150 citations · 221 across the 19 of their papers we have counts for
21 papers
On Uncertainty Estimation by Tree-based Surrogate Models in Sequential Model-based Optimization
Jungtaek Kim, Seungjin Choi
Sequential model-based optimization sequentially selects a candidate point by constructing a surrogate model with the history of evaluations, to solve a black-box optimization prob…
Combinatorial Bayesian Optimization with Random Mapping Functions to Convex Polytopes
Jungtaek Kim, Seungjin Choi, Minsu Cho
Bayesian optimization is a popular method for solving the problem of global optimization of an expensive-to-evaluate black-box function. It relies on a probabilistic surrogate mode…
Sparse Network Inversion for Key Instance Detection in Multiple Instance Learning
Beomjo Shin, Junsu Cho, Hwanjo Yu +1
Multiple Instance Learning (MIL) involves predicting a single label for a bag of instances, given positive or negative labels at bag-level, without accessing to label for each inst…
Neural Complexity Measures
Yoonho Lee, Juho Lee, Sung Ju Hwang +2
While various complexity measures for deep neural networks exist, specifying an appropriate measure capable of predicting and explaining generalization in deep networks has proven…
Discrete Infomax Codes for Supervised Representation Learning
Yoonho Lee, Wonjae Kim, Wonpyo Park +1
Learning compact discrete representations of data is a key task on its own or for facilitating subsequent processing of data. In this paper we present a model that produces Discret…
Bayesian Optimization with Approximate Set Kernels
Jungtaek Kim, Michael McCourt, Tackgeun You +2
We propose a practical Bayesian optimization method over sets, to minimize a black-box function that takes a set as a single input. Because set inputs are permutation-invariant, tr…
Practical Bayesian Optimization with Threshold-Guided Marginal Likelihood Maximization
Jungtaek Kim, Seungjin Choi
We propose a practical Bayesian optimization method using Gaussian process regression, of which the marginal likelihood is maximized where the number of model selection steps is gu…
MxML: Mixture of Meta-Learners for Few-Shot Classification
Minseop Park, Jungtaek Kim, Saehoon Kim +2
A meta-model is trained on a distribution of similar tasks such that it learns an algorithm that can quickly adapt to a novel task with only a handful of labeled examples. Most of…
On Local Optimizers of Acquisition Functions in Bayesian Optimization
Jungtaek Kim, Seungjin Choi
Bayesian optimization is a sample-efficient method for finding a global optimum of an expensive-to-evaluate black-box function. A global solution is found by accumulating a pair of…
A Bayesian model for sparse graphs with flexible degree distribution and overlapping community structure
Juho Lee, Lancelot F. James, Seungjin Choi +1
We consider a non-projective class of inhomogeneous random graph models with interpretable parameters and a number of interesting asymptotic properties. Using the results of Bollob…
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
Juho Lee, Yoonho Lee, Jungtaek Kim +3
Many machine learning tasks such as multiple instance learning, 3D shape recognition, and few-shot image classification are defined on sets of instances. Since solutions to such pr…
Learning to Warm-Start Bayesian Hyperparameter Optimization
Jungtaek Kim, Saehoon Kim, Seungjin Choi
Hyperparameter optimization aims to find the optimal hyperparameter configuration of a machine learning model, which provides the best performance on a validation dataset. Manual s…
Bayesian inference on random simple graphs with power law degree distributions
Juho Lee, Creighton Heaukulani, Zoubin Ghahramani +2
We present a model for random simple graphs with a degree distribution that obeys a power law (i.e., is heavy-tailed). To attain this behavior, the edge probabilities in the graph…
Gaussian Copula Variational Autoencoders for Mixed Data
Suwon Suh, Seungjin Choi
The variational autoencoder (VAE) is a generative model with continuous latent variables where a pair of probabilistic encoder (bottom-up) and decoder (top-down) is jointly learned…
Tree-Guided MCMC Inference for Normalized Random Measure Mixture Models
Juho Lee, Seungjin Choi
Normalized random measures (NRMs) provide a broad class of discrete random measures that are often used as priors for Bayesian nonparametric models. Dirichlet process is a well-kno…
Bilinear Random Projections for Locality-Sensitive Binary Codes
Saehoon Kim, Seungjin Choi
Locality-sensitive hashing (LSH) is a popular data-independent indexing method for approximate similarity search, where random projections followed by quantization hash the points…
Learning to Select Pre-Trained Deep Representations with Bayesian Evidence Framework
Yong-Deok Kim, Taewoong Jang, Bohyung Han +1
We propose a Bayesian evidence framework to facilitate transfer learning from pre-trained deep convolutional neural networks (CNNs). Our framework is formulated on top of a least s…
Bayesian Hierarchical Clustering with Exponential Family: Small-Variance Asymptotics and Reducibility
Juho Lee, Seungjin Choi
Bayesian hierarchical clustering (BHC) is an agglomerative clustering method, where a probabilistic model is defined and its marginal likelihoods are evaluated to decide which clus…
Convex Optimization for Binary Classifier Aggregation in Multiclass Problems
Sunho Park, TaeHyun Hwang, Seungjin Choi
Multiclass problems are often decomposed into multiple binary problems that are solved by individual binary classifiers whose results are integrated into a final answer. Various me…
Regularized Discriminant Embedding for Visual Descriptor Learning
Kye-Hyeon Kim, Rui Cai, Lei Zhang +1
Images can vary according to changes in viewpoint, resolution, noise, and illumination. In this paper, we aim to learn representations for an image, which are robust to wide change…
Learning Features with Structure-Adapting Multi-view Exponential Family Harmoniums
Yoonseop Kang, Seungjin Choi
We proposea graphical model for multi-view feature extraction that automatically adapts its structure to achieve better representation of data distribution. The proposed model, str…