| 2026.6.3 |
Tam Le |
Sobolev IPM with graph metric: Theory and application |
English We study the Sobolev IPM problem for probability measures supported on a graph metric space. Sobolev IPM is an important instance of integral probability metrics (IPM), and is obtained by constraining a critic function within a unit ball defined by the Sobolev norm. In particular, it has been used to compare probability measures and is crucial for several theoretical works in machine learning. However, there are no efficient algorithmic approaches to compute Sobolev IPM effectively, which hinders its practical applications. We establish a relation between Sobolev norm and weighted Lp-norm, and leverage it to propose a novel regularization for Sobolev IPM. By exploiting the graph structure, we demonstrate that the regularized Sobolev IPM provides a closed-form expression for fast computation. This advancement addresses long-standing computational challenges, and paves the way to apply Sobolev IPM for practical applications, even in large-scale settings. Moreover, building on the insights of tree systems, we further introduce tree-sliced Sobolev IPM (TS-Sobolev), a tree-sliced metric that aggregates regularized Sobolev IPMs over random tree systems for applications with probability measures on Euclidean or hyperspheres. Notably, TS-Sobolev admits the tree-sliced Wasserstein as its special case. Empirically, we evaluate the proposed approaches on various tasks, e.g., document classification and topological data analysis for measures with a graph metric; as well as gradient flows, self-supervised learning, generative modeling, and text topic modeling for measures on Euclidean and hyperspheres.
References:
[1] Tam Le*, Truyen Nguyen*, Hideitsu Hino, Kenji Fukumizu. Scalable Sobolev IPM for Probability Measures on a Graph. ICML, 2025. (*: equal contribution)
[2] Viet-Hoang Tran*, Thanh Q. Tran*, Thanh Chu, Duy-Tung Pham, Trung-Khang Tran, Tam Le**, Tan M. Nguyen**. Tree-Sliced Sobolev IPM. ICLR, 2026. (*: equal contribution; **: co-last author) |
Online |
D208 |
| 2026.6.3 |
庄 建倉 |
How predictable are earthquakes? Advances in earthquake forecasting and predictability limits |
English Earthquakes resist deterministic prediction, yet their occurrence is not fully random. This paper develops a unified information-theoretic framework to quantify predictability. By reviewing Shannon entropy and the Kullback--Leibler divergence, we formalize predictability as the entropy gap between complete randomness and the true data-generating process and clarify how this absolute notion relates to the relative skill gains used in prospective model evaluation. Within the point-process setting, we derive entropy rates for the Poisson process and for ETAS and identify the intrinsic predictability rate as an information gain functional of the conditional intensity. Using this lens, we summarize what is currently established about earthquake predictability in time, space, and magnitude: temporal and spatial predictability are dominated by clustering and heterogeneous background rates, while magnitude predictability requires separating marginal magnitude statistics (e.g., Gutenberg--Richter and tapered laws) from genuine inter-event dependence encoded by the multivariate magnitude distribution. Finally, we show how incorporating high-dimensional pre-event observations can increase predictability through mutual information, thereby reframing forecasting progress as the extraction of structured dependence between available information and future seismicity. This perspective provides a coherent basis for assessing predictability limits, comparing models, and identifying where additional information and physics are most likely to yield substantive forecasting improvements. |
Hybrid |
D208 |
| 2026.6.10 |
濵田 ひろか |
データ駆動型アプローチによる研究活動の構造的学際性可視化 |
日本語 学際研究の重要性が国際的に認識される一方,研究活動の分野横断性や異分野融合(学際性)を定量的に把握するための指標は未だ十分に確立されていない.Rao–Stirling指数や REDi(Research Diversity Index)といった学際性評価のための既存指標は,マクロな分野横断的広がりの把握には有用であるが,個別研究間の微細な差異を捉えることは難しく,実務での活用には課題がある.本研究では,こうした課題に対し,論文の意味的情報と共著関係をカーネル法により統合し,ガウス混合モデル(GMM)によって「研究評価単位」を構成したうえで,Bures–Wasserstein距離により研究活動間の非類似度を定義するフレームワークを紹介する.発表では,手法の概要と実データへの適用を通じて得た知見を中心に報告する. |
Hybrid |
D208 |
| 2026.6.10 |
林 慶浩 |
生分解性・生体適合性材料創出に向けたマテリアルズインフォマティクス |
日本語 |
TBD |
D208 |
| 2026.6.17 |
奥野 彰文 |
Algebraic approach to ridge-regularized mean squared error minimization in minimal ReLU neural network |
日本語 プレプリント https://arxiv.org/abs/2508.17783 について講演します. |
Hybrid |
D208 |
| 2026.6.17 |
木野 日織 |
Global attention-based identification of energy-relevant atoms in atomistic models |
日本語 In this study, the limited interpretability of conventional deep learning models for structure–property relationships is addressed by proposing an interpretable model incorporating an attention mechanism. Evaluations on multiple datasets, including molecules and crystals, demonstrate that predictive performance comparable to state-of-the-art methods is achieved. Furthermore, comparisons with first-principles calculations reveal that the importance of local atomic structures, as quantified by attention, is effective for understanding material properties. The proposed approach enables both accurate property prediction and identification of key structural features, contributing to accelerated materials design. https://doi.org/10.1038/s41524-023-01163-9 |
Hybrid |
D208 |
| 2026.6.24 |
南 和宏 |
プライバシー保護技術の体系的評価 |
日本語 |
Online |
D313-4 |
| 2026.6.24 |
― |
― |
― |
― |
― |
| 2026.7.8 |
― |
― |
― |
― |
― |
| 2026.7.8 |
前田 忠彦 |
いくつかの社会調査プロジェクトからの話題 |
日本語 |
Online |
D208 |
| 2026.7.15 |
二宮 嘉行 |
混合効果モデルにおけるスパース正則化法と条件付き AIC |
日本語 |
Hybrid |
D208 |
| 2026.7.15 |
吉田 淳一郎 |
機械学習を含む特異モデルに対するLAN理論の拡張とデータ駆動型検定法の開発 |
日本語 パラメータ推定において、「真のパラメータが唯一つに定まらない」という識別不能性を有するモデルは特異モデルと呼ばれ、有限混合モデルや機械学習など多くの現代的統計モデルが該当する。特異モデルでは、従来の局所漸近正規性(LAN)理論が破綻し、最尤推定量や尤度比検定統計量の漸近挙動が複雑化するため、その不確実性を明示的に捉えることは一般には難しい。そこで本講演では、特異モデルに適用可能な局所漸近理論を構築し、その応用として、特異モデル下での推定量の推定誤差評価や仮説検定を可能とする、データ駆動型アルゴリズムを提案する。 |
Hybrid |
D208 |
| 2026.7.22 |
岡﨑 彰良 |
回帰問題における事前分布推定に関する話題 |
日本語 |
TBD |
D208 |
| 2026.7.22 |
赤穂 昭太郎 |
ガウス過程の情報幾何 |
日本語 ガウス過程に対する情報幾何学的枠組みを提案する.無限次元性に起因して KL ダイバージェンスが発散してしまう問題点を,入力点に依存しない平均 KL ダイバージェンスにより回避し,さらに拡張ガウス過程を導入することで双対平坦構造を与える.GP 空間はその中の m-flat 部分多様体として記述される.応用として,e-射影に基づく転移学習の定式化と計算アルゴリズムについて紹介する. |
Hybrid |
D208 |
| 2026.7.29 |
鎌谷 研吾 |
MCMC Diagnostics |
日本語 |
Hybrid |
D208 |
| 2026.7.29 |
LEE Ching-pei |
Revisiting superlinear convergence of proximal Newton-like methods to degenerate solutions |
English We describe inexact proximal Newton-like methods for solving degenerate regularized optimization problems and for the broader problem of finding a zero of a generalized equation that is the sum of a continuous map and a maximal monotone operator. Superlinear convergence for both the distance to the solution set and a certain measure of first-order optimality can be achieved under a Hölderian error bound condition, including for problems in which the continuous map is nonmonotone, with Jacobian singular at the solution and not Lipschitz. Superlinear convergence is attainable even when the Jacobian is merely uniformly continuous, relaxing the standard Lipschitz assumption to its theoretical limit. For convex regularized optimization problems, we introduce a novel globalization strategy that ensures strict objective decrease and avoids the Maratos effect, attaining local Q-superlinear convergence without prior knowledge of problem parameters. Unit step size acceptance in our line search strategy does not rely on continuity or even existence of the Hessian of the smooth term in the objective, making the framework compatible with other potential candidates for superlinearly convergent updates.
This is joint work with Stephen J. Wright. |
Hybrid |
D208 |