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!

Why don't we implement ACL Findings type publication models to the ML venues? I don't see any outstanding reason to be reluctant. I know borderline papers sometimes do not provide "surprising" insights, but this ought to be judged by the test of time.

This is the metareview

This is not OK. I don't submit often to NeurIPS, but I reviewed papers for this conference almost every year. As a reviewer, why would I spend time trying to give a fair opinion on papers if it's what happens in the end???

Je suis tellement content que mon papier est accepté à JMLR après plus d’un an! C’était très long…

In this weekend I attended a workshop among mathematicians, where I was discussing dynamical systems. During the workshop, there are numerous novel insights to me, which I want to briefly share. 1) metastability in Allen-Cahn equation (fig based on people.maths.ox.ac.uk/trefethen/pd...)

Today's my favorites: "Clustering with Bregman Divergences: an Asymptotic Analysis" (Liu & Belkin, 2016) proceedings.neurips.cc/paper_files/... It's concerned with the limiting distribution of k-means (or Bregman) centroids (w/ n, k -> \infty). This is an escort distribution! (maybe overlooked)

Today I learned that the continuous-time limit of Nesterov's accelerated gradient is Bessel's differential equation, which can be solved analytically. That's unexpectedly a beautiful result to me... web.stanford.edu/~boyd/papers...

I was on a three-day vacation in Siem Reap 🇰🇭 Here are a few views of my favorites: 1) Baphuon

I participated in Deep Learning Theory Workshop 2025 held in RIKEN AIP. I enjoyed lively discussions among the participants. delta-workshop.github.io/deep-learnin...

I thought IIIT Hyderabad and IIIT Delhi are branches of IIIT (not IIT to make sure!), but it turns out to be that the first I are different!

I'm recently learning MPEC (mathematical programming with equilibrium constraints), which is basically a bilevel programming. Since MPEC is known to violate LICQ (I didn't realize it before), it's much harder. Interestingly, MPEC-ver of LICQ etc. is known instead. link.springer.com/article/10.1...

AISTATS 2026 will be in Morocco!

I’m so glad to get passed French DELF A1! (Still need to train my listening skill quite a lot 🫠)

NeurIPS satellite and EurIPS are interesting experiments and potentially mitigate visa issues and environmental concerns for sure. Nevertheless, Asian local communities are oftentimes not associated well with the "global" academic community. I feel our geographic location remains to be an obstacle.

The unsustainability of long distance flights to conferences is a valid concern. Clearly, meeting international experts is important for high-level research, but dynamic regional events to supplement huge monolithic conferences might even make that easier. We need more experiments like EurIPS asap.

Je suis arrivé à Lyon le jour de 125e anniversaire de Saint-Ex!

Sunset view at ISM this evening

Recently I get to recognize there are at least three kinda independent streams in research on large stepsize GD: (1) edge of stability (e.g. openreview.net/pdf?id=jh-rT...), (2) silver stepsize (e.g. arxiv.org/abs/2309.07879), (3) minima stability (e.g. proceedings.neurips.cc/paper/2021/f...)

J'ai fini mon premier examen de français (après un an d'études). Pas sûr de le passer mais je l'espère.

Finally got my office at ISM! (the name correspondence does not look great tho 😂 Han is my first name corresponding to 含 in Kanji)

Today I met a political scientist who is familiar with Wasserstein distance, which was quite amazing...

On this Friday, Yutong@Illinois Tech will visit ISM and give a talk on the recent advances in multiclass classification theory, including implicit bias and the connections to SVM, ranking, noisy labels. Please check it out (you can view it online). www.ism.ac.jp/events/2025/...

Folks, here's our latest work on convolutional Fenchel-Young losses! We show convex smooth losses can have a linear surrogate regret bound on discrete losses (e.g. 01 loss, Prec@k), and it's relies on inf-conv, which is the most beautiful proof I saw ever. arxiv.org/abs/2505.09432

I’m highly delighted that finally I can attend AISTATS in person (I had AISTATS papers during online years only so far😂). The community size remains to be quite reasonable and people are enthusiastic even after the poster session! (Someone stopped me for asking about our poster)

pretty unexpected rejection... c'est la vie😵‍💫

I’ve finished almost all of research talks in Singapore during the long long one week! Here’s the Hive, a very cool architecture by the Heatherwick Studio. Finally I encountered this after finishing the talk at NTU 😊

#ICLR2025 We are going to present it this evening. If you are interested in any of contrastive representation learning, predictive coding, learning dynamics, come by at #608!

I feel like briefly mentioning my favorite paper a day in ICLR. [Day 1] The two-layer ReLU nonconvex objective can be elegantly reformulated into a convex objective. Therein we can invoke convex analysis to characterize the phase transition of mode connectivity. openreview.net/forum?id=4xW...

I'm glad to be chosen as a recipient of AISTATS2025 Best Reviewer Award🥳🥳🥳 Among ML confs, I quite love the atmosphere of AISTATS. (Although this year I'm going to attend AISTATS in person for the first time🤣) aistats.org/aistats2025/...

A new entmax-based SSL, E2MC (will appear in AISTATS25): arxiv.org/abs/2411.15931 They argued in intro > By maximizing the amount of information retained, one hopes to prepare as well as possible for future which I agree partially yet then why we need compression at all? (my everytime question🤯)

Je vais à singapour la semaine prochaine pour assister à ICLR 🇸🇬 1) TAID openreview.net/forum?id=cqs... : distillation pour modèle de langage 2) PhiNets openreview.net/forum?id=5tj... : representation learning basé sur modèle d'hippocampe