Search Results for author: Namjoon Suh

Found 10 papers, 1 papers with code

Discriminative Estimation of Total Variation Distance: A Fidelity Auditor for Generative Data

no code implementations24 May 2024 Lan Tao, SHIRONG XU, Chi-Hua Wang, Namjoon Suh, Guang Cheng

In particular, this paper establishes theoretical results regarding the convergence rate of the estimation error of TV distance between two Gaussian distributions.

Approximation of RKHS Functionals by Neural Networks

no code implementations18 Mar 2024 Tian-Yi Zhou, Namjoon Suh, Guang Cheng, Xiaoming Huo

Motivated by the abundance of functional data such as time series and images, there has been a growing interest in integrating such data into neural networks and learning maps from function spaces to R (i. e., functionals).

regression Time Series

Theoretical Understanding of In-Context Learning in Shallow Transformers with Unstructured Data

no code implementations1 Feb 2024 Yue Xing, Xiaofeng Lin, Chenheng Xu, Namjoon Suh, Qifan Song, Guang Cheng

We observe that (1) a transformer with two layers of (self-)attentions with a look-ahead attention mask can learn from the prompt in the unstructured data, and (2) positional encoding can match the $x_i$ and $y_i$ tokens to achieve a better ICL performance.

In-Context Learning

AutoDiff: combining Auto-encoder and Diffusion model for tabular data synthesizing

1 code implementation24 Oct 2023 Namjoon Suh, Xiaofeng Lin, Din-Yin Hsieh, Merhdad Honarkhah, Guang Cheng

Diffusion model has become a main paradigm for synthetic data generation in many subfields of modern machine learning, including computer vision, language model, or speech synthesis.

Language Modelling Speech Synthesis +1

On Excess Risk Convergence Rates of Neural Network Classifiers

no code implementations26 Sep 2023 Hyunouk Ko, Namjoon Suh, Xiaoming Huo

The recent success of neural networks in pattern recognition and classification problems suggests that neural networks possess qualities distinct from other more classical classifiers such as SVMs or boosting classifiers.

Binary Classification

Generalization of Overparametrized Deep Neural Network Under Noisy Observations

no code implementations ICLR 2022 Namjoon Suh, Hyunouk Ko, Xiaoming Huo

We study the generalization properties of the overparameterized deep neural network (DNN) with Rectified Linear Unit (ReLU) activations.

Asymptotic Theory of $\ell_1$-Regularized PDE Identification from a Single Noisy Trajectory

no code implementations12 Mar 2021 Yuchen He, Namjoon Suh, Xiaoming Huo, Sungha Kang, Yajun Mei

We provide a set of sufficient conditions which guarantee that, from a single trajectory data denoised by a Local-Polynomial filter, the support of $\mathbf{c}(\lambda)$ asymptotically converges to the true signed-support associated with the underlying PDE for sufficiently many data and a certain range of $\lambda$.

Factor Analysis on Citation, Using a Combined Latent and Logistic Regression Model

no code implementations2 Dec 2019 Namjoon Suh, Xiaoming Huo, Eric Heim, Lee Seversky

We propose a combined model, which integrates the latent factor model and the logistic regression model, for the citation network.

regression

Review on Parameter Estimation in HMRF

no code implementations20 Nov 2017 Namjoon Suh

In following section, we expand this idea on estimating parameters in Gaussian Hidden Markov Spatial-Temporal Random Field, and display results on two performed experiments.

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