Search Results for author:
Found 76 papers, 19 papers with code
State-Separated SARSA: A Practical Sequential Decision-Making Algorithm with Recovering Rewards
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.
Neural-Kernel Conditional Mean Embeddings
In conditional density estimation tasks, our NN-CME hybrid achieves competitive performance and often surpasses existing deep learning-based methods.
Extended Flow Matching: a Method of Conditional Generation with Generalized Continuity Equation
In this paper, we develop the theory of conditional generation based on Flow Matching, a current strong contender of diffusion methods.
Generalized Sobolev Transport for Probability Measures on a Graph
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.
Optimal Transport for Measures with Noisy Tree Metric
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.
Neural Fourier Transform: A General Approach to Equivariant Representation Learning
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.
Controlling Posterior Collapse by an Inverse Lipschitz Constraint on the Decoder Network
Variational autoencoders (VAEs) are one of the deep generative models that have experienced enormous success over the past decades.
Scalable Unbalanced Sobolev Transport for Measures on a Graph
We show that the proposed unbalanced Sobolev transport (UST) admits a closed-form formula for fast computation, and it is also negative definite.
Transfer learning with affine model transformation
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.
Invariance-adapted decomposition and Lasso-type contrastive learning
Recent years have witnessed the effectiveness of contrastive learning in obtaining the representation of dataset that is useful in interpretation and downstream tasks.
Unsupervised Learning of Equivariant Structure from Sequences
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.
Robust Topological Inference in the Presence of Outliers
The distance function to a compact set plays a crucial role in the paradigm of topological data analysis.
Invariance Learning based on Label Hierarchy
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.
ALGAN: Anomaly Detection by Generating Pseudo Anomalous Data via Latent Variables
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.
β-Intact-VAE: Identifying and Estimating Causal Effects under Limited Overlap
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.
Towards Principled Causal Effect Estimation by Deep Identifiable Models
As an important problem in causal inference, we discuss the estimation of treatment effects (TEs).
A Scaling Law for Syn-to-Real Transfer: How Much Is Your Pre-training Effective?
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.
$\beta$-Intact-VAE: Identifying and Estimating Causal Effects under Limited Overlap
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.
A Scaling Law for Synthetic-to-Real Transfer: How Much Is Your Pre-training Effective?
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.
Identifying and Estimating Causal Effects under Weak Overlap by Generative Prognostic Model
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.
Intact-VAE: Estimating Treatment Effects under Unobserved Confounding
As an important problem of causal inference, we discuss the identification and estimation of treatment effects under unobserved confounding.
Advantage of Deep Neural Networks for Estimating Functions with Singularity on Hypersurfaces
We develop a minimax rate analysis to describe the reason that deep neural networks (DNNs) perform better than other standard methods.
Meta Learning for Causal Direction
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.
A General Class of Transfer Learning Regression without Implementation Cost
We propose a novel framework that unifies and extends existing methods of transfer learning (TL) for regression.
Robust Persistence Diagrams using Reproducing Kernels
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.
The equivalence between Stein variational gradient descent and black-box variational inference
We formalize an equivalence between two popular methods for Bayesian inference: Stein variational gradient descent (SVGD) and black-box variational inference (BBVI).
Smoothness and Stability in GANs
Generative adversarial networks, or GANs, commonly display unstable behavior during training.
Causal Mosaic: Cause-Effect Inference via Nonlinear ICA and Ensemble Method
We address the problem of distinguishing cause from effect in bivariate setting.
Exchangeable deep neural networks for set-to-set matching and learning
Matching two different sets of items, called heterogeneous set-to-set matching problem, has recently received attention as a promising problem.
A Kernel Stein Test for Comparing Latent Variable Models
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.
Semi-flat minima and saddle points by embedding neural networks to overparameterization
We theoretically study the landscape of the training error for neural networks in overparameterized cases.
Convex Covariate Clustering for Classification
Clustering, like covariate selection for classification, is an important step to compress and interpret the data.
Tree-Sliced Variants of Wasserstein Distances
Optimal transport (\OT) theory defines a powerful set of tools to compare probability distributions.
Understanding GANs via Generalization Analysis for Disconnected Support
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.
Pointwise HSIC: A Linear-Time Kernelized Co-occurrence Norm for Sparse Linguistic Expressions
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).
Robust Bayesian Model Selection for Variable Clustering with the Gaussian Graphical Model
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).
Variational Learning on Aggregate Outputs with Gaussian Processes
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.
Kernel Recursive ABC: Point Estimation with Intractable Likelihood
We propose a novel approach to parameter estimation for simulator-based statistical models with intractable likelihood.
Post Selection Inference with Incomplete Maximum Mean Discrepancy Estimator
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.
Selecting the Best in GANs Family: a Post Selection Inference Framework
"Which Generative Adversarial Networks (GANs) generates the most plausible images?"
Deep Neural Networks Learn Non-Smooth Functions Effectively
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.
Convergence Analysis of Deterministic Kernel-Based Quadrature Rules in Misspecified Settings
This paper presents a convergence analysis of kernel-based quadrature rules in misspecified settings, focusing on deterministic quadrature in Sobolev spaces.
Kernel method for persistence diagrams via kernel embedding and weight factor
Topological data analysis is an emerging mathematical concept for characterizing shapes in multi-scale data.
Ranked #4 on
Graph Classification
on NEURON-MULTI
A Linear-Time Kernel Goodness-of-Fit Test
We propose a novel adaptive test of goodness-of-fit, with computational cost linear in the number of samples.
Influence Function and Robust Variant of Kernel Canonical Correlation Analysis
Many unsupervised kernel methods rely on the estimation of the kernel covariance operator (kernel CO) or kernel cross-covariance operator (kernel CCO).
Trimmed Density Ratio Estimation
Density ratio estimation is a vital tool in both machine learning and statistical community.
Learning Sparse Structural Changes in High-dimensional Markov Networks: A Review on Methodologies and Theories
Recent years have seen an increasing popularity of learning the sparse \emph{changes} in Markov Networks.
Post Selection Inference with Kernels
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.
Kernel Mean Embedding of Distributions: A Review and Beyond
Next, we discuss the Hilbert space embedding for conditional distributions, give theoretical insights, and review some applications.
Convergence guarantees for kernel-based quadrature rules in misspecified settings
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.
Robust Kernel (Cross-) Covariance Operators in Reproducing Kernel Hilbert Space toward Kernel Methods
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.
Persistence weighted Gaussian kernel for topological data analysis
Topological data analysis (TDA) is an emerging mathematical concept for characterizing shapes in complex data.
Algebraic Topology
Estimating Posterior Ratio for Classification: Transfer Learning from Probabilistic Perspective
Transfer learning assumes classifiers of similar tasks share certain parameter structures.
Structure Learning of Partitioned Markov Networks
We learn the structure of a Markov Network between two groups of random variables from joint observations.
Computing Functions of Random Variables via Reproducing Kernel Hilbert Space Representations
We describe a method to perform functional operations on probability distributions of random variables.
Model-based Kernel Sum Rule: Kernel Bayesian Inference with Probabilistic Models
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.
Kernel-based Information Criterion
This paper introduces Kernel-based Information Criterion (KIC) for model selection in regression analysis.
Support Consistency of Direct Sparse-Change Learning in Markov Networks
We study the problem of learning sparse structure changes between two Markov networks $P$ and $Q$.
Kernel Mean Shrinkage Estimators
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.
Characteristic Kernels and Infinitely Divisible Distributions
If $P, Q$, and kernel $k$ are Gaussians, then computation (i) and (ii) results in Gaussian pdfs that is tractable.
Filtering with State-Observation Examples via Kernel Monte Carlo Filter
In particular, the sampling and resampling procedures are novel in being expressed using kernel mean embeddings, so we theoretically analyze their behaviors.
Density Estimation in Infinite Dimensional Exponential Families
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 $C^\beta$.
Kernel Mean Estimation and Stein's Effect
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.
Optimal kernel choice for large-scale two-sample tests
A means of parameter selection for the two-sample test based on the MMD is proposed.
Gradient-based kernel method for feature extraction and variable selection
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.
Learning from Distributions via Support Measure Machines
This paper presents a kernel-based discriminative learning framework on probability measures.
Equivalence of distance-based and RKHS-based statistics in hypothesis testing
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.
Kernel Bayes' Rule
A nonparametric kernel-based method for realizing Bayes' rule is proposed, based on kernel representations of probabilities in reproducing kernel Hilbert spaces.
Learning in Hilbert vs. Banach Spaces: A Measure Embedding Viewpoint
The goal of this paper is to investigate the advantages and disadvantages of learning in Banach spaces over Hilbert spaces.
A Fast, Consistent Kernel Two-Sample Test
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.
Graph Zeta Function in the Bethe Free Energy and Loopy Belief Propagation
We also propose a new approach to the uniqueness of LBP fixed point, and show various conditions of uniqueness.
Hilbert space embeddings and metrics on probability measures
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}.
On integral probability metrics, φ-divergences and binary classification
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
Characteristic Kernels on Groups and Semigroups
Embeddings of random variables in reproducing kernel Hilbert spaces (RKHSs) may be used to conduct statistical inference based on higher order moments.
