Evolutionary Computation Digest — Thursday, 03 December 2020, Volume
34: Issue 12

SUBMISSION ADDRESS:    [log in to unmask]

(UN)SUBSCRIPTION INSTRUCTIONS:  at the bottom of this email

Today's Topics:

- 04 December: Lecturer Position in Algorithms (University of Sheffield, UK)
- Microsoft Research Postdoc: ML and AI
- Microsoft Research Postdoc: Reinforcement Learning
- PhD Studentship in Multi-task Learning in Deep Neural Networks

 CFPs (with submission deadline)
 - Call for sessions on Evolutionary and Swarm Optimizatino @ EURO 2021
 - 12 January, 2021: Genetic Improvement Workshop (@ICSE)
 - 25 January, 2021: Conference on Machine Learning, Optimization, and
Data Science (LOD 2021)
 - 31 January, 2021: IEEE Workshop on Parallel/Distributed
Combinatorics and Optimization (PDCO)
 - 30 February, 2021: Book Chapters---Handbook of Nature-Inspired Optimization
 - 28 May, 2021: Call for Entries: 18th Annual "Humies" Awards


April 7–9, 2021, Seville, Spain: EvoStar 2021

July 10–14, 2021, Lille, France: GECCO 2021

Sender: Pietro Oliveto <[log in to unmask]>
Subject: Lecturer Position in Algorithms (University of Sheffield, UK)
[Closing Date: 4 December 2020]

This is an exciting opportunity for a Lecturer in Algorithms at the
University of Sheffield, UK,  a world top 100 University. Working in
the Department of Computer Science, you will join our established
Algorithms Group. The group focuses on the design and analysis of
algorithms which provably solve computational problems efficiently.

The Department is embarking on an exciting growth strategy following
our strong performance in the Research Excellence Framework (REF)
2014, in which we were ranked 5th out of 89 computer science
departments in the UK. To build upon our continued success, we seek to
appoint a Lecturer in the design and analysis of algorithms, with
specialist expertise in an area including, but not limited to:

randomised algorithms
streaming algorithms and sublinear-time algorithms
combinatorial optimisation
approximation algorithms
parameterised complexity and fixed-parameter tractable algorithms
distributed computing
graph algorithms analysis
data structures design and analysis
algorithmic game theory
randomised search heuristics

You will hold a PhD in computer science or a related area, and you
will be able to conduct research to the highest standards. You will
secure research funding, publish in high impact journals and
conferences, supervise research students and manage research projects.
As a teacher, you will play a key role in maintaining our reputation
for high-quality teaching by designing, delivering and assessing
undergraduate and postgraduate-level courses in computer science. We
seek candidates who will be able to make a distinctive individual
contribution to our algorithms research portfolio.

We’re one of the best not-for-profit organisations to work for in the
UK. The University’s Total Reward Package includes a competitive
salary, a generous Pension Scheme and annual leave entitlement, as
well as access to a range of learning and development courses to
support your personal and professional development.

We build teams of people from different heritages and lifestyles whose
talent and contributions complement each other to greatest effect. We
believe diversity in all its forms delivers greater impact through
research, teaching and student experience. The Department of Computer
Science holds a Silver Athena SWAN award, in recognition of our
commitment to equality and diversity.

This role has been identified as a full-time post, but we are
committed to exploring flexible working opportunities with our staff
which benefit both the individual and the University. We would be
pleased to consider flexible delivery of the role subject to meeting
the business needs of the post.

For more information:

Sender: Cyril Zhang <[log in to unmask]>
Subject: ML/AI postdoc positions at Microsoft Research NYC

Microsoft Research in New York City seeks outstanding postdoc
applicants in the areas of machine learning, artificial intelligence,
and related fields.

Microsoft Research offers an exhilarating and supportive environment
for cutting-edge, multidisciplinary research, both theoretical and
applied, with access to an extraordinary diversity of big and small
data sources, an open publications policy, and close links to top
academic institutions around the world. We seek applicants with the
passion and ability to craft and pursue an independent research
program, including a strong publication record at top research venues.
The earliest start date is July 1, 2021.


For more details, and to apply, visit:

Sender: Cyril Zhang <[log in to unmask]>
Subject: RL research positions at Microsoft Research

Microsoft Research is expanding its global Reinforcement Learning team
and has multiple openings for researchers (at all levels), postdocs,
and engineers with interest in all aspects of this field, including
theory, empirics and applications. In addition to candidates working
on core RL, we encourage applicants from related research areas such
as deep learning and representation learning, natural language
processing, computer vision, games, dialog systems, online learning,
operations research, systems, and other areas (e.g., theoretical CS
and HCI), as long as their future research agenda overlaps with RL or
sequential decision making. We are hiring in New York, Redmond,
Montreal, Boston, and Cambridge UK.

Microsoft Research wants to enable the next generation of machine
learning using interactive reinforcement-based approaches to solve
real-world problems. We believe that the best solutions will arise by
combining expertise of people with many different backgrounds and this
unique opportunity is part of that effort. To see more details on the
existing people and examples of some of the ongoing RL projects,
please see
The links to apply for specific positions are:

Postdoctoral positions:
Full-time roles for recent graduates:
Full-time roles for more senior levels:
All positions:

Sender: ICAS <[log in to unmask]>
Subject: PhD Studentship in Computer Science - Multi-task Learning in
Deep Neural Networks

PhD Studentship in Computer Science -

Multi-task Learning in Deep Neural Networks

Supervisors: Professor Giuseppe Di Fatta; Professor Xia Hong;

Project Overview:
In AI and Deep Learning a fascinating challenge is to create an agent
that can solve multiple tasks. In the large majority of machine
learning approaches, the trained model is specialised on a single task
and is useless to solve any other problem. Multi-task Learning (MTL)
is an approach to machine learning in which a model is trained to
solve multiple tasks simultaneously. This is similar to the learning
process in humans, who learn general skills useful to multiple tasks:
e.g., hand dexterity is useful to solve many tasks and is improved by
learning many tasks at the same time. In machine learning MTL has been
shown to be particularly effective in generating better generalised
models that take advantage of the similarities and differences across
tasks. Its effectiveness is also very useful in solving a group of
problems altogether, each of which with a limited number of training
In this PhD project MTL methods will be investigated to identify the
best approaches for Deep Neural Networks and, in particular, for
training the networks with evolutionary algorithms instead of a more
classic gradient descent strategy. The overarching aim of this project
is to contribute to theory and applications of machine learning with
effective deep Neuroevolution algorithms and non-linear optimization
methods. A key enabling factor to understand deep neural networks is
to consider neural networks as complex networks, this PhD project will
try to decipher the complex neural networks by the information
theoretic learning principle, in general, and the information
bottleneck, in particular.
Multi-task Deep Neuroevolution will be applied to classic and recent
testbeds for deep learning (e.g., CIFAR-100, Atari games, XTREME,
StarCraftII) as well as real-world problems, such as the prediction of
neurodegenerative diseases (dementia) from human brain images or
synthetic motor control for modelling  rich and diverse motor
behaviours across multiple tasks at humanoid scale.
The project will be guided by a team of experienced supervisors with
extensive competence in this area and will have access to
state-of-the-art computing facilities.

Applicants should hold or expect to gain a minimum of a 2:1 Bachelor
Degree or equivalent in Mathematics or Computer Science.

Funding Details:
Starts January 2021 or soon after
3 year award
Funding covers full tuition fees plus UKRI stipend

How to apply:
To apply for this studentship please submit an application for a PhD
in Computer Science at

*Important notes*

Please quote the reference ‘GS20-097’ in the ‘Scholarships applied
for’ box which appears within the Funding Section of your on-line
When you are prompted to upload a research proposal, please submit a
personal statement (max 1 page) to present your interest, motivation
and suitability for this project

Further Enquiries:
Please note that, where a candidate is successful in being awarded
funding, this will be confirmed via a formal studentship award letter;
this will be provided separately from any Offer of Admission and will
be subject to standard checks for eligibility and other criteria.
For further details please contact [log in to unmask], quoting
the reference ‘GS20-097’ in the email subject.

Sender: Patrick Siarry <[log in to unmask]>
Subject: Call for sessions on topics associated with the stream
“Evolutionary and Swarm Optimization ” of EURO 2021 _ Athens, Greece,
11-14 July 2021

EURO 2021, the 31st European Conference on Operational Research
Athens, Greece, 11-14 July 2021 (
 «  Evolutionary and Swarm Optimization » Stream
“Discrete Optimization Algorithms” Area

We invite proposals for sessions on topics associated with the Stream
“Evolutionary and Swarm Optimization ” which falls within the Area
“Discrete Optimization Algorithms”. If you are interested in running a
session with this stream, please email us with details of your
proposal (including the session title and names of the potential
organizers). Sessions could, for example, specialise in particular
problem areas (e.g. transportation, timetabling, energy management
etc) or examine the application of a particular technique that employs
Evolutionary or Swarm principles, such as illumination algorithms,
distributed algorithms or performance comparisons across techniques.

Best Wishes,

Laetitia Jourdan - [log in to unmask]
Patrick Siarry - [log in to unmask]
Neil Urquhart - [log in to unmask]

Sender: w langdon <[log in to unmask]>
Subject: GI-2021 deadline 12 Jan 2021 Genetic Improvement workshop CFP

10th International Workshop on the Repair and Optimisation of Software
                          using Computational Search

                              23-29 May 2021

                twitter @gi2021

  Co-located with the 43rd International Conference on Software Engineering,
  ICSE 2021, Madrid, Spain, and virtually.

Paper submission deadline: 12 January 2021

Call for Submissions:

We invite submissions that discuss recent developments in all areas of
research on, and applications of, Genetic Improvement.

GI is the premier workshop in the field and provides an opportunity
for researchers interested in automated program repair and software
optimisation to disseminate their work, exchange ideas and discover
new research directions.

Topics of interest include both the theory and practice of
Genetic Improvement. Applications include, but are not limited to,
using GI to:

 * Improve efficiency
 * Decrease memory consumption
 * Decrease energy consumption
 * Transplant new functionality
 * Specialise software
 * Translate between programming languages
 * Generate multiple versions of software
 * Repair bugs

Key Dates:

    Submission    12 January  2021 (Tue)
    Notification  22 February 2021 (Mon)
    Camera-ready  12 March    2021 (Fri)
    Workshop      23-29 May 2021

Sender: ICAS <[log in to unmask]>
Subject: Save the Date: The 7th Online & Onsite Int. Conf. on Machine
Learning, Optimization & Data Science

Save the Date:
The 7th Online & Onsite International Conference on Machine Learning,
Optimization, and Data Science – LOD 2021
June 29 - July 2, Grasmere, Lake District, England – UK

Dear Colleague,

The 7th International Online & Onsite Conference on Machine Learning,
Optimization, and Data Science – LOD 2021, June 29 - July 2, Grasmere,
Lake District, England – UK

[log in to unmask]

Important Dates:
* Special Session Proposals: Monday December 14, 2020.
* Paper Submission Deadline: Monday January 25, 2021 – Anywhere on Earth.

Sender: "Grégoire DANOY" <[log in to unmask]>
Subject: CFP - 11th IEEE Workshop on Parallel / Distributed
Combinatorics and Optimization (PDCO) in conjunction with IEEE IPDPS

The 11th IEEE Workshop on Parallel / Distributed
               Combinatorics and Optimization (PDCO 2021)


                             held in conjunction with
                           the 35th IEEE International
   Parallel and Distributed Processing Symposium (IPDPS'2021)
                                   May 17-21, 2021

                                     Portland, USA

The IEEE Workshop on Parallel / Distributed Combinatorics and
Optimization aims at providing a forum for scientific researchers and
engineers on recent advances in the field of parallel or distributed
combinatorics for difficult optimization problems, ranging from
theoretical to applied problems. The latter include for instance 0-1
multidimensional knapsack problems and cutting stock problems, large
scale linear programming problems, nonlinear optimization problems,
global optimization and scheduling problems.

Emphasis will be placed on new techniques for solving difficult
optimization problems, like cooperative methods for integer
programming problems, nature-inspired techniques and hybrid methods.
Aspects related to Combinatorial Scientific Computing (CSC) will also
be treated. We also solicit submissions of original manuscripts on
sparse matrix computations and related topics (including graph
algorithms); and related methods and tools for their efficiency on
different parallel systems. Applications combining traditional
parallel and distributed combinatorics and optimization techniques as
well as theoretical issues (convergence, complexity, etc.) are

Application domains of interest include (but are not limited to) cloud
computing, planning, logistics, manufacturing, finance,
telecommunications and computational biology.

* Exact methods, heuristics, metaheuristics, hybrid methods;
* Parallel / distributed algorithms for combinatorial optimization;
* Parallel / distributed  metaheuristics;
* Nature inspired parallel / distributed computing;
* Integer programming, linear programming, nonlinear programming;
* Global optimization, polynomial optimization;
* Cooperative methods, hybrid methods;
* Parallel sparse matrix computations, graph algorithms, load balancing;
* Applications: cloud computing, planning, logistics, manufacturing,
finance, telecommunications, computational biology, combinatorial
algorithms in high performance computing.

Important Dates:
- Submission deadline: January 31, 2021
- Decision notification: March 1, 2021
- Camera-Ready papers due: March 15, 2021
- Workshop: May 17, 2021

Sender: "[log in to unmask]" <[log in to unmask]>
Subject: IEEE CIS School ; Call for Book Chapters ;

Dear Colleague,

We look forward to your participations in the following activities.

1.   IEEE CIS Summer School at IIT Indore:  We’re delighted to inform
that IIT Indore is organizing a 4 days IEEE Computational Intelligence
Society (CIS) Summer School (online mode) on "Emerging Research Trends
in Computational Intelligence – Theory and Applications" during
November 26-29, 2020. Details of the summer school are available at

2.  Call for Book Chapters (Springer Book):  Handbook of
Nature-Inspired Optimization Algorithms: The State of the Art Volume
I: Solving Single Objective Bound-Constrained Real-Parameter Numerical
Optimization Problems

3.   Call for Book Chapters (Springer Book):   Handbook of
Nature-Inspired Optimization Algorithms: The State of the Art Volume
II: Solving Single Objective Constrained Real-Parameter Optimization

4.  Three CEC 2021 Competitions with associated Special Sessions
(SS-37 & SS-46) in Krakow, Poland in June-July 2021 ( ):

(a)  Real-World Multiobjective Constrained Optimization:

 (b)   Real Parameter Single Objective Bound Constrained Optimization:

 (c)   Multimodal Multiobjective Path Planning Optimization:

5.   Surveys   &     Benchmarks For Evolutionary & Swarm Algorithms:

6.       Codes/software of our publications available for downloading:

Sender: w langdon <[log in to unmask]>
Subject: Call For Entries 18th Annual (2021) "Humies" Awards

      Call For Entries
                    18th Annual (2021) "Humies" Awards
For Human-Competitive Results Produced by Genetic and Evolutionary Computation

To be held as part of:

Genetic and Evolutionary Computation Conference (GECCO)
July 10-14, 2021 (Saturday - Wednesday)
Lille, France

See the latest, updated information at

Entries are hereby solicited for awards totaling $10,000 for
human-competitive results that have been produced by any form of
genetic and evolutionary computation (including, but not limited to
genetic algorithms, genetic programming, evolution strategies,
evolutionary programming, learning classifier systems, grammatical
evolution, gene expression programming, differential evolution, etc.)
and that have been published in the open literature between the
deadline for the previous competition and the deadline for the current

This information is also available at the GECCO-2021 website, under
the "Calls" dropdown at top of the main page, which takes you to  At least one author of the
submission must be registered for GECCO, although there is no
requirement to present a paper there--only the in-person or video
presentation of the Humies entry.

Important Dates:

 * Friday May 28, 2021
   Deadline for entries (consisting of one TEXT file, PDF files for
   one or more papers, and possible "in press" documentation. Please
   send entries to goodman at msu dot edu

 * Friday June 11, 2021
   Finalists will be notified by e-mail

 * Friday, June 25, 2021
   Finalists not presenting in person must submit a 10-minute video
   presentation to goodman at msu dot edu.

 * July 10-14, 2021 (Saturday - Wednesday)
   GECCO conference
   (the schedule for the Humies session is not yet final, so please
   check the GECCO program as it is updated)

 * Monday, July 12, 2021, 13:40-15:20
   Presentation session, where 10-minute videos will be available for

 * Wednesday, July 14, 2021
   Announcement of awards at plenary session of the GECCO conference

Call For Entries

Techniques of genetic and evolutionary computation are being
increasingly applied to difficult real-world problems, often yielding
results that are not merely academically interesting, but competitive
with the work done by creative and inventive humans. Starting at the
Genetic and Evolutionary Computation Conference (GECCO) in 2004, cash
prizes have been awarded for human-competitive results that had been
produced by some form of genetic and evolutionary computation in the
previous year.

This prize competition is based on published results. The publication
must be a refereed publication in the open literature (e.g., the GECCO
conference, any another reviewed conference or workshop, journal, or
chapter in edited book). Submission of more than one entry by a single
person or team is allowed.

The competition is open to any paper

 (1) published in the open literature between May 29, 2020
(the deadline for the previous year's competition) and May 28, 2021
(the deadline for this competition), (explicitly including GECCO-2000) or

 (2) that is "in press" by the deadline for this competition.
"In Press" means the paper must have been unconditionally accepted for
publication and be identical to that which will be published
imminently without the possibility of any further changes or revision
by the authors or editors. For example, a paper accepted for the
current year's GECCO conference would not have been published by the
deadline for the competition. However, because the paper has already
been unconditionally accepted for publication (and the final
camera-ready version submitted to the conference prior to the deadline
for this competition), a GECCO paper is "in press."  If an entry is
"in press," the entry must include a copy of the documentation
establishing that the paper meets this requirement.

Cash prizes of $5,000 (gold), $3,000 (silver), and bronze (either one
prize of $2,000 or two prizes of $1,000) will be awarded for the best
entries that satisfy one or more of the criteria for
human-competitiveness. The awards will be divided equally among
co-authors unless the authors specify a different division at the time
of submission.

Please find the full call for entries and detailed instructions for at
the following URL:

        Prof. W. B. Langdon
        Department of Computer Science
        University College London
        Gower Street, London WC1E 6BT, UK


 - Send submissions (articles) to [log in to unmask]
 DO NOT send submissions to the [log in to unmask] address.

 - To subscribe send email to [log in to unmask] containing the
 following text in the body of the message:

   subscribe ec-digest-l <Your Name (up to 4 words)>

 - To unsubscribe send email to [log in to unmask] containing the
 following text in the body of the message:

   unsubscribe ec-digest-l

 - To change your email address, simply unsubscribe the old address
 and subscribe the new one.

 - Send other administrative requests to [log in to unmask]

 End of Evolutionary Computation Digest