Search Results for author: Seungjin Choi

Found 21 papers, 5 papers with code

Combinatorial Bayesian Optimization with Random Mapping Functions to Convex Polytope

no code implementations26 Nov 2020 Jungtaek Kim, Minsu Cho, Seungjin Choi

The main idea is to use a random mapping which embeds the combinatorial space into a convex polytope in a continuous space, on which all essential process is performed to determine a solution to the black-box optimization in the combinatorial space.

Global Optimization

Sparse Network Inversion for Key Instance Detection in Multiple Instance Learning

no code implementations7 Sep 2020 Beomjo Shin, Junsu Cho, Hwanjo Yu, Seungjin Choi

Since a positive bag contains both positive and negative instances, it is often required to detect positive instances (key instances) when a set of instances is categorized as a positive bag.

Multiple Instance Learning

Neural Complexity Measures

1 code implementation NeurIPS 2020 Yoonho Lee, Juho Lee, Sung Ju Hwang, Eunho Yang, Seungjin Choi

While various complexity measures for deep neural networks exist, specifying an appropriate measure capable of predicting and explaining generalization in deep networks has proven challenging.

Meta-Learning

Discrete Infomax Codes for Supervised Representation Learning

no code implementations28 May 2019 Yoonho Lee, Wonjae Kim, Wonpyo Park, Seungjin Choi

In this paper we present a model that produces Discrete InfoMax Codes (DIMCO); we learn a probabilistic encoder that yields k-way d-dimensional codes associated with input data.

Meta-Learning Metric Learning +1

Bayesian Optimization with Approximate Set Kernels

no code implementations23 May 2019 Jungtaek Kim, Michael McCourt, Tackgeun You, Saehoon Kim, Seungjin Choi

We propose a practical Bayesian optimization method over sets, to minimize a black-box function that takes a set as a single input.

Practical Bayesian Optimization with Threshold-Guided Marginal Likelihood Maximization

1 code implementation18 May 2019 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 guided by a pre-defined threshold.

Model Selection

MxML: Mixture of Meta-Learners for Few-Shot Classification

no code implementations11 Apr 2019 Minseop Park, Jungtaek Kim, Saehoon Kim, Yanbin Liu, Seungjin Choi

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.

General Classification Meta-Learning

On Local Optimizers of Acquisition Functions in Bayesian Optimization

no code implementations24 Jan 2019 Jungtaek Kim, Seungjin Choi

In practice, however, local optimizers of an acquisition function are also used, since searching for the global optimizer is often a non-trivial or time-consuming task.

A Bayesian model for sparse graphs with flexible degree distribution and overlapping community structure

1 code implementation3 Oct 2018 Juho Lee, Lancelot F. James, Seungjin Choi, François Caron

We consider a non-projective class of inhomogeneous random graph models with interpretable parameters and a number of interesting asymptotic properties.

Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace

1 code implementation ICML 2018 Yoonho Lee, Seungjin Choi

Our primary contribution is the {\em MT-net}, which enables the meta-learner to learn on each layer's activation space a subspace that the task-specific learner performs gradient descent on.

Few-Shot Image Classification Meta-Learning

Learning to Warm-Start Bayesian Hyperparameter Optimization

no code implementations17 Oct 2017 Jungtaek Kim, Saehoon Kim, Seungjin Choi

A simple alternative of manual search is random/grid search on a space of hyperparameters, which still undergoes extensive evaluations of validation errors in order to find its best configuration.

Global Optimization Hyperparameter Optimization +1

Bayesian inference on random simple graphs with power law degree distributions

no code implementations ICML 2017 Juho Lee, Creighton Heaukulani, Zoubin Ghahramani, Lancelot F. James, Seungjin Choi

The BFRY random variables are well approximated by gamma random variables in a variational Bayesian inference routine, which we apply to several network datasets for which power law degree distributions are a natural assumption.

Bayesian Inference

Finite-Dimensional BFRY Priors and Variational Bayesian Inference for Power Law Models

no code implementations NeurIPS 2016 Juho Lee, Lancelot F. James, Seungjin Choi

Bayesian nonparametric methods based on the Dirichlet process (DP), gamma process and beta process, have proven effective in capturing aspects of various datasets arising in machine learning.

Bayesian Inference

Gaussian Copula Variational Autoencoders for Mixed Data

no code implementations18 Apr 2016 Suwon Suh, Seungjin Choi

To this end, we employ Gaussian copula to model the local dependency in mixed categorical and continuous data, leading to {\em Gaussian copula variational autoencoder} (GCVAE).

Tree-Guided MCMC Inference for Normalized Random Measure Mixture Models

no code implementations NeurIPS 2015 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.

Learning to Select Pre-Trained Deep Representations with Bayesian Evidence Framework

no code implementations CVPR 2016 Yong-Deok Kim, Taewoong Jang, Bohyung Han, Seungjin Choi

We propose a Bayesian evidence framework to facilitate transfer learning from pre-trained deep convolutional neural networks (CNNs).

Transfer Learning

Bilinear Random Projections for Locality-Sensitive Binary Codes

no code implementations CVPR 2015 Saehoon Kim, Seungjin Choi

In this paper we analyze a bilinear random projection method where feature matrices are transformed to binary codes by two smaller random projection matrices.

Quantization

Bayesian Hierarchical Clustering with Exponential Family: Small-Variance Asymptotics and Reducibility

no code implementations29 Jan 2015 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 clusters to merge.

Convex Optimization for Binary Classifier Aggregation in Multiclass Problems

no code implementations16 Jan 2014 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.

Clustering sequence sets for motif discovery

no code implementations NeurIPS 2009 Jong K. Kim, Seungjin Choi

Most of existing methods for DNA motif discovery consider only a single set of sequences to find an over-represented motif.

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