Practical advice on building a research collaboration with our group, from first contact and shared goals to partnership.
- BIO
Pliff Jenkins
"I have already bought and tested many, many templates. But this Canvas HTML Template is really the best and most comprehensive for me. I highly recommend it."
Academic Positions
Professor
MIT, Course - Jun 3rd 2022
Assistant Professor
MIT, Course - Sep 11th, 2017
Assistant Professor
St. John’s University, Kishanattam, Kerala - Mar 7th, 2011
Visiting Ass. Professor
ADR-Centric Juridical University - Dec 8th, 2010
Education & Training
Ph.D. in Course
University of NY - 2021
B. Sc. in Applied Course
University of NY - 2017
B. Sc. in Statistics
Institute for Mathametics - 2015
Rewards
Distinguished Faculty Research Excellence
2023
Awarded for sustained contributions to applied statistics and machine learning, recognising a decade of peer-reviewed work that reshaped how predictive models are taught and applied across the department. The committee cited the candidate’s mentorship of doctoral students and a consistent record of rigorous, reproducible research.
Camvat Education Reward
2020
Recognised by the Camvat education board for innovative teaching that made advanced quantitative subjects accessible to first-year students, combining clear lectures, open datasets, and collaborative sessions.
Listen & lecture Statistical
2020
Watch video here.
Honoured for a public lecture series on statistical reasoning that drew record attendance, translating complex inference into intuitive examples for students, teachers, and the wider community across the region.
Honoured for a public lecture series on statistical reasoning that drew record attendance, translating complex inference into intuitive examples for students, teachers, and the wider community across the region.
Year of the Knowledge Rewards
2018
Watch video here.
Celebrated as a leading voice in knowledge sharing, this award marked years of accessible workshops, freely published course notes, and a commitment to teaching that helped many learners discover a passion for mathematics.
Celebrated as a leading voice in knowledge sharing, this award marked years of accessible workshops, freely published course notes, and a commitment to teaching that helped many learners discover a passion for mathematics.
Works
The Psycolodgy of Knowledge.
Published on: 11th Oct, 2021
An accessible exploration of how people acquire, retain, and apply knowledge across disciplines. Drawing on cognitive research and real teaching experience, the book offers educators practical strategies for building lasting understanding in their classrooms.
Experience
Dec 2022 ─ Present
Leading the applied statistics group, supervising doctoral candidates and directing funded research on optimal transport and learning theory.
Mar 2021 ─ Dec 2022
Conducted postdoctoral studies in optimisation and algorithmic complexity, publishing several peer-reviewed papers and co-teaching graduate seminars each term.
Feb 2019 ─ Mar 2021
Tutored undergraduate mathematics and assisted senior faculty with curriculum design and grading.
Jan 2017 ─ Feb 2019
Began teaching introductory statistics while completing graduate coursework and early independent research projects.
Math Expert
Deep command of statistics, probability, and applied mathematical modelling.
Longtime Experience
More than fifteen years teaching and researching across leading universities.
Loyalty
A steady, dependable mentor committed to students and colleagues for the long term.
Hard Worker
Tireless dedication to research, lecture preparation, and student guidance.
Great Leadership
Guiding research teams and study groups with clarity, vision, and genuine care.
Good Speakers
An engaging lecturer who makes complex quantitative ideas clear and memorable.
Journal
Convergence Rates in Transport
Borjan Geshkovski, Cyril Letrouit, Yury Polyanskiy, and Philippe Rigollet (2023)
Preprint
abcdefg: 123456
Abstract
This paper studies the convergence of gradient-based estimators under optimal transport metrics, establishing sharp rates across a broad class of distributions. We introduce a unified framework, prove minimax-optimal bounds, and validate the theory with numerical experiments showing how sample size, dimension, and regularity govern efficiency.
Minimax Optimality for High-Dimensional Models
Borjan Geshkovski, Cyril Letrouit, Yury Polyanskiy, and Philippe Rigollet (2023)
Closed
abcdefg: 123456
Abstract
We derive minimax lower bounds for estimation in high-dimensional models and propose procedures attaining them up to logarithmic factors. The analysis combines information-theoretic arguments with new concentration inequalities valid when parameters far exceed the sample size, and simulations confirm the predicted scaling.
Algorithms and Complexity of Learning Tasks
Borjan Geshkovski, Cyril Letrouit, Yury Polyanskiy, and Philippe Rigollet (2023)
Info
abcdefg: 123456
Abstract
This work studies the computational complexity of core learning tasks, characterising which admit efficient algorithms and which face hardness barriers. We present new approximation schemes, establish matching lower bounds, and discuss implications for the design of scalable training procedures used in practice.
Optimization Methods for Statistical Learning
Borjan Geshkovski, Cyril Letrouit, Yury Polyanskiy, and Philippe Rigollet (2023)
Preprint
abcdefg: 123456
Abstract
We analyse a family of optimisation methods tailored to statistical learning objectives, proving convergence under realistic assumptions on smoothness and curvature. The study bridges optimisation and estimation theory, showing how algorithmic choices shape speed and model quality across several benchmark datasets.Research
Research Summary
Reliable, reproducible research at the intersection of statistics and learning theory.
My work focuses on optimal transport, minimax optimality, and the optimisation methods that make modern learning models both accurate and trustworthy in real settings.
Interests
Learning
Minimax optimality
Optimal transport
Optimization
Algorithms and complexity
Latest Blogs
Reflections on the hard-won lessons of academic life, the kind of insight that only years of teaching and study can truly reveal over time.
A clear look at how online education is reshaping access to learning, with practical tips for students choosing remote courses today.
Everything prospective applicants should know about current vacancies in our research team, including how to apply and what we look for.
Contact
My Office
795 Folsom Ave, Suite 600San Francisco, CA 94107
Phone: (1) 8547 632521
Fax: (1) 11 4752 1433
Email: info@canvas.com