Mijung Park | DeepAI

DeepAI AI Chat

Featured Co-authors

Max Welling
161 publications
Xiaoxiao Li
70 publications
Kamalika Chaudhuri
70 publications
Dino Sejdinovic
62 publications
Krikamol Muandet
37 publications
Wittawat Jitkrittum
29 publications
Zoltan Szabo
23 publications
Anant Raj
23 publications
Lars Buesing
20 publications
Jakob H. Macke
20 publications
Danica J. Sutherland
18 publications

∙ 03/08/2023

Differential Privacy Meets Neural Network Pruning

A major challenge in applying differential privacy to training deep neur...

0 Kamil Adamczewski, et al. ∙

∙ 03/03/2023

Differentially Private Neural Tangent Kernels for Privacy-Preserving Data Generation

Maximum mean discrepancy (MMD) is a particularly useful distance metric ...

0 Yilin Yang, et al. ∙

∙ 05/25/2022

Differentially Private Data Generation Needs Better Features

Training even moderately-sized generative models with differentially-pri...

0 Fredrik Harder, et al. ∙

∙ 11/25/2021

DP-SEP! Differentially Private Stochastic Expectation Propagation

We are interested in privatizing an approximate posterior inference algo...

0 Margarita Vinaroz, et al. ∙

∙ 06/09/2021

Polynomial magic! Hermite polynomials for private data generation

Kernel mean embedding is a useful tool to compare probability measures. ...

0 Mijung Park, et al. ∙

∙ 11/10/2020

Dirichlet Pruning for Neural Network Compression

We introduce Dirichlet pruning, a novel post-processing technique to tra...

0 Kamil Adamczewski, et al. ∙

∙ 10/26/2020

Q-FIT: The Quantifiable Feature Importance Technique for Explainable Machine Learning

We introduce a novel framework to quantify the importance of each input ...

0 Kamil Adamczewski, et al. ∙

∙ 02/26/2020

Differentially Private Mean Embeddings with Random Features (DP-MERF) for Simple Practical Synthetic Data Generation

We present a differentially private data generation paradigm using rando...

0 Frederik Harder, et al. ∙

∙ 10/15/2019

DP-MAC: The Differentially Private Method of Auxiliary Coordinates for Deep Learning

Developing a differentially private deep learning algorithm is challengi...

11 Frederik Harder, et al. ∙

∙ 10/11/2019

ABCDP: Approximate Bayesian Computation Meets Differential Privacy

We develop a novel approximate Bayesian computation (ABC) framework, ABC...

0 Mijung Park, et al. ∙

∙ 07/03/2019

Neuron ranking -- an informed way to condense convolutional neural networks architecture

Convolutional neural networks (CNNs) in recent years have made a dramati...

13 Kamil Adamczewski, et al. ∙

∙ 06/05/2019

Interpretable and Differentially Private Predictions

Interpretable predictions, where it is clear why a machine learning mode...

0 Frederik Harder, et al. ∙

∙ 05/29/2019

Private Causal Inference using Propensity Scores

The use of propensity score methods to reduce selection bias when determ...

0 Si Kai Lee, et al. ∙

∙ 02/07/2019

Radial and Directional Posteriors for Bayesian Neural Networks

We propose a new variational family for Bayesian neural networks. We dec...

0 ChangYong Oh, et al. ∙

∙ 08/01/2018

A Differentially Private Kernel Two-Sample Test

Kernel two-sample testing is a useful statistical tool in determining wh...

2 Anant Raj, et al. ∙

∙ 11/01/2016

Variational Bayes In Private Settings (VIPS)

We provide a general framework for privacy-preserving variational Bayes ...

0 Mijung Park, et al. ∙

∙ 09/14/2016

Private Topic Modeling

We develop a privatised stochastic variational inference method for Late...

0 Mijung Park, et al. ∙

∙ 05/24/2016

A note on privacy preserving iteratively reweighted least squares

Iteratively reweighted least squares (IRLS) is a widely-used method in m...

0 Mijung Park, et al. ∙

∙ 05/23/2016

DP-EM: Differentially Private Expectation Maximization

The iterative nature of the expectation maximization (EM) algorithm pres...

0 Mijung Park, et al. ∙

∙ 02/09/2015

K2-ABC: Approximate Bayesian Computation with Kernel Embeddings

Complicated generative models often result in a situation where computin...

0 Mijung Park, et al. ∙

∙ 10/24/2014

Bayesian Manifold Learning: The Locally Linear Latent Variable Model (LL-LVM)

We introduce the Locally Linear Latent Variable Model (LL-LVM), a probab...

0 Mijung Park, et al. ∙

∙ 10/12/2014

Hierarchical models for neural population dynamics in the presence of non-stationarity

Neural population activity often exhibits rich variability and temporal ...

0 Mijung Park, et al. ∙

∙ 02/09/2012

Active Bayesian Optimization: Minimizing Minimizer Entropy

The ultimate goal of optimization is to find the minimizer of a target f...

0 Il Memming Park, et al. ∙