While LLM/diffusion are extremely popular, we still can find classical topics in the poster session. This paper proposes convexified heterogeneous OT (unlike nonconvex Gromow-Wasserstein). In essence, | E[d(x,X)|y] - E[d(y,Y)|x] | is regarded as the base cost for OT. arxiv.org/abs/2606.02047

I'll arrive at Seoul at Monday noon. Would love to see old friends and connect with new people there!

On Monday @ncollina.bsky.social @iraglobusharris.bsky.social and I are giving a tutorial at ICML on (multi)calibration and its applications. You can find slides and an annotated bibliography on the website: calibration-tutorial.github.io as well as an interactive demo of online calibration algs.

TMLR has been facing an significant uptick in the number of submissions since the start of 2026. This is placing an extreme burden on our amazing team of reviewers & action editors. To ease this burden, TMLR will be implementing submission quotas, effective July 1. 1/n medium.com/@TmlrOrg/ann...

I participated a workshop among ML vs. PL (programming lang) people. For a long time I have zero understanding of CPS transform (en.wikipedia.org/wiki/Continu...), but a PL person told me it's essentially the dual transform from a convex set to a support function (!) Convex analysis everywhere...

It is always fantastic to read old strong papers! I read this by Koltchinskii (30 years ago) today. In this paper, he gave a convex-analytic view of the quantile function (quantile = convex conjugate supremum!), and extend it elegantly to multivariate rvs. projecteuclid.org/journals/ann...

My first PhD student Xianliang worked hard out this: In Muon, polar decomposition should always precede momentum, which significantly improves signal recovery. I'm excited to share this since few theory has been working on the benefit of momentum in Muon! arxiv.org/abs/2606.03899

#AISTATS2026 It was extremely great to first see someone whose paper I have closely read, those with whom I collaborated recently without having met in-person, got invited to a next workshop, etc. Even though the time is quite challenging before the deadline😅, I really enjoyed the conference!

My new policy: if someone asks me to read something, I ask them how they used AI in creating it, and what validation/processing they applied to the AI outputs. (I disclose the same.) Been burned by giving too much attention to (undisclosed) slop folks have sent me...

D'ailleurs, j'ai pu profiter de mon séjour à Paris cette fois-ci pendant l'escale avant d'aller au Maroc. J'ai vu quelques endroits que j'aime là-bas---surtout le Centre de Pompidou, même s'il est en rénovation---aprés 7 ans! Maintenant, c'est le moment de se concentrer intensément sur le travail...

Me: I highly look forward to exploring Morocco🤩 Reality: NeurIPS😅

Half a year ago I got a quotation for a GPU server, and I redid it this month, and noticed that the server price almost doubled🤯

If you meet the eligibility requirements for the LOTUS Program and are interested in working with me, feel free to reach out. www.jst.go.jp/program/indi...

Tomorrow is the very first class of my lecture at ISM (I'm gonna introduce learning theory and convex analysis). It's extremely useful for myself as well to review bunch of facts and proofs, but I need to rush because I've prepared for only half a semester😅

Sad to see more and more people rely on LLMs to generate reviews... (for some reasons, it is very easy to find at a glance; and senior people tend to rely, tho I don't intend to generalize this)

We made this public now: arxiv.org/abs/2603.10452 Hope it inspires OT enthusiasts!

J’ai pris une semaine de congés et bien je suis venu en Azerbaijan. Je ne connaissais présque rien parce que c’est très loin du Japon, mais j’ai trouvé que Baku est très bien organisé avec le mélange entre la vielle ville et des architectures modernes.

J’ai rencontré deux français ce matin au café à Tokyo et après j’ai soudainement parlé avec eux, on a decidé de avoir le dîner la semaine prochaine à Kyoto! Quel chance 😂

Fantastic post by Colin Raffel, "We Are Over-Indexing on Paper Acceptance," drafted in May 2021 (!) but only posted now. The more things change.. Last sentence: "If you want to judge a researcher’s quality, the only meaningful way is to read their papers and judge for yourself."

To all convex analysis freaks: here's new perspective of flow matching🔭 The denoising operator from the corrupted to the target data is indeed a proximal operator of the Brenier potential! This viewpoint leads to Lyapunov analysis: FM identifies target support. arxiv.org/abs/2602.12683

While haven't verified carefully, it is surprising that the swap regret and the calibration error is equivalent, which can be shown with only the basic properties of the Bregman divergence arxiv.org/abs/2505.21460

Franchement j'était désespéré par le résultat des élections législatives au Japon cette fois-ci, mais je ne peux rien y faire parce que je n'ai pas le droit de vote...

Je ne sais pas guider les étudiants pour qu'ils réussissent leurs recherches… C'est bien que je ne fais que mes propres recherches, mais c'est tellement difficile d'amener les étudiants à réussir leur premier projet.

3rd "Mathematics of Data" Summer School is being held in Singapore in June. Applications for attendance (with accommodation for most & no registration fee for all) are open throughout February and possibly longer: ims.nus.edu.sg/events/ma_da...

🚨Muon can smash anisotropy of inputs! Our new work investigates learning dynamics of phase retrieval (f(x)=xᵀMx) on the spiked covariance (I+λvvᵀ), for which spectral GD (≒muon) is less affected by the spike direction v than standard GD. arxiv.org/pdf/2601.22652

(A bit long; nothing special here) I think I’m on the relatively optimistic side to embrace academic writing with LLMs, including survey and math proofs—they enable me to new research which I shall never be able to do alone. As a researcher, it’s so much exciting.

I really wish #OpenAI would stop releasing free stochastic parrots in every community they can think of. They sure look pretty but they are shitting all over the place and you can't have a decent conversation between humans anymore.

Delighted to have our "Brenier isotonic regression" accepted at #AISTATS2026! We extend isotonic regression to *multiclass* setup based on Brenier optimal transport, which can be used for multiclass calibration, improving the calibration map nicely over binning etc.

Excited to see people will organize a workshop on calibration in the upcoming AISTATS calibration-workshop.github.io

Weekend reads: Rudin et al. (2004) "The Dynamics of AdaBoost: Cyclic Behavior and Convergence of Margins" www.jmlr.org/papers/v5/ru... Highly illuminating to demonstrate AdaBoost can yield stable limit cycles under some configurations of weak classifiers, and moreover, this dates back to 2004!

Recently I'm getting more and more unsure about how many research projects I'm actively involved in, and it turns out to be 10 in total after writing down! All of them highly excite me equally but the only thing is the limited time 🤯

The list of accepted papers at the Algorithmic Learning Theory Conference, a.k.a. #ALT2026, is out! h/t @thejonullman.bsky.social (PC chair). algorithmiclearningtheory.org/alt2026/acce... "ALT: topics so hot, it has to be held in Canada in February"

J'ai réussi A2🥳

Openreview opened the door to continuous and major revisions that nobody has time to check properly. I think that we should come back to short one pdf page replies to reviews. It would mean having decisions quicker so that we actually have time to work on papers before resubmitting them.

The next #NeurIPS2025 poster this evening on the interaction between loss functions and gradient descent dynamics: See you soon at Poster No.3007😎

NeurIPS is so exciting as usual that I could have an endless research discussion at bars even after the poster session! Love to see not a few friends are obsessed with math questions yet seeing the light of day

Although I’ll unfortunately miss #NeurIPS2025, our spotlight work on Conv-FY losses will still be there. My excellent collaborator @han-b.bsky.social will be presenting at Exhibit Hall C,D,E, 3001. If you’re on site, feel free to stop by and chat with him!

Convolutional Fenchel-Young loss paper has been updated slightly, with more examples e.g. classification with rejection (with the great effort of @caoyuzhou.bsky.social ). We're gonna present the spotlight poster at #NeurIPS2025, at 4:30pm-7:30pm on Dec 3. See you all soon😎

A simple yet computational efficient approach to online RL: By noting that Q-function can be written with a policy and partition, we can eliminate Z by taking the difference of Q. Thus, all we need is to regress to **difference of Q** (eq. (6)). arxiv.org/abs/2410.04612

In the past few weeks, I learned singular perturbation theory (mainly based on Jones (2006) dalab.unn.ru/SiteGorbanKa...). In short, it studies two-timescale dynamics, where x and y are the "fast" and "slow" variables. Fenichel's theorem ensures the "slow manifold" exists for finitely small eps.

I didn’t notice that this is fully described by Strogatz’ textbook (Chap 9) under the name Lorenz map

Le week-end derniere, je suis allé au Chateau Takeda, qui est populaire pour ses nuages. Même s‘il pleut, on pourrait voir des beaux nuages.

Shiga University has the best campus environment across Japanese universities. This is today’s morning view while walking to the campus from a train station. (Disclaimer: the campus is behind the castle😂)

Yesterday I heard an opinion such that “informatics” is merely a suffix (like bioinformatics) and doesn’t sound like a principled field, which was shocking to me but makes sense to some extent. Why don’t we have a nice name like physics and mathematics…🤯

French speaker bluesky: I have a question on l’informatique. In Japanese, literal translation of computer science is 計算機科学, but it’s not natural, and people use 情報科学/工学 (literally information science/engineering) as department and discipline names. I know French uses l’informatique, which is (1/n)

This paper studies why Adam occasionally causes loss spikes, which is attributed to the edge of stability phenomenon. As seen from the figure, once hitting EOS (see b) a loss spike is triggered. An interesting experimental report! arxiv.org/abs/2506.04805

A nice paper in ICML2025, generalizing the smoothness notion, for which GD convergence is provided. The convergence proof is very transparent: descent lemma + telescoping + estimation of stepsize. arxiv.org/abs/2412.11773

Yesterday I learned from a pharmacologist that an integration of surrogate models and pharmacokinetics (PK) has been emerging. For example this (jpharmsci.org/article/S002... ). I just wonder if we can refine it by PINN-like approach.

Thrilled to share our paper is accepted to #NeurIPS2025 as a Spotlight! 🎉 Big thanks to my awesome collaborators and the program committee. See you in San Diego!