We hold SDS reading seminars irregularly, depending on our schedules.
Speakers are primarily students, and they give a talk about recent papers or general topics in statistics and data science.
2024
[Oct 10]
Transformers are Minimax Optimal Nonparametric In-Context Learners
Presented by Hyeok Kyu Kwon. [Slides]
[Sep 26]
Transfer Learning for Nonparametric Regression: Non-Asymptotic Minimax Analysis
Presented by Dongguen Kim. [Slides]
[Sep 03]
Statistical Optimality of Online SGD
Presented by Jeyong Lee. [Slides]
[Aug 20]
Density Ratio Estimation in Fair Generative Modeling
Presented by Myeongsoo Kim. [Slides]
[Aug 08]
Wavelet theory for function approximation
Presented by Jeongjik Lee. [Slides]
[Sep 18]
Normalizing Flow for Discrete Random Variable
Presented by Junhyeok Choi. [Slides]
[Sep 14]
Algorithms for Group Distributionally Robust Optimization with Application
Presented by Sungho Jo. [Slides]
[Aug 31]
Neural Tangent Kernel with an Infinitely Wide Neural Network
Presented by Dongguen Kim. [Slides]
[Aug 24]
HyperBandit: Contextual Bandit with Hypernetwork for Time-Varying User Preferences in Streaming Recommendation
Presented by Jeongjik Lee. [Slides]
[Aug 16]
Stable Diffusion and Guidance Sampling
Presented by Hyeok Kyu Kwon. [Slides]
[Aug 11]
Statistical Efficiency of Score Matching
Presented by Jeyong Lee. [Slides]
[Jul 27]
Learning Models with Uniform Performance via Distributionally Robust Optimization
Presented by Seonghwi Kim. [Slides]
[Jul 20]
The Methods to Improve Bayesian Neural Networks
Presented by Junhyeok Choi. [Slides]
[Jul 13]
Wasserstein Distributional Robustness Framework for Adversarial Training
Presented by Sungho Jo. [Slides]
[Jul 05]
Sub-sampling Algorithms in Multi-Armed Bandit
Presented by Dongguen Kim. [Slides]
[Jul 05]
Accelerate Sampling Methods of Diffusion Model
Presented by Myeongsoo Kim. [Slides]
[Jun 22]
MCMC Methods Using Normalizing Flows
Presented by Hyeok Kyu Kwon. [Slides]
[Jun 22]
Architecture of Diffusion Models
Presented by Jaeseung Yang. [Slides]
[Jun 15]
Grouped Variable Selection with Discrete Optimization
Presented by Jeongjik Lee. [Slides]
[Jun 08]
Bayesian Asymptotics and Variational Approximation
Presented by Jeyong Lee. [Slides]
[May 18]
Scalable Laplace Approximation for Bayesian Neural Network
Presented by Junhyeok Choi. [Slides]
[May 11]
Unsupervised Deep Embedding for Clustering
Presented by Suhyun Park. [Slides]
[May 04]
Distributionally Robust Neural Networks for Group Shift
Presented by Sungho Jo. [Slides]
[Apr 27]
Offline Change Point Detection Methods :
Optimal Search Method, PELT
Presented by Hye-young Kim. [Slides]
[Apr 20] POEM: Out-of-Distribution Detection with Posterior Sampling
Presented by Dongguen Kim. [Slides]
[Apr 07] Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network
Presented by Somin Lee. [Slides]
[Apr 07] Inferring Causal Impact Using Bayesian Structural Time-Series Models
Presented by Myeongsoo Kim. [Slides]
[Mar 31] Normalizing Flows
Presented by Hyeok Kyu Kwon. [Slides]
[Mar 16] USG-Net: Deep Learning-based Ultrasound
Scanning-Guide for an Orthopedic Sonographer /
Stochastic Adaptive Activation Function
Presented by Jaeseung Yang. [Slides]
[Mar 09] Hidden Markov Model: Infernce and its Applications
Presented by Kyungmin Kim. [Slides]
[Mar 02] Minimax Optimal Deep Neural Network Classifiers under Smooth Decision Boundary
Presented by Jeongjik Lee. [Slides]
[Feb 14] Meta-Prod2Vec Model for Addressing Item Cold Problem in Recommender Systems
Presented by Suhyun Park. [Slides]
[Feb 14] Markov Chain Convergence Theory 1 : Finite State Space
Presented by Jeyong Lee. [Slides]
[Feb 08] Robust Optimization Approach to Deep Learning
Presented by Sungho Jo. [Slides]