Search Results for author: Masaaki Imaizumi

Found 33 papers, 5 papers with code

Bayesian Analysis for Over-parameterized Linear Model without Sparsity

no code implementations25 May 2023 Tomoya Wakayama, Masaaki Imaizumi

In high-dimensional Bayesian statistics, several methods have been developed, including many prior distributions that lead to the sparsity of estimated parameters.

Asymptotically Minimax Optimal Fixed-Budget Best Arm Identification for Expected Simple Regret Minimization

no code implementations6 Feb 2023 Masahiro Kato, Masaaki Imaizumi, Takuya Ishihara, Toru Kitagawa

This result contrasts with the results of Bubeck et al. (2011), which shows that drawing each treatment arm with an equal ratio is minimax optimal in a bounded outcome setting.

Adversarially Slicing Generative Networks: Discriminator Slices Feature for One-Dimensional Optimal Transport

no code implementations30 Jan 2023 Yuhta Takida, Masaaki Imaizumi, Chieh-Hsin Lai, Toshimitsu Uesaka, Naoki Murata, Yuki Mitsufuji

Generative adversarial networks (GANs) learn a target probability distribution by optimizing a generator and a discriminator with minimax objectives.

Best Arm Identification with Contextual Information under a Small Gap

no code implementations15 Sep 2022 Masahiro Kato, Masaaki Imaizumi, Takuya Ishihara, Toru Kitagawa

We then develop the ``Random Sampling (RS)-Augmented Inverse Probability weighting (AIPW) strategy,'' which is asymptotically optimal in the sense that the probability of misidentification under the strategy matches the lower bound when the budget goes to infinity in the small-gap regime.

Benign Overfitting in Time Series Linear Model with Over-Parameterization

no code implementations18 Apr 2022 Shogo Nakakita, Masaaki Imaizumi

Then, we derive bounds of risks by the estimator for the cases where the temporal correlation of each coordinate of dependent data is homogeneous and heterogeneous, respectively.

Time Series Analysis

Benign-Overfitting in Conditional Average Treatment Effect Prediction with Linear Regression

no code implementations10 Feb 2022 Masahiro Kato, Masaaki Imaizumi

We study the benign overfitting theory in the prediction of the conditional average treatment effect (CATE), with linear regression models.

Causal Inference regression

Unified Perspective on Probability Divergence via Maximum Likelihood Density Ratio Estimation: Bridging KL-Divergence and Integral Probability Metrics

no code implementations31 Jan 2022 Masahiro Kato, Masaaki Imaizumi, Kentaro Minami

This paper provides a unified perspective for the Kullback-Leibler (KL)-divergence and the integral probability metrics (IPMs) from the perspective of maximum likelihood density-ratio estimation (DRE).

Density Ratio Estimation

Optimal Best Arm Identification in Two-Armed Bandits with a Fixed Budget under a Small Gap

no code implementations12 Jan 2022 Masahiro Kato, Kaito Ariu, Masaaki Imaizumi, Masahiro Nomura, Chao Qin

We show that a strategy following the Neyman allocation rule (Neyman, 1934) is asymptotically optimal when the gap between the expected rewards is small.

Causal Inference

On generalization bounds for deep networks based on loss surface implicit regularization

1 code implementation12 Jan 2022 Masaaki Imaizumi, Johannes Schmidt-Hieber

We argue that under reasonable assumptions, the local geometry forces SGD to stay close to a low dimensional subspace and that this induces another form of implicit regularization and results in tighter bounds on the generalization error for deep neural networks.

Generalization Bounds Learning Theory

Minimax Analysis for Inverse Risk in Nonparametric Planer Invertible Regression

no code implementations1 Dec 2021 Akifumi Okuno, Masaaki Imaizumi

The derived minimax rate corresponds to that of the non-invertible bi-Lipschitz function, which rejects the expectation of whether invertibility improves the minimax rate, similar to other shape constraints.

Econometrics regression

Exponential escape efficiency of SGD from sharp minima in non-stationary regime

1 code implementation7 Nov 2021 Hikaru Ibayashi, Masaaki Imaizumi

An "escape efficiency" has been an attractive notion to tackle this question, which measures how SGD efficiently escapes from sharp minima with potentially low generalization performance.

Learning Causal Models from Conditional Moment Restrictions by Importance Weighting

no code implementations3 Aug 2021 Masahiro Kato, Masaaki Imaizumi, Kenichiro McAlinn, Haruo Kakehi, Shota Yasui

To address this issue, we propose a method that transforms conditional moment restrictions to unconditional moment restrictions through importance weighting, using a conditional density ratio estimator.

Causal Inference

Minimum sharpness: Scale-invariant parameter-robustness of neural networks

1 code implementation23 Jun 2021 Hikaru Ibayashi, Takuo Hamaguchi, Masaaki Imaizumi

Toward achieving robust and defensive neural networks, the robustness against the weight parameters perturbations, i. e., sharpness, attracts attention in recent years (Sun et al., 2020).

Instrument Space Selection for Kernel Maximum Moment Restriction

1 code implementation7 Jun 2021 Rui Zhang, Krikamol Muandet, Bernhard Schölkopf, Masaaki Imaizumi

Kernel maximum moment restriction (KMMR) recently emerges as a popular framework for instrumental variable (IV) based conditional moment restriction (CMR) models with important applications in conditional moment (CM) testing and parameter estimation for IV regression and proximal causal learning.

Asymptotic Risk of Overparameterized Likelihood Models: Double Descent Theory for Deep Neural Networks

no code implementations28 Feb 2021 Ryumei Nakada, Masaaki Imaizumi

We investigate the asymptotic risk of a general class of overparameterized likelihood models, including deep models.

Ensemble Learning regression

Understanding Higher-order Structures in Evolving Graphs: A Simplicial Complex based Kernel Estimation Approach

no code implementations6 Feb 2021 Manohar Kaul, Masaaki Imaizumi

In this paper, we overcome these obstacles by capturing higher-order interactions succinctly as \textit{simplices}, model their neighborhood by face-vectors, and develop a nonparametric kernel estimator for simplices that views the evolving graph from the perspective of a time process (i. e., a sequence of graph snapshots).

Link Prediction

Finite Sample Analysis of Minimax Offline Reinforcement Learning: Completeness, Fast Rates and First-Order Efficiency

no code implementations5 Feb 2021 Masatoshi Uehara, Masaaki Imaizumi, Nan Jiang, Nathan Kallus, Wen Sun, Tengyang Xie

We offer a theoretical characterization of off-policy evaluation (OPE) in reinforcement learning using function approximation for marginal importance weights and $q$-functions when these are estimated using recent minimax methods.

Off-policy evaluation reinforcement-learning

Higher-order Structure Prediction in Evolving Graph Simplicial Complexes

no code implementations1 Jan 2021 Manohar Kaul, Masaaki Imaizumi

In this paper, we overcome these obstacles by capturing higher-order interactions succinctly as simplices, model their neighborhood by face-vectors, and develop a nonparametric kernel estimator for simplices that views the evolving graph from the perspective of a time process (i. e., a sequence of graph snapshots).

Link Prediction

On Gaussian Approximation for M-Estimator

no code implementations31 Dec 2020 Masaaki Imaizumi, Taisuke Otsu

This study develops a non-asymptotic Gaussian approximation theory for distributions of M-estimators, which are defined as maximizers of empirical criterion functions.

Statistics Theory Statistics Theory

Advantage of Deep Neural Networks for Estimating Functions with Singularity on Hypersurfaces

no code implementations4 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.

Instrumental Variable Regression via Kernel Maximum Moment Loss

1 code implementation15 Oct 2020 Rui Zhang, Masaaki Imaizumi, Bernhard Schölkopf, Krikamol Muandet

We investigate a simple objective for nonlinear instrumental variable (IV) regression based on a kernelized conditional moment restriction (CMR) known as a maximum moment restriction (MMR).


Improved Generalization Bounds of Group Invariant / Equivariant Deep Networks via Quotient Feature Spaces

no code implementations15 Oct 2019 Akiyoshi Sannai, Masaaki Imaizumi, Makoto Kawano

To describe the effect of invariance and equivariance on generalization, we develop a notion of a \textit{quotient feature space}, which measures the effect of group actions for the properties.

Generalization Bounds

Improved Generalization Bound of Permutation Invariant Deep Neural Networks

no code implementations25 Sep 2019 Akiyoshi Sannai, Masaaki Imaizumi

Learning problems with data that are invariant to permutations are frequently observed in various applications, for example, point cloud data and graph neural networks.

Adaptive Approximation and Generalization of Deep Neural Network with Intrinsic Dimensionality

no code implementations4 Jul 2019 Ryumei Nakada, Masaaki Imaizumi

In this study, we prove that an intrinsic low dimensionality of covariates is the main factor that determines the performance of deep neural networks (DNNs).

On Random Subsampling of Gaussian Process Regression: A Graphon-Based Analysis

no code implementations28 Jan 2019 Kohei Hayashi, Masaaki Imaizumi, Yuichi Yoshida

In this paper, we study random subsampling of Gaussian process regression, one of the simplest approximation baselines, from a theoretical perspective.


Understanding GANs via Generalization Analysis for Disconnected Support

no code implementations27 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.

Deep Neural Networks Learn Non-Smooth Functions Effectively

no code implementations13 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.

Tensor Decomposition with Smoothness

no code implementations ICML 2017 Masaaki Imaizumi, Kohei Hayashi

Real data tensors are usually high dimensional but their intrinsic information is preserved in low-dimensional space, which motivates to use tensor decompositions such as Tucker decomposition.

Tensor Decomposition

On Tensor Train Rank Minimization: Statistical Efficiency and Scalable Algorithm

no code implementations1 Aug 2017 Masaaki Imaizumi, Takanori Maehara, Kohei Hayashi

Tensor train (TT) decomposition provides a space-efficient representation for higher-order tensors.

Cannot find the paper you are looking for? You can Submit a new open access paper.