J.N. (Joost)

Personal page

Our mission Human Touch

At the UT it's all about people, in line with our university's High Tech Human Touch philosophy. In everything we do, the well-being and future of our students and staff are paramount. From research and teaching to personnel management, campus management and the use of new technologies.

Our mission We are a university of technology

Our university is a public institution that serves society. We are accountable to society for the ways in which we use our academic freedom. We are responsible for ensuring that the power of science and technology is harnessed to achieve the best possible impact in a changing world. We cherish our rich tradition of combining technical and social sciences in our five profiling themes: Improving healthcare by personalized technologies; Creating intelligent manufacturing systems; Shaping our world with smart materials; Engineering our digital society; and Engineering for a resilient world.

Our mission We help to strengthen society

We help society meet the challenges of today and tomorrow. But we are also transparent about what science and technology can and cannot do in finding sustainable solutions. And help translate these solutions into everyday life.

Our mission We are sustainable

We want our communities to flourish and show resilience, so we seize opportunities for innovation. We are knowledgeable and have an eye for what society needs. Our students and staff receive all the guidance they need in their quest for ecological, social and economic sustainability. “The University of Twente is all about people. Our sustainable technologies help to strengthen society.”

Browse all jobs