Searcharxiv⌕ Search

arXiv subjects

Inyoung Kim

Publications and source records attributed to Inyoung Kim.

15 recordsLinked to original sources
arXiv2026

StarDrinks: An English and Korean Test Set for SLU Evaluation in a Drink Ordering Scenario

LLMs and speech assistants are increasingly used for task-oriented interactions, yet their evaluation often relies on controlled scenarios that fail to capture the variability and complexity of real user requests. Drink ordering, for example, involves diverse named entities, drink types, sizes, customizations, and brand-specific terminology, as well as spontaneous speech phenomena such as hesitations and self-corrections. To address this gap, we introduce StarDrinks, a test set in English and Korean containing speech utterances features, transcriptions, and annotated slots. Our dataset supports speech-to-slots SLU, transcription-to-slots NLU, and speech-to-transcription ASR evaluation, providing a realistic benchmark for model robustness and generalization in a linguistically rich, real-world task.

cs.CL↗
arXiv2025

Pinched self-dual Weyl curvature on Einstein four-manifolds

We show that a compact oriented riemannian four-manifold with harmonic and pinched self-dual Weyl curvature is anti-self-dual if the type is nonpositive. The main part is to show that there is an almost-K\"ahler structure outside the zero set of the self-dual Weyl curvature.

math.DG↗
arXiv2025

Likelihood-guided Regularization in Attention Based Models

The transformer architecture has demonstrated strong performance in classification tasks involving structured and high-dimensional data. However, its success often hinges on large- scale training data and careful regularization to prevent overfitting. In this paper, we intro- duce a novel likelihood-guided variational Ising-based regularization framework for Vision Transformers (ViTs), which simultaneously enhances model generalization and dynamically prunes redundant parameters. The proposed variational Ising-based regularization approach leverages Bayesian sparsification techniques to impose structured sparsity on model weights, allowing for adaptive architecture search during training. Unlike traditional dropout-based methods, which enforce fixed sparsity patterns, the variational Ising-based regularization method learns task-adaptive regularization, improving both efficiency and interpretability. We evaluate our approach on benchmark vision datasets, including MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100, demonstrating improved generalization under sparse, complex data and allowing for principled uncertainty quantification on both weights and selection parameters. Additionally, we show that the Ising regularizer leads to better-calibrated probability estimates and structured feature selection through uncertainty-aware attention mechanisms. Our results highlight the effectiveness of structured Bayesian sparsification in enhancing transformer-based architectures, offering a principled alternative to standard regularization techniques.

stat.ML↗
arXiv2023

Self-dual almost-K\"ahler four manifolds

We classify compact self-dual almost-K\"ahler four manifolds of positive type and zero type. In particular, using LeBrun's result, we show that any self-dual almost-K\"ahler metric on a manifold which is diffeomorphic to $\mathbb{CP}_{2}$ is the Fubini-Study metric up to rescaling. In case of negative type, we classify compact self-dual almost-K\"ahler four manifolds with $J$-invariant Ricci tensor.

math.DG↗
arXiv2023

Almost-K\"ahler four manifolds with harmonic self-dual Weyl curvature

We show that a compact almost-K\"ahler four manifold $(M, g, \omega)$ with harmonic self-dual Weyl curvature and constant scalar curvature is K\"ahler if $c_{1}\cdot\omega\geq 0$. We also prove an integral curvature inequality for compact almost-K\"ahler four manifolds with harmonic self-dual Weyl curvature.

math.DG↗
arXiv2021

A Robust Asymmetric Kernel Function for Bayesian Optimization, with Application to Image Defect Detection in Manufacturing Systems

Some response surface functions in complex engineering systems are usually highly nonlinear, unformed, and expensive-to-evaluate. To tackle this challenge, Bayesian optimization, which conducts sequential design via a posterior distribution over the objective function, is a critical method used to find the global optimum of black-box functions. Kernel functions play an important role in shaping the posterior distribution of the estimated function. The widely used kernel function, e.g., radial basis function (RBF), is very vulnerable and susceptible to outliers; the existence of outliers is causing its Gaussian process surrogate model to be sporadic. In this paper, we propose a robust kernel function, Asymmetric Elastic Net Radial Basis Function (AEN-RBF). Its validity as a kernel function and computational complexity are evaluated. When compared to the baseline RBF kernel, we prove theoretically that AEN-RBF can realize smaller mean squared prediction error under mild conditions. The proposed AEN-RBF kernel function can also realize faster convergence to the global optimum. We also show that the AEN-RBF kernel function is less sensitive to outliers, and hence improves the robustness of the corresponding Bayesian optimization with Gaussian processes. Through extensive evaluations carried out on synthetic and real-world optimization problems, we show that AEN-RBF outperforms existing benchmark kernel functions.

stat.ML↗
arXiv2017

4-dimensional Riemannian manifolds with a harmonic 2-form of constant length

It was shown by Seaman that if a compact, oriented 4-dimensional riemannian manifold (M, g) of positive sectional curvature admits a harmonic 2-form of constant length, its intersection form is definite and such a harmonic form is unique up to constant multiples. In this paper, we show that such a manifold is diffeomorphic to $\mathbb{CP}_{2}$ with a slightly weaker curvature hypothesis and there is an infinite dimensional moduli space of such metrics near the Fubini-Study metric on $\mathbb{CP}_{2}$. We discuss some of conditions which can be added in order to get the Fubini-Study metric up to diffeomorphisms and rescaling.

math.DG↗
arXiv2015

Almost-Kahler Anti-Self-Dual Metrics

We show the existence of strictly almost-Kahler anti-self-dual metrics on certain 4-manifolds by deforming scalar-flat Kahler metrics. On the other hand, we prove the non-existence of such metrics on certain other 4-manifolds by means of Seiberg-Witten theory. In the process, we provide a simple new proof of the fact that any almost-Kahler anti-self-dual 4-manifold must have a non-trivial Seiberg-Witten invariant.

math.DG↗
arXiv2015

Hit and Run ARMS: Adaptive Rejection Metropolis Sampling with Hit and Run Random Direction

An algorithm for sampling from non-log-concave multivariate distributions is proposed, which improves the adaptive rejection Metropolis sampling (ARMS) algorithm by incorporating the hit and run sampling. It is not rare that the ARMS is trapped away from some subspace with significant probability in the support of the multivariate distribution. While the ARMS updates samples only in the directions that are parallel to dimensions, our proposed method, the hit and run ARMS (HARARMS), updates samples in arbitrary directions determined by the hit and run algorithm, which makes it almost not possible to be trapped in any isolated subspaces. The HARARMS performs the same as ARMS in a single dimension while more reliable in multidimensional spaces. Its performance is illustrated by a Bayesian free-knot spline regression example. We showed that it overcomes the well-known `lethargy' property and decisively find the global optimal number and locations of the knots of the spline function.

stat.CO↗
arXiv2012

Flexible Variable Selection for Recovering Sparsity in Nonadditive Nonparametric Models

Variable selection for recovering sparsity in nonadditive nonparametric models has been challenging. This problem becomes even more difficult due to complications in modeling unknown interaction terms among high dimensional variables. There is currently no variable selection method to overcome these limitations. Hence, in this paper we propose a variable selection approach that is developed by connecting a kernel machine with the nonparametric multiple regression model. The advantages of our approach are that it can: (1) recover the sparsity, (2) automatically model unknown and complicated interactions, (3) connect with several existing approaches including linear nonnegative garrote, kernel learning and automatic relevant determinants (ARD), and (4) provide flexibility for both additive and nonadditive nonparametric models. Our approach may be viewed as a nonlinear version of a nonnegative garrote method. We model the smoothing function by a least squares kernel machine and construct the nonnegative garrote objective function as the function of the similarity matrix. Since the multiple regression similarity matrix can be written as an additive form of univariate similarity matrices corresponding to input variables, applying a sparse scale parameter on each univariate similarity matrix can reveal its relevance to the response variable. We also derive the asymptotic properties of our approach, and show that it provides a square root consistent estimator of the scale parameters. Furthermore, we prove that sparsistency is satisfied with consistent initial kernel function coefficients under certain conditions and give the necessary and sufficient conditions for sparsistency. An efficient coordinate descent/backfitting algorithm is developed. A resampling procedure for our variable selection methodology is also proposed to improve power.

stat.ME↗
arXiv2012

A Graphical View of Bayesian Variable Selection

In recent years, Ising prior with the network information for the "in" or "out" binary random variable in Bayesian variable selections has received more and more attentions. In this paper, we discover that even without the informative prior a Bayesian variable selection problem itself can be considered as a complete graph and described by a Ising model with random interactions. There are many advantages of treating variable selection as a graphical model, such as it is easy to employ the single site updating as well as the cluster updating algorithm, suitable for problems with small sample size and larger variable number, easy to extend to nonparametric regression models and incorporate graphical prior information and so on. In a Bayesian variable selection Ising model the interactions are determined by the linear model coefficients, so we systematically study the performance of different scale normal mixture priors for the model coefficients by adopting the global-local shrinkage strategy. Our results prove that the best prior of the model coefficients in terms of variable selection should maintain substantial weight on small shrinkage instead of large shrinkage. We also discuss the connection between the tempering algorithms for Ising models and the global-local shrinkage approach, showing that the shrinkage parameter plays a tempering role. The methods are illustrated with simulated and real data.

stat.ME↗
arXiv2012

Semiparametric Mixed Model for Evaluating Pathway-Environment Interaction

A biological pathway represents a set of genes that serves a particular cellular or a physiological function. The genes within the same pathway are expected to function together and hence may interact with each other. It is also known that many genes, and so pathways, interact with other environmental variables. However, no formal procedure has yet been developed to evaluate the pathway-environment interaction. In this article, we propose a semiparametric method to model the pathway-environment interaction. The method connects a least square kernel machine and a semiparametric mixed effects model. We model nonparametrically the environmental effect via a natural cubic spline. Both a pathway effect and an interaction between a pathway and an environmental effect are modeled nonparametrically via a kernel machine, and we estimate variance component representing an interaction effect under a semiparametric mixed effects model. We then employ a restricted likelihood ratio test and a score test to evaluate the main pathway effect and the pathway-environment interaction. The approach was applied to a genetic pathway data of Type II diabetes, and pathways with either a significant main pathway effect, an interaction effect or both were identified. Other methods previously developed determined many as having a significant main pathway effect only. Furthermore, among those significant pathways, we discovered some pathways having a significant pathway-environment interaction effect, a result that other methods would not be able to detect.

stat.ME↗