Han Bao

書き捨てのPoCはLLMが圧倒的に向いている一方で、プロダクト意識する規模だとコードベース全体の一貫性を保つ必要があって、long context にまだ難のあるLLMだとそれが難しいのかなと思ってるんですけど、どうですか（僕は後者をやらないので想像で喋っている）

Haha, even for those in Japan, the current political scene is highly unpredictable😂

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

Prediction of Human Pharmacokinetics From Chemical Structure: Combining Mechanistic Modeling with Machine Learning Pharmacokinetics (PK) is the result of a complex interplay between compound properties and physiology, and a detailed characterization of a molecule's PK during preclinical research is key to understa...

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???

Thank you, and the same to you! It is truly well-deserved to be selected as a spotlight!

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

おめでとうございます！今後とも活躍を楽しみにしています。
(僕もちょうどストロガッツ気になってるとこでした)

2) Metastability of Lorenz attractor
Metastability can even seen in the classical Lorentz system. Here's ρ=23.2. Yorke & Yorke (1979) fit least squares to the so-called "peak return map", and (semi-)analytically derived the transient time.

link.springer.com/content/pdf/...

Recently, Otto & Reznikoff (2006) studied the metastability in a general setup. They consider gradient-flow-based systems and demonstrated: if the energy function is δ-Lipschitz and satisfies a variant of KL-type inequality, the system is metastable for t=O(1/δ)!

webdoc.sub.gwdg.de/ebook/serien...

A-C eq. is dynamics based on a reaction-diffusion system. It has a "metastability" phenomenon, i.e., the system state is trapped in an initial condition for a quite long time, which is apparently the stable state, but exhibits a drastic transient behavior at some time. See the first fig.

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...

烏丸より西側は総じて平和ですよ

3) Angkor Wat, of course (in daylight and sunrise each)

2) Kulen Mountain

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!

Abadie-Type Constraint Qualification for Mathematical Programs with Equilibrium Constraints - Journal of Optimization Theory and Applications Mathematical programs with equilibrium constraints (MPEC) are nonlinear programs which do not satisfy any of the common constraint qualifications (CQ). In order to obtain first-order optimality condit...

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 went last year, right before MLSS Okinawa! Indeed it was nearly 30 years after this film, but some filming locations (including the tango bar) still exist. But Hong-Kong must be developing way faster...

I really love this film! Actually this film finally brought me to Argentina 😂

Thanks, I’m gonna keep learning!

ありがとう！試験もの久しぶりでかなり嬉しい