Leonard Wong

Associate Professor @UofTStatSci and @UTSC. I work on mathematical finance, probability, optimal transport, information geometry, and their applications.

[Leonard Wong @wongtkleonard]

This paper has been accepted at Calculus of Variations and Partial Differential Equations.

[Leonard Wong @wongtkleonard]

New paper on the JKO scheme with Cale Rankin:

https://t.co/yASVehuTus

We prove convergence of JKO schemes with general transport costs. They are particularly useful when the Riemannian Wasserstein distance is computationally intractable but a suitable cost is.

[理化学研究所（理研） @RIKEN_JP]

今日のAIの基礎となる人工ニューラルネットワークや機械学習、情報幾何学の分野での先駆的研究が高く評価され、2025年の京都賞（先端技術部門）を受賞した ＃⽢利俊⼀ 栄誉研究員。脳科学分野の発展に多大なる貢献を果たしてきたその歩みをたどります。
#クローズアップRIKEN
https://t.co/7uxKrkg7om

[Leonard Wong @wongtkleonard]

New paper with Steven Campbell who was my PhD student at U of T. The excess growth rate is a fundamental logarithmic functional in portfolio theory. We connect it with various information-theoretic concepts and provide three axiomatic characterization theorems!

[arXiv math.IT Information Theory @mathITbot]

Campbell, Wong: A mathematical study of the excess growth rate https://t.co/CoIN5IuMCx https://t.co/VQVPkXzb4o https://t.co/MtJYtwpINA

[Leonard Wong @wongtkleonard]

Finally, this paper has been published at IEEE Transactions on Information Theory. Very proud of Cale (now at Monash University) and Amanjit who made this happen. We are honoured to dedicate this work to Prof. Amari.

https://t.co/aZBwq9J26f

[Leonard Wong @wongtkleonard]

New version on https://t.co/ZAEbHWNSm8. Couldn't have done it without help from my student Amanjit who joined as a co-author. Includes new implementations with neural OT. Figure shows our primal and dual displacement interpolations w.r.t. "transport KL-geometry" on the simplex.

[Dan Roy @roydanroy]

I've not mentioned it yet on Twitter, but since my department announced it today, I'll do so too. I was promoted to Full Professor 🎉 (effective July 2024, in fact). Those of you who are professors will know how critical mentors and students are to our success, and this is very much the case in my case. I couldn't have asked for a better string of students (and postdocs). They have all found incredible success, and I'm happy to call them colleagues. In fact, one of my postdocs, Thibault Randrianarisoa, has just accepted a tenure track position at UTSC. Congrats, Thibault. In a week, I'm hoping to come back and congratulate yet another student.

[Leonard Wong @wongtkleonard]

Glad to share that this paper has been accepted for publication at the journal Quantitative Finance.

[Leonard Wong @wongtkleonard]

Revised version available on arXiv. Now we use data up to Dec 2024.

[Leonard Wong @wongtkleonard]

Proud to say that my work on the logarithmic divergence is discussed in Prof. Amari’s survey.

[SpringerMath @SpringerMath]

🎖️The 2025 @KyotoPrize Shun-ichi Amari 👏👏👏

🔓Check out Amari's research suvery article "Information geometry" (48 pages) published in 2021 here: https://t.co/uCnrZQ8VUq @springer1842
#DownloadForFree til July 31, 2025 🎉

#JapaneseJournalofMathematics 🏵️#TakagiLectures

[Information Geometry @SN_INGE]

BREAKING NEWS
Congratulations to Professor Shun-ichi Amari!

2025 Kyoto Prize Laureates
https://t.co/4fOpidHtO1

[Information Geometry @SN_INGE]

🏆Good News. The journal Information Geometry has received its first #ImpactFactor of 🌟1.2🌟!
Ranked as
Q1 (84th/483) in SCIE/ESCI mathematics journals worldwide.👏👏👏
👉https://t.co/Ej4fnKJCuB

cf. CiteScore @Scopus 2024: 2.0

Thanks to all our authors, reviewers and editors!

[Leonard Wong @wongtkleonard]

New version on https://t.co/ZAEbHWNSm8. Couldn't have done it without help from my student Amanjit who joined as a co-author. Includes new implementations with neural OT. Figure shows our primal and dual displacement interpolations w.r.t. "transport KL-geometry" on the simplex.

[Leonard Wong @wongtkleonard]

Proud to present my new paper with Cale Rankin @FieldsInstitute
We study the Bregman-Wasserstein divergence - the optimal transport cost where the cost function is a Bregman divergence.

https://t.co/ZAEbHWNSm8

[Leonard Wong @wongtkleonard]

To me this is my real entry point to information geometry

[Frank Nielsen @FrnkNlsn]

Article #OTD 1/2

"Logarithmic divergences from optimal transport and Rényi geometry"

L(±α)-divergences induce geometries are dually projectively flat with constant sectional curvatures

[Leonard Wong @wongtkleonard]

Revised version available on arXiv. Now we use data up to Dec 2024.

[Leonard Wong @wongtkleonard]

Happy to share my new paper on macroscopic properties of the US equity market with Steven Campbell and Qien Song. We study several macroscopic properties such as the capital distribution curve (see figure), market diversity and intrinsic volatility.

https://t.co/w8CcSWVZn5

[Information Geometry @SN_INGE]

Professor Shun-ichi Amari, aged 89, giving a brief but passionate speech after all the presentations of "Open Problems in Information Geometry" at #FDIG2025, on March 21, 2025, The University of Tokyo.

[Leonard Wong @wongtkleonard]

It is an honour to present my work in Japan where many ideas were first developed.

[Information Geometry @SN_INGE]

We had a wonderful time at #FDIG2025!

A message dessert plate has been presented to the chair at #informationgeometry editorial board meeting.

[Leonard Wong @wongtkleonard]

And I’ll be supervising a group project on optimal transport.

[Dan Roy @roydanroy]

Are you a Canadian citizen or PR? 3rd or 4th year in undergrad? Available June 2-13 for a fully funded summer school in statistics?

Learn more and apply here:
https://t.co/zBfdor6DEa

Yours truly will be teaching you some online learning theory.

[Leonard Wong @wongtkleonard]

Recently, Acciaio, Hou, and Pammer extended our method to cover the multivariate case with entropic regularization. Together, we obtained a good understanding of adapted OT between Gaussian processes.

https://t.co/0qGwojmDLo

[Leonard Wong @wongtkleonard]

To appear in Electronic Communications in Probability:

https://t.co/86giYOOepN

[Leonard Wong @wongtkleonard]

New paper with my PhD student Madhu Gunasingam. We derive the adapted (bicausal) 2-Wasserstein distance between Gaussian distributions. It leads to an adapted version of the Bures-Wasserstein distance.

https://t.co/86giYONGAf

[University of Toronto @UofT]

#UofT to increase base funding for PhD students to $40,000 per year 🏫 https://t.co/iMM3xywMxb

[RIKEN Center for Brain Science @RIKEN_CBS]

Comment from Dr. Shun-ichi Amari, RIKEN Honorary Science Advisor, Former Director, RIKEN Brain Science Institute, regarding the 2024 Nobel Prize in Physics
*
https://t.co/7TL82dyZj4
*
#NovelPrizeInPhysics #AI #Neuroscience #riken #rikencbs
@RIKEN_CBS