Dr.  Mostafa Rezapour

Teacher Scholar Postdoctoral Fellow

 

Dr. Rezapour’s

Optimization, Numerical Linear Algebra, Machine Learning, Deep Learning.

Machine Learning Group

  • Office: 348 Manchester
  • Home Page:
  • Email: rezapom 'at' wfu.edu
  • Ph.D. in Applied Mathematics (optimization and machine learning), Department of Mathematics and Statistics, Washington State University, Jun 2020 Adviser: Dr. Thomas Asaki;    Thesis: Trust-region methods for unconstrained optimization problems
  • M.S. in Statistics (Data Analysis), Department of Mathematics and Statistics, Washington State University, Spring 2019 Adviser: Dr. Nairanjana Dasgupta;  Project: Application of Machine Learning on a diagnostic Breast Cancer data with a modified Gradient Descent
  • M.S. in Applied Mathematics (Optimization), Department of Mathematics and Statistics, Sharif University of technology Adviser: Dr. Nezam Mahdavi-Amiri Thesis: Implementation of a Retrospective Trust-Region Method for Unconstrained Optimization
Selected publications:
Summer 2022: Spring 2022:
  • Instructor, MST 113 - Multivariable Calculus (section B)
  • Instructor, MST 113 - Multivariable Calculus (section C)
  • Instructor, MST 113 - Multivariable Calculus (section D)
Fall 2021: Summer 2021:
  • Instructor, MST 113 - Multivariable Calculus
  • Instructor, MST 111- Calculus with Analytic Geometry I
Spring 2021: Fall 2020: Instructor, 2017- 2020
  • Advanced Linear Algebra for PhD students (PhD Qualifying Exam)
  • Principles of Optimization (Linear, Integer and Nonlinear)
  • Differential Equations
  • Introductory Statistics for Engineers
  •  Calculus for Business and Economics
  •  Calculus III
  • Calculus II (course mentor)
  • Calculus I
Python, Matlab, PHP, Java, R, SAS
Awards 2019-2020
  • The Craft Family Scholarship, Jun 2020, Washington State University, the College of Arts and Sciences (CAS). This funding is offered in recognition of the outstanding achievements and is intended to support the academic success. Arnold M. and Atsuko (Onda) Craft established this scholarship to support hard working students in a variety of fields.
  • Sidney G. and Evelyn Hacker Graduate Research Fellowship (2019-2020, WSU). The scholarship recognizes excellence in graduate research.
  • American Mathematical Society Travel Award (2020). To attend Joint Mathematics Meeting, Jan 15-18, 2020, Denver, Colorado, US.
  •  SIAM Travel Award (2019). To attend the "Applied Mathematics: The Next 50 Years".
  •  SIAM Travel Award (2020). To attend SIAM Conference on Mathematics of Data Science (MDS20) Hilton Cincinnati Netherland Plaza, Cincinnati, Ohio, U.S.
  •  GPSA Travel Award (2019). To attend Informs Annual Meeting, October 2019.
  •  GPSA Travel Award (2020). To attend Joint Mathematics Meeting, Jan 15-18, 2020, Denver, Colorado, US.
Exams
  • The top score of GQE (PhD Qualifying Examination) - Department of Mathematics and Statistics, WSU (94/100, 2017)
  • Ranking number 8 among more than 12000 of students participating in the national university entrance examination for master's degree in Applied Mathematics.
  • Ranking number 9 among more than 12000 of students participating in the national university entrance examination for master's degree in Pure Mathematics.
 Recent
  • A Machine Learning Analysis of Covid-19 Mental Health Data, December 2nd, 2021, Machine Learning Group, Wake Forest University, NC, U.S.
  • Supervised vs. Unsupervised Learning, November 4, 2021, EGR 312 (invited by Professor Courtney Di Vittorio), Department of Engineering, Wake Forest University, NC, U.S.
  • Deep Neural Network as an Interpolator, September 16, 2021, Machine Learning Group, Wake Forest University, NC, U.S.
  • A Machine Learning Analysis of a Cancer Dataset, September 9, 2021, Machine Learning Group, Wake Forest University, NC, U.S.
  • (Minisymposium- A talk on this paper)A New Multipoint Symmetric Secant Method with a Dense Initial Matrix, July 20, 2021, SIAM Conference on Optimization (OP21)
  • How to use deep learning in our research (part 2), April 30, 2021, Python Working Group, WSU, Washington, U.S.
  • (Colloquium) Adaptive trust-region algorithms for unconstrained nonlinear optimization, Department of Mathematics and Statistics Colloquium, April 29, 2021, Wake Forest University, North Carolina, U.S.
  • How to use deep learning in our research (part 1), April 23, 2021, Python Working Group, WSU, Washington, U.S.
  • A new approach in derivative-free optimization (part II), Analysis, PDEs, differential geometry and applications seminar, April 15, 2021, Department of Mathematics and Statistics, Wake Forest University, North Carolina, U.S.
  • A new approach in derivative-free optimization (part I), Analysis, PDEs, differential geometry and applications seminar, April 8, 2021, Department of Mathematics and Statistics, Wake Forest University, North Carolina, U.S.
  • Python for Machine Learning, Deep Learning, Differential Equations, and Optimization, Python Working Group, WSU, Dec 4, 2020, Washington, U.S.
  • Trust-region Methods for Unconstrained Optimization Problems, WFU MST 683 Seminar, Nov 11, 2020, Wake Forest University, Winston Salem, North Carolina, U.S.
  • Neural Trust-Region Methods for Unconstrained Nonlinear Optimization, SIAM Conference on Mathematics of Data Science (MDS20), May 2020, Cincinnati, Ohio, U.S.
  • Neural partial differential equation solver with fractional gradient descent, JMM (American Mathematical Society contributed paper session), Jan 2020, Denver, Colorado, U.S.
  • Solving PDEs with Neural Networks, JMM (Mathematical Association of America contributed paper session), Jan 2020, Denver, Colorado, U.S.
  • Two Modified Trust Region Algorithms for Unconstrained Optimization, Informs Annual Meeting, October 2019, Seattle, WA, U.S.
  • Application of a Flexible Gradient Descent to Machine Learning, Informs Annual Meeting, October 2019, Seattle, WA, U.S.
Soccer, computer programming, travel, hiking and running

Subscribe to the Machine Learning Group email list

The Machine Learning Reading Group welcomes faculty and students who are interested in doing research in optimization, machine learning, deep learning and related areas. If you are interested in receiving information from the Machine Learning Group, please enter your name, email address and leave “Subscribe to the Machine Learning Group’s email list” in the comment box.

 

Comments are closed.