Search Results for author:
Found 69 papers, 12 papers with code
Fast Deterministic CUR Matrix Decomposition with Accuracy Assurance
This is because coordinate descent iteratively updates all the parameters in the objective until convergence.
Neural Operators Meet Energy-based Theory: Operator Learning for Hamiltonian and Dissipative PDEs
The operator learning has received significant attention in recent years, with the aim of learning a mapping between function spaces.
Meta-Learning for Neural Network-based Temporal Point Processes
The point process is widely used in many applications to predict such events related to human activities.
Meta-learning to Calibrate Gaussian Processes with Deep Kernels for Regression Uncertainty Estimation
We propose a meta-learning method for calibrating deep kernel GPs for improving regression uncertainty estimation performance with a limited number of training data.
Meta-learning of semi-supervised learning from tasks with heterogeneous attribute spaces
The proposed method embeds labeled and unlabeled data simultaneously in a task-specific space using a neural network, and the unlabeled data's labels are estimated by adapting classification or regression models in the embedding space.
Meta-learning of Physics-informed Neural Networks for Efficiently Solving Newly Given PDEs
We propose a neural network-based meta-learning method to efficiently solve partial differential equation (PDE) problems.
Explanation-based Training with Differentiable Insertion/Deletion Metric-aware Regularizers
To improve the faithfulness, we propose insertion/deletion metric-aware explanation-based optimization (ID-ExpO), which optimizes differentiable predictors to improve both the insertion and deletion scores of the explanations while maintaining their predictive accuracy.
Information-theoretic Analysis of Test Data Sensitivity in Uncertainty
Furthermore, we extend the existing analysis of Bayesian meta-learning and show the novel sensitivities among tasks for the first time.
Meta-learning for heterogeneous treatment effect estimation with closed-form solvers
With our formulation, we can obtain optimal task-specific parameters in a closed form that are differentiable with respect to task-shared parameters, making it possible to perform effective meta-learning.
Modeling Nonlinear Dynamics in Continuous Time with Inductive Biases on Decay Rates and/or Frequencies
Inductive biases are helpful for training neural networks especially when training data are small.
Linear Embedding-based High-dimensional Batch Bayesian Optimization without Reconstruction Mappings
In this paper, we investigate a simple alternative approach: tackling the problem in the original high-dimensional space using the information from the learned low-dimensional structure.
Active Learning for Regression with Aggregated Outputs
Due to the privacy protection or the difficulty of data collection, we cannot observe individual outputs for each instance, but we can observe aggregated outputs that are summed over multiple instances in a set in some real-world applications.
Data-driven End-to-end Learning of Pole Placement Control for Nonlinear Dynamics via Koopman Invariant Subspaces
With the proposed method, a policy network is trained such that the eigenvalues of a Koopman operator of controlled dynamics are close to the target eigenvalues.
Predicting Opinion Dynamics via Sociologically-Informed Neural Networks
Traditionally, theoretical models of opinion dynamics have been proposed to describe the interactions between individuals (i. e., social interaction) and their impact on the evolution of collective opinions.
Aggregated Multi-output Gaussian Processes with Knowledge Transfer Across Domains
Since the supports may have various granularities depending on attributes (e. g., poverty rate and crime rate), modeling such data is not straightforward.
Meta-learning for Out-of-Distribution Detection via Density Estimation in Latent Space
With the proposed method, the OoD detection is performed by density estimation in a latent space.
Excess risk analysis for epistemic uncertainty with application to variational inference
Bayesian deep learning plays an important role especially for its ability evaluating epistemic uncertainty (EU).
Tight integration of neural- and clustering-based diarization through deep unfolding of infinite Gaussian mixture model
Speaker diarization has been investigated extensively as an important central task for meeting analysis.
Gaussian Process Regression With Interpretable Sample-Wise Feature Weights
In the proposed model, both the prediction and explanation for each sample are performed using an easy-to-interpret locally linear model.
Training Deep Models to be Explained with Fewer Examples
For improving the interpretability, reducing the number of examples in the explanation model is important.
Evacuation Shelter Scheduling Problem
In this study, we formulate the "Evacuation Shelter Scheduling Problem," which allocates evacuees to shelters in such a way to minimize the movement costs of the evacuees and the operation costs of the shelters.
End-to-End Learning of Deep Kernel Acquisition Functions for Bayesian Optimization
In experiments using three text document datasets, we demonstrate that the proposed method achieves better BO performance than the existing methods.
Meta-Learning for Relative Density-Ratio Estimation
The closed-form solution enables fast and effective adaptation to a few instances, and its differentiability enables us to train our model such that the expected test error for relative DRE can be explicitly minimized after adapting to a few instances.
Few-shot Learning for Unsupervised Feature Selection
We propose a few-shot learning method for unsupervised feature selection, which is a task to select a subset of relevant features in unlabeled data.
Meta-learning for Matrix Factorization without Shared Rows or Columns
The neural network is meta-learned such that the expected imputation error is minimized when the factorized matrices are adapted to each matrix by a maximum a posteriori (MAP) estimation.
Loss function based second-order Jensen inequality and its application to particle variational inference
First, we provide a new second-order Jensen inequality, which has the repulsion term based on the loss function.
Dynamic Hawkes Processes for Discovering Time-evolving Communities' States behind Diffusion Processes
Hawkes processes offer a central tool for modeling the diffusion processes, in which the influence from the past events is described by the triggering kernel.
Few-shot Learning for Topic Modeling
The proposed method trains the neural networks such that the expected test likelihood is improved when topic model parameters are estimated by maximizing the posterior probability using the priors based on the EM algorithm.
Context-aware Neural Machine Translation with Mini-batch Embedding
It is crucial to provide an inter-sentence context in Neural Machine Translation (NMT) models for higher-quality translation.
Meta-learning One-class Classifiers with Eigenvalue Solvers for Supervised Anomaly Detection
With a meta-learning framework, quick adaptation to each task and its effective backpropagation are important since the model is trained by the adaptation for each epoch.
Meta-learning representations for clustering with infinite Gaussian mixture models
We propose a meta-learning method that train neural networks for obtaining representations such that clustering performance improves when the representations are clustered by the variational Bayesian (VB) inference with an infinite Gaussian mixture model.
Meta-Learning for Koopman Spectral Analysis with Short Time-series
With the proposed method, a representation of a given short time-series is obtained by a bidirectional LSTM for extracting its properties.
Adversarial Training Makes Weight Loss Landscape Sharper in Logistic Regression
We theoretically and experimentally confirm that the weight loss landscape becomes sharper as the magnitude of the noise of adversarial training increases in the linear logistic regression model.
Neural Dynamic Mode Decomposition for End-to-End Modeling of Nonlinear Dynamics
With our proposed method, the forecast error is backpropagated through the neural networks and the spectral decomposition, enabling end-to-end learning of Koopman spectral analysis.
Meta-learning from Tasks with Heterogeneous Attribute Spaces
We propose a heterogeneous meta-learning method that trains a model on tasks with various attribute spaces, such that it can solve unseen tasks whose attribute spaces are different from the training tasks given a few labeled instances.
Learning Contextualised Cross-lingual Word Embeddings and Alignments for Extremely Low-Resource Languages Using Parallel Corpora
We propose a new approach for learning contextualised cross-lingual word embeddings based on a small parallel corpus (e. g. a few hundred sentence pairs).
Bilingual Lexicon Induction
Cross-Lingual Word Embeddings
+4
Meta-Active Learning for Node Response Prediction in Graphs
Meta-learning is an important approach to improve machine learning performance with a limited number of observations for target tasks.
Few-shot Learning for Spatial Regression
We propose a few-shot learning method for spatial regression.
Few-shot Learning for Time-series Forecasting
Forecasting models are usually trained using time-series data in a specific target task.
Gaussian Process Regression with Local Explanation
In the proposed model, both the prediction and explanation for each sample are performed using an easy-to-interpret locally linear model.
Probabilistic Optimal Transport based on Collective Graphical Models
In this study, we propose a new framework in which OT is considered as a maximum a posteriori (MAP) solution of a probabilistic generative model.
Neural Generators of Sparse Local Linear Models for Achieving both Accuracy and Interpretability
Additionally, the prediction is interpretable because it is obtained by the inner product between the simplified representations and the sparse weights, where only a small number of weights are selected by our gate module in the NGSLL.
Semi-supervised Anomaly Detection on Attributed Graphs
To learn node embeddings specialized for anomaly detection, in which there is a class imbalance due to the rarity of anomalies, the parameters of a GCN are trained to minimize the volume of a hypersphere that encloses the node embeddings of normal instances while embedding anomalous ones outside the hypersphere.
Transfer Anomaly Detection by Inferring Latent Domain Representations
The proposed method can infer the anomaly detectors for target domains without re-training by introducing the concept of latent domain vectors, which are latent representations of the domains and are used for inferring the anomaly detectors.
Efficient Transfer Bayesian Optimization with Auxiliary Information
By using the neural network covariance function, we can extract nonlinear correlation among feature vectors that are shared across related tasks.
Anomaly Detection with Inexact Labels
We model the anomaly score function by a neural network-based unsupervised anomaly detection method, e. g., autoencoders.
Spatially Aggregated Gaussian Processes with Multivariate Areal Outputs
By deriving the posterior GP, we can predict the data value at any location point by considering the spatial correlations and the dependences between areal data sets, simultaneously.
Unsupervised Multilingual Word Embedding with Limited Resources using Neural Language Models
Recently, a variety of unsupervised methods have been proposed that map pre-trained word embeddings of different languages into the same space without any parallel data.
Deep Mixture Point Processes: Spatio-temporal Event Prediction with Rich Contextual Information
Though many point processes have been proposed to model events in a continuous spatio-temporal space, none of them allow for the consideration of the rich contextual factors that affect event occurrence, such as weather, social activities, geographical characteristics, and traffic.
Supervised Anomaly Detection based on Deep Autoregressive Density Estimators
We propose a supervised anomaly detection method based on neural density estimators, where the negative log likelihood is used for the anomaly score.
Autoencoding Binary Classifiers for Supervised Anomaly Detection
Since our approach becomes able to reconstruct the normal data points accurately and fails to reconstruct the known and unknown anomalies, it can accurately discriminate both known and unknown anomalies from normal data points.
Finding Appropriate Traffic Regulations via Graph Convolutional Networks
In this paper, we propose a method to learn a function that outputs regulation effects given the current traffic situation as inputs.
Unsupervised Object Matching for Relational Data
The estimated latent vectors contain hidden structural information of each object in the given relational dataset.
Refining Coarse-grained Spatial Data using Auxiliary Spatial Data Sets with Various Granularities
With the proposed model, a distribution for each auxiliary data set on the continuous space is modeled using a Gaussian process, where the representation of uncertainty considers the levels of granularity.
Variational Autoencoder with Implicit Optimal Priors
However, KL divergence with the aggregated posterior cannot be calculated in a closed form, which prevents us from using this optimal prior.
Unsupervised Cross-lingual Word Embedding by Multilingual Neural Language Models
The proposed model contains bidirectional LSTMs that perform as forward and backward language models, and these networks are shared among all the languages.
Zero-shot Domain Adaptation without Domain Semantic Descriptors
The proposed method can infer appropriate domain-specific models without any semantic descriptors by introducing the concept of latent domain vectors, which are latent representations for the domains and are used for inferring the models.
Few-shot learning of neural networks from scratch by pseudo example optimization
In this paper, we propose a simple but effective method for training neural networks with a limited amount of training data.
Improving Output Uncertainty Estimation and Generalization in Deep Learning via Neural Network Gaussian Processes
We propose a simple method that combines neural networks and Gaussian processes.
Multi-view Anomaly Detection via Robust Probabilistic Latent Variable Models
With the proposed model, all views of a non-anomalous instance are assumed to be generated from a single latent vector.
Localized Lasso for High-Dimensional Regression
We introduce the localized Lasso, which is suited for learning models that are both interpretable and have a high predictive power in problems with high dimensionality $d$ and small sample size $n$.
Cross-Domain Matching for Bag-of-Words Data via Kernel Embeddings of Latent Distributions
We propose a kernel-based method for finding matching between instances across different domains, such as multilingual documents and images with annotations.
Latent Support Measure Machines for Bag-of-Words Data Classification
With the latent SMM, a latent vector is associated with each vocabulary term, and each document is represented as a distribution of the latent vectors for words appearing in the document.
Multi-view Anomaly Detection via Probabilistic Latent Variable Models
We propose a nonparametric Bayesian probabilistic latent variable model for multi-view anomaly detection, which is the task of finding instances that have inconsistent views.
Warped Mixtures for Nonparametric Cluster Shapes
A mixture of Gaussians fit to a single curved or heavy-tailed cluster will report that the data contains many clusters.
Warped Mixtures for Nonparametric Cluster Shapes
A mixture of Gaussians fit to a single curved or heavy-tailed cluster will report that the data contains many clusters.
Dynamic Infinite Relational Model for Time-varying Relational Data Analysis
We propose a new probabilistic model for analyzing dynamic evolutions of relational data, such as additions, deletions and split & merge, of relation clusters like communities in social networks.
Modeling Social Annotation Data with Content Relevance using a Topic Model
We propose a probabilistic topic model for analyzing and extracting content-related annotations from noisy annotated discrete data such as web pages stored in social bookmarking services.
