no code implementations • 18 Mar 2024 • Yuto Tanimoto, Kenji Fukumizu
While many multi-armed bandit algorithms assume that rewards for all arms are constant across rounds, this assumption does not hold in many real-world scenarios.
no code implementations • 16 Mar 2024 • Eiki Shimizu, Kenji Fukumizu, Dino Sejdinovic
In conditional density estimation tasks, our NN-CME hybrid achieves competitive performance and often surpasses existing deep learning-based methods.
no code implementations • 29 Feb 2024 • Noboru Isobe, Masanori Koyama, Kohei Hayashi, Kenji Fukumizu
In this paper, we develop the theory of conditional generation based on Flow Matching, a current strong contender of diffusion methods.
no code implementations • 7 Feb 2024 • Tam Le, Truyen Nguyen, Kenji Fukumizu
In connection with the OW, we show that one only needs to simply solve a univariate optimization problem to compute the GST, unlike the complex two-level optimization problem in OW.
1 code implementation • 20 Oct 2023 • Tam Le, Truyen Nguyen, Kenji Fukumizu
It is known that such OT problem (i. e., tree-Wasserstein (TW)) admits a closed-form expression, but depends fundamentally on the underlying tree structure over supports of input measures.
no code implementations • 29 May 2023 • Masanori Koyama, Kenji Fukumizu, Kohei Hayashi, Takeru Miyato
Symmetry learning has proven to be an effective approach for extracting the hidden structure of data, with the concept of equivariance relation playing the central role.
no code implementations • 25 Apr 2023 • Yuri Kinoshita, Kenta Oono, Kenji Fukumizu, Yuichi Yoshida, Shin-ichi Maeda
Variational autoencoders (VAEs) are one of the deep generative models that have experienced enormous success over the past decades.
1 code implementation • 24 Feb 2023 • Tam Le, Truyen Nguyen, Kenji Fukumizu
We show that the proposed unbalanced Sobolev transport (UST) admits a closed-form formula for fast computation, and it is also negative definite.
1 code implementation • NeurIPS 2023 • Shunya Minami, Kenji Fukumizu, Yoshihiro Hayashi, Ryo Yoshida
Supervised transfer learning has received considerable attention due to its potential to boost the predictive power of machine learning in scenarios where data are scarce.
no code implementations • 13 Oct 2022 • Masanori Koyama, Takeru Miyato, Kenji Fukumizu
Recent years have witnessed the effectiveness of contrastive learning in obtaining the representation of dataset that is useful in interpretation and downstream tasks.
1 code implementation • 12 Oct 2022 • Takeru Miyato, Masanori Koyama, Kenji Fukumizu
In this study, we present meta-sequential prediction (MSP), an unsupervised framework to learn the symmetry from the time sequence of length at least three.
1 code implementation • 3 Jun 2022 • Siddharth Vishwanath, Bharath K. Sriperumbudur, Kenji Fukumizu, Satoshi Kuriki
The distance function to a compact set plays a crucial role in the paradigm of topological data analysis.
no code implementations • 29 Mar 2022 • Shoji Toyota, Kenji Fukumizu
Invariance Learning (IL) has been developed recently to overcome this shortcoming; using training data in many domains, IL estimates such a predictor that is invariant to a change of domain.
no code implementations • 21 Feb 2022 • Hironori Murase, Kenji Fukumizu
In this paper, we propose an Anomalous Latent variable Generative Adversarial Network (ALGAN) in which the GAN generator produces pseudo-anomalous data as well as fake-normal data, whereas the discriminator is trained to distinguish between normal and pseudo-anomalous data.
no code implementations • 11 Oct 2021 • Pengzhou Wu, Kenji Fukumizu
As an important problem in causal inference, we discuss the identification and estimation of treatment effects (TEs) under limited overlap; that is, when subjects with certain features belong to a single treatment group.
no code implementations • 30 Sep 2021 • Pengzhou Wu, Kenji Fukumizu
As an important problem in causal inference, we discuss the estimation of treatment effects (TEs).
no code implementations • 29 Sep 2021 • Hiroaki Mikami, Kenji Fukumizu, Shogo Murai, Shuji Suzuki, Yuta Kikuchi, Taiji Suzuki, Shin-ichi Maeda, Kohei Hayashi
Synthetic-to-real transfer learning is a framework in which a synthetically generated dataset is used to pre-train a model to improve its performance on real vision tasks.
no code implementations • ICLR 2022 • Pengzhou Abel Wu, Kenji Fukumizu
We use a latent variable to model a prognostic score which is widely used in biostatistics and sufficient for TEs; i. e., we build a generative prognostic model.
1 code implementation • 25 Aug 2021 • Hiroaki Mikami, Kenji Fukumizu, Shogo Murai, Shuji Suzuki, Yuta Kikuchi, Taiji Suzuki, Shin-ichi Maeda, Kohei Hayashi
Synthetic-to-real transfer learning is a framework in which a synthetically generated dataset is used to pre-train a model to improve its performance on real vision tasks.
no code implementations • NeurIPS 2021 • Pengzhou Abel Wu, Kenji Fukumizu
As an important problem of causal inference, we discuss the identification and estimation of treatment effects (TEs) under weak overlap, i. e., subjects with certain features all belong to a single treatment group.
no code implementations • 17 Jan 2021 • Pengzhou Wu, Kenji Fukumizu
As an important problem of causal inference, we discuss the identification and estimation of treatment effects under unobserved confounding.
no code implementations • 4 Nov 2020 • Masaaki Imaizumi, Kenji Fukumizu
We develop a minimax rate analysis to describe the reason that deep neural networks (DNNs) perform better than other standard methods.
no code implementations • 6 Jul 2020 • Jean-Francois Ton, Dino Sejdinovic, Kenji Fukumizu
Based on recent developments in meta learning as well as in causal inference, we introduce a novel generative model that allows distinguishing cause and effect in the small data setting.
no code implementations • 23 Jun 2020 • Shunya Minami, Song Liu, Stephen Wu, Kenji Fukumizu, Ryo Yoshida
We propose a novel framework that unifies and extends existing methods of transfer learning (TL) for regression.
1 code implementation • NeurIPS 2020 • Siddharth Vishwanath, Kenji Fukumizu, Satoshi Kuriki, Bharath Sriperumbudur
Persistent homology has become an important tool for extracting geometric and topological features from data, whose multi-scale features are summarized in a persistence diagram.
no code implementations • ICLR Workshop DeepDiffEq 2019 • Casey Chu, Kentaro Minami, Kenji Fukumizu
We formalize an equivalence between two popular methods for Bayesian inference: Stein variational gradient descent (SVGD) and black-box variational inference (BBVI).
no code implementations • ICLR 2020 • Casey Chu, Kentaro Minami, Kenji Fukumizu
Generative adversarial networks, or GANs, commonly display unstable behavior during training.
no code implementations • 7 Jan 2020 • Pengzhou, Wu, Kenji Fukumizu
We address the problem of distinguishing cause from effect in bivariate setting.
2 code implementations • ECCV 2020 • Yuki Saito, Takuma Nakamura, Hirotaka Hachiya, Kenji Fukumizu
Matching two different sets of items, called heterogeneous set-to-set matching problem, has recently received attention as a promising problem.
1 code implementation • 1 Jul 2019 • Heishiro Kanagawa, Wittawat Jitkrittum, Lester Mackey, Kenji Fukumizu, Arthur Gretton
We propose a kernel-based nonparametric test of relative goodness of fit, where the goal is to compare two models, both of which may have unobserved latent variables, such that the marginal distribution of the observed variables is intractable.
no code implementations • NeurIPS 2019 • Kenji Fukumizu, Shoichiro Yamaguchi, Yoh-ichi Mototake, Mirai Tanaka
We theoretically study the landscape of the training error for neural networks in overparameterized cases.
1 code implementation • 5 Mar 2019 • Daniel Andrade, Kenji Fukumizu, Yuzuru Okajima
Clustering, like covariate selection for classification, is an important step to compress and interpret the data.
2 code implementations • NeurIPS 2019 • Tam Le, Makoto Yamada, Kenji Fukumizu, Marco Cuturi
Optimal transport (\OT) theory defines a powerful set of tools to compare probability distributions.
no code implementations • 27 Sep 2018 • Masaaki Imaizumi, Kenji Fukumizu
This paper focuses the situation where the target probability measure satisfies the disconnected support property, which means a separate support of a probability, and relates it with the advantage of GANs.
no code implementations • EMNLP 2018 • Sho Yokoi, Sosuke Kobayashi, Kenji Fukumizu, Jun Suzuki, Kentaro Inui
As well as deriving PMI from mutual information, we derive this new measure from the Hilbert--Schmidt independence criterion (HSIC); thus, we call the new measure the pointwise HSIC (PHSIC).
1 code implementation • 15 Jun 2018 • Daniel Andrade, Akiko Takeda, Kenji Fukumizu
Even more severe, small insignificant partial correlations due to noise can dramatically change the clustering result when evaluating for example with the Bayesian Information Criteria (BIC).
1 code implementation • NeurIPS 2018 • Ho Chung Leon Law, Dino Sejdinovic, Ewan Cameron, Tim CD Lucas, Seth Flaxman, Katherine Battle, Kenji Fukumizu
While a typical supervised learning framework assumes that the inputs and the outputs are measured at the same levels of granularity, many applications, including global mapping of disease, only have access to outputs at a much coarser level than that of the inputs.
no code implementations • ICML 2018 • Takafumi Kajihara, Motonobu Kanagawa, Keisuke Yamazaki, Kenji Fukumizu
We propose a novel approach to parameter estimation for simulator-based statistical models with intractable likelihood.
no code implementations • ICLR 2019 • Makoto Yamada, Denny Wu, Yao-Hung Hubert Tsai, Ichiro Takeuchi, Ruslan Salakhutdinov, Kenji Fukumizu
In the paper, we propose a post selection inference (PSI) framework for divergence measure, which can select a set of statistically significant features that discriminate two distributions.
no code implementations • 15 Feb 2018 • Yao-Hung Hubert Tsai, Makoto Yamada, Denny Wu, Ruslan Salakhutdinov, Ichiro Takeuchi, Kenji Fukumizu
"Which Generative Adversarial Networks (GANs) generates the most plausible images?"
no code implementations • 13 Feb 2018 • Masaaki Imaizumi, Kenji Fukumizu
We theoretically discuss why deep neural networks (DNNs) performs better than other models in some cases by investigating statistical properties of DNNs for non-smooth functions.
1 code implementation • 1 Sep 2017 • Motonobu Kanagawa, Bharath K. Sriperumbudur, Kenji Fukumizu
This paper presents a convergence analysis of kernel-based quadrature rules in misspecified settings, focusing on deterministic quadrature in Sobolev spaces.
1 code implementation • 12 Jun 2017 • Genki Kusano, Kenji Fukumizu, Yasuaki Hiraoka
Topological data analysis is an emerging mathematical concept for characterizing shapes in multi-scale data.
Ranked #4 on Graph Classification on NEURON-MULTI
4 code implementations • NeurIPS 2017 • Wittawat Jitkrittum, Wenkai Xu, Zoltan Szabo, Kenji Fukumizu, Arthur Gretton
We propose a novel adaptive test of goodness-of-fit, with computational cost linear in the number of samples.
no code implementations • 9 May 2017 • Md. Ashad Alam, Kenji Fukumizu, Yu-Ping Wang
Many unsupervised kernel methods rely on the estimation of the kernel covariance operator (kernel CO) or kernel cross-covariance operator (kernel CCO).
1 code implementation • NeurIPS 2017 • Song Liu, Akiko Takeda, Taiji Suzuki, Kenji Fukumizu
Density ratio estimation is a vital tool in both machine learning and statistical community.
no code implementations • 6 Jan 2017 • Song Liu, Kenji Fukumizu, Taiji Suzuki
Recent years have seen an increasing popularity of learning the sparse \emph{changes} in Markov Networks.
no code implementations • 12 Oct 2016 • Makoto Yamada, Yuta Umezu, Kenji Fukumizu, Ichiro Takeuchi
We propose a novel kernel based post selection inference (PSI) algorithm, which can not only handle non-linearity in data but also structured output such as multi-dimensional and multi-label outputs.
no code implementations • 31 May 2016 • Krikamol Muandet, Kenji Fukumizu, Bharath Sriperumbudur, Bernhard Schölkopf
Next, we discuss the Hilbert space embedding for conditional distributions, give theoretical insights, and review some applications.
no code implementations • NeurIPS 2016 • Motonobu Kanagawa, Bharath K. Sriperumbudur, Kenji Fukumizu
Kernel-based quadrature rules are becoming important in machine learning and statistics, as they achieve super-$\sqrt{n}$ convergence rates in numerical integration, and thus provide alternatives to Monte Carlo integration in challenging settings where integrands are expensive to evaluate or where integrands are high dimensional.
no code implementations • 17 Feb 2016 • Md. Ashad Alam, Kenji Fukumizu, Yu-Ping Wang
Finally, we propose a method based on robust kernel CO and robust kernel CCO, called robust kernel CCA, which is designed for contaminated data and less sensitive to noise than classical kernel CCA.
2 code implementations • 8 Jan 2016 • Genki Kusano, Kenji Fukumizu, Yasuaki Hiraoka
Topological data analysis (TDA) is an emerging mathematical concept for characterizing shapes in complex data.
Algebraic Topology
no code implementations • 9 Jun 2015 • Song Liu, Kenji Fukumizu
Transfer learning assumes classifiers of similar tasks share certain parameter structures.
no code implementations • 2 Apr 2015 • Song Liu, Taiji Suzuki, Masashi Sugiyama, Kenji Fukumizu
We learn the structure of a Markov Network between two groups of random variables from joint observations.
no code implementations • 27 Jan 2015 • Bernhard Schölkopf, Krikamol Muandet, Kenji Fukumizu, Jonas Peters
We describe a method to perform functional operations on probability distributions of random variables.
no code implementations • 18 Sep 2014 • Yu Nishiyama, Motonobu Kanagawa, Arthur Gretton, Kenji Fukumizu
Our contribution in this paper is to introduce a novel approach, termed the {\em model-based kernel sum rule} (Mb-KSR), to combine a probabilistic model and kernel Bayesian inference.
no code implementations • 25 Aug 2014 • Somayeh Danafar, Kenji Fukumizu, Faustino Gomez
This paper introduces Kernel-based Information Criterion (KIC) for model selection in regression analysis.
no code implementations • 2 Jul 2014 • Song Liu, Taiji Suzuki, Raissa Relator, Jun Sese, Masashi Sugiyama, Kenji Fukumizu
We study the problem of learning sparse structure changes between two Markov networks $P$ and $Q$.
no code implementations • 21 May 2014 • Krikamol Muandet, Bharath Sriperumbudur, Kenji Fukumizu, Arthur Gretton, Bernhard Schölkopf
A mean function in a reproducing kernel Hilbert space (RKHS), or a kernel mean, is central to kernel methods in that it is used by many classical algorithms such as kernel principal component analysis, and it also forms the core inference step of modern kernel methods that rely on embedding probability distributions in RKHSs.
no code implementations • 28 Mar 2014 • Yu Nishiyama, Kenji Fukumizu
If $P, Q$, and kernel $k$ are Gaussians, then computation (i) and (ii) results in Gaussian pdfs that is tractable.
no code implementations • 17 Dec 2013 • Motonobu Kanagawa, Yu Nishiyama, Arthur Gretton, Kenji Fukumizu
In particular, the sampling and resampling procedures are novel in being expressed using kernel mean embeddings, so we theoretically analyze their behaviors.
1 code implementation • 12 Dec 2013 • Bharath Sriperumbudur, Kenji Fukumizu, Arthur Gretton, Aapo Hyvärinen, Revant Kumar
When $p_0\in\mathcal{P}$, we show that the proposed estimator is consistent, and provide a convergence rate of $n^{-\min\left\{\frac{2}{3},\frac{2\beta+1}{2\beta+2}\right\}}$ in Fisher divergence under the smoothness assumption that $\log p_0\in\mathcal{R}(C^\beta)$ for some $\beta\ge 0$, where $C$ is a certain Hilbert-Schmidt operator on $H$ and $\mathcal{R}(C^\beta)$ denotes the image of $C^\beta$.
no code implementations • 4 Jun 2013 • Krikamol Muandet, Kenji Fukumizu, Bharath Sriperumbudur, Arthur Gretton, Bernhard Schölkopf
A mean function in reproducing kernel Hilbert space, or a kernel mean, is an important part of many applications ranging from kernel principal component analysis to Hilbert-space embedding of distributions.
no code implementations • NeurIPS 2012 • Arthur Gretton, Dino Sejdinovic, Heiko Strathmann, Sivaraman Balakrishnan, Massimiliano Pontil, Kenji Fukumizu, Bharath K. Sriperumbudur
A means of parameter selection for the two-sample test based on the MMD is proposed.
no code implementations • NeurIPS 2012 • Kenji Fukumizu, Chenlei Leng
We propose a novel kernel approach to dimension reduction for supervised learning: feature extraction and variable selection; the former constructs a small number of features from predictors, and the latter finds a subset of predictors.
no code implementations • NeurIPS 2012 • Krikamol Muandet, Kenji Fukumizu, Francesco Dinuzzo, Bernhard Schölkopf
This paper presents a kernel-based discriminative learning framework on probability measures.
no code implementations • 25 Jul 2012 • Dino Sejdinovic, Bharath Sriperumbudur, Arthur Gretton, Kenji Fukumizu
We provide a unifying framework linking two classes of statistics used in two-sample and independence testing: on the one hand, the energy distances and distance covariances from the statistics literature; on the other, maximum mean discrepancies (MMD), that is, distances between embeddings of distributions to reproducing kernel Hilbert spaces (RKHS), as established in machine learning.
no code implementations • NeurIPS 2011 • Kenji Fukumizu, Le Song, Arthur Gretton
A nonparametric kernel-based method for realizing Bayes' rule is proposed, based on kernel representations of probabilities in reproducing kernel Hilbert spaces.
no code implementations • NeurIPS 2011 • Kenji Fukumizu, Gert R. Lanckriet, Bharath K. Sriperumbudur
The goal of this paper is to investigate the advantages and disadvantages of learning in Banach spaces over Hilbert spaces.
no code implementations • NeurIPS 2009 • Arthur Gretton, Kenji Fukumizu, Zaïd Harchaoui, Bharath K. Sriperumbudur
A kernel embedding of probability distributions into reproducing kernel Hilbert spaces (RKHS) has recently been proposed, which allows the comparison of two probability measures P and Q based on the distance between their respective embeddings: for a sufficiently rich RKHS, this distance is zero if and only if P and Q coincide.
no code implementations • NeurIPS 2009 • Yusuke Watanabe, Kenji Fukumizu
We also propose a new approach to the uniqueness of LBP fixed point, and show various conditions of uniqueness.
no code implementations • 30 Jul 2009 • Bharath K. Sriperumbudur, Arthur Gretton, Kenji Fukumizu, Bernhard Schölkopf, Gert R. G. Lanckriet
First, we consider the question of determining the conditions on the kernel $k$ for which $\gamma_k$ is a metric: such $k$ are denoted {\em characteristic kernels}.
no code implementations • 18 Jan 2009 • Bharath K. Sriperumbudur, Kenji Fukumizu, Arthur Gretton, Bernhard Schölkopf, Gert R. G. Lanckriet
First, to understand the relation between IPMs and $\phi$-divergences, the necessary and sufficient conditions under which these classes intersect are derived: the total variation distance is shown to be the only non-trivial $\phi$-divergence that is also an IPM.
Information Theory Information Theory
no code implementations • NeurIPS 2008 • Kenji Fukumizu, Arthur Gretton, Bernhard Schölkopf, Bharath K. Sriperumbudur
Embeddings of random variables in reproducing kernel Hilbert spaces (RKHSs) may be used to conduct statistical inference based on higher order moments.