Search Results for author: Ichiro Takeuchi

Found 65 papers, 13 papers with code

Exact Statistical Inference for Time Series Similarity using Dynamic Time Warping by Selective Inference

no code implementations14 Feb 2022 Vo Nguyen Le Duy, Ichiro Takeuchi

In this paper, we study statistical inference on the similarity/distance between two time-series under uncertain environment by considering a statistical hypothesis test on the distance obtained from Dynamic Time Warping (DTW) algorithm.

Decision Making Dynamic Time Warping +1

Bayesian Optimization for Distributionally Robust Chance-constrained Problem

no code implementations31 Jan 2022 Yu Inatsu, Shion Takeno, Masayuki Karasuyama, Ichiro Takeuchi

In black-box function optimization, we need to consider not only controllable design variables but also uncontrollable stochastic environment variables.

Continuation Path with Linear Convergence Rate

no code implementations9 Dec 2021 Eugene Ndiaye, Ichiro Takeuchi

Path-following algorithms are frequently used in composite optimization problems where a series of subproblems, with varying regularization hyperparameters, are solved sequentially.

Topic Analysis of Superconductivity Literature by Semantic Non-negative Matrix Factorization

no code implementations1 Dec 2021 Valentin Stanev, Erik Skau, Ichiro Takeuchi, Boian S. Alexandrov

We utilize a recently developed topic modeling method called SeNMFk, extending the standard Non-negative Matrix Factorization (NMF) methods by incorporating the semantic structure of the text, and adding a robust system for determining the number of topics.

Physics in the Machine: Integrating Physical Knowledge in Autonomous Phase-Mapping

no code implementations15 Nov 2021 A. Gilad Kusne, Austin McDannald, Brian DeCost, Corey Oses, Cormac Toher, Stefano Curtarolo, Apurva Mehta, Ichiro Takeuchi

Application of artificial intelligence (AI), and more specifically machine learning, to the physical sciences has expanded significantly over the past decades.

Materials Screening

Exact Statistical Inference for the Wasserstein Distance by Selective Inference

no code implementations29 Sep 2021 Vo Nguyen Le Duy, Ichiro Takeuchi

In this paper, we study statistical inference for the Wasserstein distance, which has attracted much attention and has been applied to various machine learning tasks.

More Powerful Conditional Selective Inference for Generalized Lasso by Parametric Programming

no code implementations11 May 2021 Vo Nguyen Le Duy, Ichiro Takeuchi

The basic concept of conditional SI is to make the inference conditional on the selection event, which enables an exact and valid statistical inference to be conducted even when the hypothesis is selected based on the data.

Model Selection

Conditional Selective Inference for Robust Regression and Outlier Detection using Piecewise-Linear Homotopy Continuation

no code implementations22 Apr 2021 Toshiaki Tsukurimichi, Yu Inatsu, Vo Nguyen Le Duy, Ichiro Takeuchi

In practical data analysis under noisy environment, it is common to first use robust methods to identify outliers, and then to conduct further analysis after removing the outliers.

Outlier Detection

Root-finding Approaches for Computing Conformal Prediction Set

1 code implementation14 Apr 2021 Eugene Ndiaye, Ichiro Takeuchi

Conformal prediction constructs a confidence set for an unobserved response of a feature vector based on previous identically distributed and exchangeable observations of responses and features.

Mapping causal patterns in crystalline solids

no code implementations2 Mar 2021 Chris Nelson, Anna N. Morozovska, Maxim A. Ziatdinov, Eugene A. Eliseev, Xiaohang Zhang, Ichiro Takeuchi, Sergei V. Kalinin

The evolution of the atomic structures of the combinatorial library of Sm-substituted thin film BiFeO3 along the phase transition boundary from the ferroelectric rhombohedral phase to the non-ferroelectric orthorhombic phase is explored using scanning transmission electron microscopy (STEM).

Data Analysis, Statistics and Probability Materials Science

Active learning for distributionally robust level-set estimation

no code implementations8 Feb 2021 Yu Inatsu, Shogo Iwazaki, Ichiro Takeuchi

A natural measure of robustness is the probability that $f(\bm x, \bm w)$ exceeds a given threshold $h$, which is known as the \emph{probability threshold robustness} (PTR) measure in the literature on robust optimization.

Active Learning

Supervised sequential pattern mining of event sequences in sport to identify important patterns of play: an application to rugby union

1 code implementation29 Oct 2020 Rory Bunker, Keisuke Fujii, Hiroyuki Hanada, Ichiro Takeuchi

Given a set of sequences comprised of time-ordered events, sequential pattern mining is useful to identify frequent subsequences from different sequences or within the same sequence.

Sequential Pattern Mining

Quantifying Statistical Significance of Neural Network-based Image Segmentation by Selective Inference

no code implementations5 Oct 2020 Vo Nguyen Le Duy, Shogo Iwazaki, Ichiro Takeuchi

To overcome this difficulty, we introduce a conditional selective inference (SI) framework -- a new statistical inference framework for data-driven hypotheses that has recently received considerable attention -- to compute exact (non-asymptotic) valid p-values for the segmentation results.

Semantic Segmentation Two-sample testing

Mean-Variance Analysis in Bayesian Optimization under Uncertainty

no code implementations17 Sep 2020 Shogo Iwazaki, Yu Inatsu, Ichiro Takeuchi

As an AL problem in such an uncertain environment, we study Mean-Variance Analysis in Bayesian Optimization (MVA-BO) setting.

Active Learning

Bayesian Quadrature Optimization for Probability Threshold Robustness Measure

no code implementations22 Jun 2020 Shogo Iwazaki, Yu Inatsu, Ichiro Takeuchi

In many product development problems, the performance of the product is governed by two types of parameters called design parameter and environmental parameter.

Active Learning

On-the-fly Closed-loop Autonomous Materials Discovery via Bayesian Active Learning

no code implementations11 Jun 2020 A. Gilad Kusne, Heshan Yu, Changming Wu, Huairuo Zhang, Jason Hattrick-Simpers, Brian DeCost, Suchismita Sarker, Corey Oses, Cormac Toher, Stefano Curtarolo, Albert V. Davydov, Ritesh Agarwal, Leonid A. Bendersky, Mo Li, Apurva Mehta, Ichiro Takeuchi

Active learning - the field of machine learning (ML) dedicated to optimal experiment design, has played a part in science as far back as the 18th century when Laplace used it to guide his discovery of celestial mechanics [1].

Active Learning

Parametric Programming Approach for More Powerful and General Lasso Selective Inference

2 code implementations21 Apr 2020 Vo Nguyen Le Duy, Ichiro Takeuchi

Unfortunately, the main limitation of the original SI approach for Lasso is that the inference is conducted not only conditional on the selected features but also on their signs -- this leads to loss of power because of over-conditioning.

feature selection

CRYSPNet: Crystal Structure Predictions via Neural Network

1 code implementation31 Mar 2020 Haotong Liang, Valentin Stanev, A. Gilad Kusne, Ichiro Takeuchi

Structure is the most basic and important property of crystalline solids; it determines directly or indirectly most materials characteristics.

Computing Valid p-value for Optimal Changepoint by Selective Inference using Dynamic Programming

2 code implementations NeurIPS 2020 Vo Nguyen Le Duy, Hiroki Toda, Ryota Sugiyama, Ichiro Takeuchi

In this paper, we introduce a novel method to perform statistical inference on the significance of the CPs, estimated by a Dynamic Programming (DP)-based optimal CP detection algorithm.

Causal analysis of competing atomistic mechanisms in ferroelectric materials from high-resolution Scanning Transmission Electron Microscopy data

no code implementations11 Feb 2020 Maxim Ziatdinov, Chris Nelson, Xiaohang Zhang, Rama Vasudevan, Eugene Eliseev, Anna N. Morozovska, Ichiro Takeuchi, Sergei V. Kalinin

Machine learning has emerged as a powerful tool for the analysis of mesoscopic and atomically resolved images and spectroscopy in electron and scanning probe microscopy, with the applications ranging from feature extraction to information compression and elucidation of relevant order parameters to inversion of imaging data to reconstruct structural models.

Materials Science

Distance Metric Learning for Graph Structured Data

2 code implementations3 Feb 2020 Tomoki Yoshida, Ichiro Takeuchi, Masayuki Karasuyama

Hence, we propose a supervised distance metric learning method for the graph classification problem.

General Classification Graph Classification +1

Bayesian Active Learning for Structured Output Design

no code implementations9 Nov 2019 Kota Matsui, Shunya Kusakawa, Keisuke Ando, Kentaro Kutsukake, Toru Ujihara, Ichiro Takeuchi

In this paper, we propose an active learning method for an inverse problem that aims to find an input that achieves a desired structured-output.

Active Learning

Bayesian Experimental Design for Finding Reliable Level Set under Input Uncertainty

no code implementations26 Oct 2019 Shogo Iwazaki, Yu Inatsu, Ichiro Takeuchi

In the manufacturing industry, it is often necessary to repeat expensive operational testing of machine in order to identify the range of input conditions under which the machine operates properly.

Active Learning Experimental Design

Computing Full Conformal Prediction Set with Approximate Homotopy

1 code implementation NeurIPS 2019 Eugene Ndiaye, Ichiro Takeuchi

If you are predicting the label $y$ of a new object with $\hat y$, how confident are you that $y = \hat y$?

Active learning for level set estimation under cost-dependent input uncertainty

no code implementations13 Sep 2019 Yu Inatsu, Masayuki Karasuyama, Keiichi Inoue, Ichiro Takeuchi

As part of a quality control process in manufacturing it is often necessary to test whether all parts of a product satisfy a required property, with as few inspections as possible.

Active Learning

Computing Valid p-values for Image Segmentation by Selective Inference

no code implementations CVPR 2020 Kosuke Tanizaki, Noriaki Hashimoto, Yu Inatsu, Hidekata Hontani, Ichiro Takeuchi

To overcome this difficulty, we introduce a statistical approach called selective inference, and develop a framework to compute valid p-values in which the segmentation bias is properly accounted for.

Semantic Segmentation

Statistically Discriminative Sub-trajectory Mining

no code implementations6 May 2019 Vo Nguyen Le Duy, Takuto Sakuma, Taiju Ishiyama, Hiroki Toda, Kazuya Nishi, Masayuki Karasuyama, Yuta Okubo, Masayuki Sunaga, Yasuo Tabei, Ichiro Takeuchi

Given two groups of trajectories, the goal of this problem is to extract moving patterns in the form of sub-trajectories which are more similar to sub-trajectories of one group and less similar to those of the other.

Active learning for enumerating local minima based on Gaussian process derivatives

no code implementations8 Mar 2019 Yu Inatsu, Daisuke Sugita, Kazuaki Toyoura, Ichiro Takeuchi

We study active learning (AL) based on Gaussian Processes (GPs) for efficiently enumerating all of the local minimum solutions of a black-box function.

Active Learning Gaussian Processes

Safe Grid Search with Optimal Complexity

1 code implementation12 Oct 2018 Eugene Ndiaye, Tam Le, Olivier Fercoq, Joseph Salmon, Ichiro Takeuchi

Popular machine learning estimators involve regularization parameters that can be challenging to tune, and standard strategies rely on grid search for this task.

Learning sparse optimal rule fit by safe screening

no code implementations3 Oct 2018 Hiroki Kato, Hiroyuki Hanada, Ichiro Takeuchi

In this paper, we propose Safe Optimal Rule Fit (SORF) as an approach to resolve this problem, which is formulated as a convex optimization problem with sparse regularization.

Interval-based Prediction Uncertainty Bound Computation in Learning with Missing Values

no code implementations1 Mar 2018 Hiroyuki Hanada, Toshiyuki Takada, Jun Sakuma, Ichiro Takeuchi

A drawback of this naive approach is that the uncertainty in the missing entries is not properly incorporated in the prediction.

Imputation

Unsupervised Phase Mapping of X-ray Diffraction Data by Nonnegative Matrix Factorization Integrated with Custom Clustering

no code implementations20 Feb 2018 Valentin Stanev, Velimir V. Vesselinov, A. Gilad Kusne, Graham Antoszewski, Ichiro Takeuchi, Boian S. Alexandrov

Analyzing large X-ray diffraction (XRD) datasets is a key step in high-throughput mapping of the compositional phase diagrams of combinatorial materials libraries.

X-Ray Diffraction (XRD)

Post Selection Inference with Incomplete Maximum Mean Discrepancy Estimator

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.

Change Point Detection feature selection

Safe Triplet Screening for Distance Metric Learning

1 code implementation12 Feb 2018 Tomoki Yoshida, Ichiro Takeuchi, Masayuki Karasuyama

Distance metric learning can optimize a metric over a set of triplets, each one of which is defined by a pair of same class instances and an instance in a different class.

Metric Learning

Machine learning modeling of superconducting critical temperature

1 code implementation8 Sep 2017 Valentin Stanev, Corey Oses, A. Gilad Kusne, Efrain Rodriguez, Johnpierre Paglione, Stefano Curtarolo, Ichiro Takeuchi

Separate regression models are developed to predict the values of $T_{\mathrm{c}}$ for cuprate, iron-based, and "low-$T_{\mathrm{c}}$" compounds.

General Classification

Selective Inference for Sparse High-Order Interaction Models

no code implementations ICML 2017 Shinya Suzumura, Kazuya Nakagawa, Yuta Umezu, Koji Tsuda, Ichiro Takeuchi

Finding statistically significant high-order interactions in predictive modeling is important but challenging task because the possible number of high-order interactions is extremely large (e. g., $> 10^{17}$).

feature selection

Selective Inference for Change Point Detection in Multi-dimensional Sequences

no code implementations1 Jun 2017 Yuta Umezu, Ichiro Takeuchi

We study the problem of detecting change points (CPs) that are characterized by a subset of dimensions in a multi-dimensional sequence.

Change Point Detection Selection bias

Post Selection Inference with Kernels

no code implementations12 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.

General Classification Multi-class Classification

Efficiently Bounding Optimal Solutions after Small Data Modification in Large-Scale Empirical Risk Minimization

no code implementations1 Jun 2016 Hiroyuki Hanada, Atsushi Shibagaki, Jun Sakuma, Ichiro Takeuchi

We study large-scale classification problems in changing environments where a small part of the dataset is modified, and the effect of the data modification must be quickly incorporated into the classifier.

General Classification Small Data Image Classification

Selective Inference Approach for Statistically Sound Predictive Pattern Mining

no code implementations15 Feb 2016 Shinya Suzumura, Kazuya Nakagawa, Mahito Sugiyama, Koji Tsuda, Ichiro Takeuchi

The main obstacle of this problem is in the difficulty of taking into account the selection bias, i. e., the bias arising from the fact that patterns are selected from extremely large number of candidates in databases.

Selection bias Two-sample testing

Safe Pattern Pruning: An Efficient Approach for Predictive Pattern Mining

no code implementations15 Feb 2016 Kazuya Nakagawa, Shinya Suzumura, Masayuki Karasuyama, Koji Tsuda, Ichiro Takeuchi

The SPP method allows us to efficiently find a superset of all the predictive patterns in the database that are needed for the optimal predictive model.

Graph Mining

Secure Approximation Guarantee for Cryptographically Private Empirical Risk Minimization

no code implementations15 Feb 2016 Toshiyuki Takada, Hiroyuki Hanada, Yoshiji Yamada, Jun Sakuma, Ichiro Takeuchi

The key property of SAG method is that, given an arbitrary approximate solution, it can provide a non-probabilistic assumption-free bound on the approximation quality under cryptographically secure computation framework.

Simultaneous Safe Screening of Features and Samples in Doubly Sparse Modeling

no code implementations8 Feb 2016 Atsushi Shibagaki, Masayuki Karasuyama, Kohei Hatano, Ichiro Takeuchi

A significant advantage of considering them simultaneously rather than individually is that they have a synergy effect in the sense that the results of the previous safe feature screening can be exploited for improving the next safe sample screening performances, and vice-versa.

Homotopy Continuation Approaches for Robust SV Classification and Regression

no code implementations12 Jul 2015 Shinya Suzumura, Kohei Ogawa, Masashi Sugiyama, Masayuki Karasuyama, Ichiro Takeuchi

An advantage of our homotopy approach is that it can be interpreted as simulated annealing, a common approach for finding a good local optimal solution in non-convex optimization problems.

Classification General Classification +2

Safe Feature Pruning for Sparse High-Order Interaction Models

no code implementations26 Jun 2015 Kazuya Nakagawa, Shinya Suzumura, Masayuki Karasuyama, Koji Tsuda, Ichiro Takeuchi

An SFS rule has a property that, if a feature satisfies the rule, then the feature is guaranteed to be non-active in the LASSO solution, meaning that it can be safely screened-out prior to the LASSO training process.

Sparse Learning

Regularization Path of Cross-Validation Error Lower Bounds

1 code implementation NeurIPS 2015 Atsushi Shibagaki, Yoshiki Suzuki, Masayuki Karasuyama, Ichiro Takeuchi

Careful tuning of a regularization parameter is indispensable in many machine learning tasks because it has a significant impact on generalization performances.

An Algorithmic Framework for Computing Validation Performance Bounds by Using Suboptimal Models

no code implementations10 Feb 2014 Yoshiki Suzuki, Kohei Ogawa, Yuki Shinmura, Ichiro Takeuchi

If a reasonably good suboptimal model is available, our algorithm can compute lower and upper bounds of many useful quantities for making inferences on the unknown target model.

Model Selection

Safe Sample Screening for Support Vector Machines

no code implementations27 Jan 2014 Kohei Ogawa, Yoshiki Suzuki, Shinya Suzumura, Ichiro Takeuchi

Sparse classifiers such as the support vector machines (SVM) are efficient in test-phases because the classifier is characterized only by a subset of the samples called support vectors (SVs), and the rest of the samples (non SVs) have no influence on the classification result.

Parametric Task Learning

no code implementations NeurIPS 2013 Ichiro Takeuchi, Tatsuya Hongo, Masashi Sugiyama, Shinichi Nakajima

We introduce a novel formulation of multi-task learning (MTL) called parametric task learning (PTL) that can systematically handle infinitely many tasks parameterized by a continuous parameter.

Multi-Task Learning

Global Solver and Its Efficient Approximation for Variational Bayesian Low-rank Subspace Clustering

no code implementations NeurIPS 2013 Shinichi Nakajima, Akiko Takeda, S. Derin Babacan, Masashi Sugiyama, Ichiro Takeuchi

However, Bayesian learning is often obstructed by computational difficulty: the rigorous Bayesian learning is intractable in many models, and its variational Bayesian (VB) approximation is prone to suffer from local minima.

Density-Difference Estimation

no code implementations NeurIPS 2012 Masashi Sugiyama, Takafumi Kanamori, Taiji Suzuki, Marthinus D. Plessis, Song Liu, Ichiro Takeuchi

A naive approach is a two-step procedure of first estimating two densities separately and then computing their difference.

Change Point Detection

Multiple Incremental Decremental Learning of Support Vector Machines

no code implementations NeurIPS 2009 Masayuki Karasuyama, Ichiro Takeuchi

Conventional single cremental decremental SVM can update the trained model efficiently when single data point is added to or removed from the training set.

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