Namjoon Suh — accepted AI-conference papers

2026

TimeAutoDiff: A Unified Framework for Generation, Imputation, Forecasting, and Time-Varying Metadata Conditioning of Heterogeneous Time Series Tabular Data

Namjoon Suh, Yuning Yang, Din-Yin Hsieh, Qitong Luan, Shirong Xu, Shixiang Zhu +1

ICML 2026poster

We present \texttt{TimeAutoDiff}, a unified latent-diffusion framework that addresses four fundamental time-series tasks—unconditional generation, missing-data imputation, forecasting, and time-varying-metadata conditional generation—within a single model that natively handles heterogeneous features…

Cited by 0 Source ↗code ↗Scholar ↗

2023

Approximation and non-parametric estimation of functions over high-dimensional spheres via deep ReLU networks

Namjoon Suh, Tian-Yi Zhou, Xiaoming Huo

ICLR 2023poster

We develop a new approximation and estimation analysis of deep feed-forward neural networks (FNNs) with the Rectified Linear Unit (ReLU) activation. The functions of interests for the approximation and estimation are assumed to be from Sobolev spaces defined over the $d$-dimensional unit sphere with…

Cited by 7 Source ↗PDF ↗Scholar ↗

2022

A NON-PARAMETRIC REGRESSION VIEWPOINT : GENERALIZATION OF OVERPARAMETRIZED DEEP RELU NETWORK UNDER NOISY OBSERVATIONS

Namjoon Suh, Hyunouk Ko, Xiaoming Huo

ICLR 2022poster

We study the generalization properties of the overparameterized deep neural network (DNN) with Rectified Linear Unit (ReLU) activations. Under the non-parametric regression framework, it is assumed that the ground-truth function is from a reproducing kernel Hilbert space (RKHS) induced by a neural t…

Cited by 13 Source ↗PDF ↗Scholar ↗