arXiv subjects

Insu Jeon

Publications and source records attributed to Insu Jeon.

5 recordsLinked to original sources

arXiv2025

IB-GAN: Disentangled Representation Learning with Information Bottleneck Generative Adversarial Networks

We propose a new GAN-based unsupervised model for disentangled representation learning. The new model is discovered in an attempt to utilize the Information Bottleneck (IB) framework to the optimization of GAN, thereby named IB-GAN. The architecture of IB-GAN is partially similar to that of InfoGAN but has a critical difference; an intermediate layer of the generator is leveraged to constrain the mutual information between the input and the generated output. The intermediate stochastic layer can serve as a learnable latent distribution that is trained with the generator jointly in an end-to-end fashion. As a result, the generator of IB-GAN can harness the latent space in a disentangled and interpretable manner. With the experiments on dSprites and Color-dSprites dataset, we demonstrate that IB-GAN achieves competitive disentanglement scores to those of state-of-the-art \b{eta}-VAEs and outperforms InfoGAN. Moreover, the visual quality and the diversity of samples generated by IB-GAN are often better than those by \b{eta}-VAEs and Info-GAN in terms of FID score on CelebA and 3D Chairs dataset.

cs.CV↗

arXiv2025

Federated Learning via Meta-Variational Dropout

Federated Learning (FL) aims to train a global inference model from remotely distributed clients, gaining popularity due to its benefit of improving data privacy. However, traditional FL often faces challenges in practical applications, including model overfitting and divergent local models due to limited and non-IID data among clients. To address these issues, we introduce a novel Bayesian meta-learning approach called meta-variational dropout (MetaVD). MetaVD learns to predict client-dependent dropout rates via a shared hypernetwork, enabling effective model personalization of FL algorithms in limited non-IID data settings. We also emphasize the posterior adaptation view of meta-learning and the posterior aggregation view of Bayesian FL via the conditional dropout posterior. We conducted extensive experiments on various sparse and non-IID FL datasets. MetaVD demonstrated excellent classification accuracy and uncertainty calibration performance, especially for out-of-distribution (OOD) clients. MetaVD compresses the local model parameters needed for each client, mitigating model overfitting and reducing communication costs. Code is available at https://github.com/insujeon/MetaVD.

cs.LG↗

arXiv2025

Neural Variational Dropout Processes

Learning to infer the conditional posterior model is a key step for robust meta-learning. This paper presents a new Bayesian meta-learning approach called Neural Variational Dropout Processes (NVDPs). NVDPs model the conditional posterior distribution based on a task-specific dropout; a low-rank product of Bernoulli experts meta-model is utilized for a memory-efficient mapping of dropout rates from a few observed contexts. It allows for a quick reconfiguration of a globally learned and shared neural network for new tasks in multi-task few-shot learning. In addition, NVDPs utilize a novel prior conditioned on the whole task data to optimize the conditional \textit{dropout} posterior in the amortized variational inference. Surprisingly, this enables the robust approximation of task-specific dropout rates that can deal with a wide range of functional ambiguities and uncertainties. We compared the proposed method with other meta-learning approaches in the few-shot learning tasks such as 1D stochastic regression, image inpainting, and classification. The results show the excellent performance of NVDPs.

cs.LG↗

arXiv2025

QuantEvolve: Automating Quantitative Strategy Discovery through Multi-Agent Evolutionary Framework

Automating quantitative trading strategy development in dynamic markets is challenging, especially with increasing demand for personalized investment solutions. Existing methods often fail to explore the vast strategy space while preserving the diversity essential for robust performance across changing market conditions. We present QuantEvolve, an evolutionary framework that combines quality-diversity optimization with hypothesis-driven strategy generation. QuantEvolve employs a feature map aligned with investor preferences, such as strategy type, risk profile, turnover, and return characteristics, to maintain a diverse set of effective strategies. It also integrates a hypothesis-driven multi-agent system to systematically explore the strategy space through iterative generation and evaluation. This approach produces diverse, sophisticated strategies that adapt to both market regime shifts and individual investment needs. Empirical results show that QuantEvolve outperforms conventional baselines, validating its effectiveness. We release a dataset of evolved strategies to support future research.

cs.AI↗

arXiv2021

Highly efficient nonvolatile magnetization switching and multi-level states by current in single van der Waals topological ferromagnet Fe3GeTe2

Robust multi-level spin memory with the ability to write information electrically is a long-sought capability in spintronics, with great promise for applications. Here we achieve nonvolatile and highly energy-efficient magnetization switching in a single-material device formed of van-der-Waals topological ferromagnet Fe3GeTe2, whose magnetic information can be readily controlled by a tiny current. Furthermore, the switching current density and power dissipation are about 400 and 4000 times smaller than those of the existing spin-orbit-torque magnetic random access memory based on conventional magnet/heavy-metal systems. Most importantly, we also demonstrate multi-level states, switched by electrical current, which can dramatically enhance the information capacity density and reduce computing costs. Thus, our observations combine both high energy efficiency and large information capacity density in one device, showcasing the potential applications of the emerging field of van-der-Waals magnets in the field of spin memory and spintronics.

cond-mat.mtrl-sci↗