Jun Wu

Jun Wu

Posts by Tags

CART

EM algorithm

Variational Inference

4 minute read

Published:

1.Latent variable models and EM algorithm

We want to model a high dimension random vector $\boldsymbol{x}$, which can often be described by only a few latent factors $\boldsymbol{z}$. LVM take a two-step generation scheme:

category1

Blog Post number 4

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 3

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 2

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 1

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

category2

Blog Post number 4

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 3

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 2

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 1

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

causal inference

causality

Covergence cross mapping

8 minute read

Published:

1.Background

Convergent Cross Mapping (CCM) is a method for establishing causality from long time series data (\(\geq 25\) observations). The method was first proposed in 1990 by Sugihara et al and revisited in 2012.

cool posts

Blog Post number 4

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 3

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 2

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 1

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

directed acyclic graph

Learning the difference DAG between structural equation models

8 minute read

Published:

The paper “Direct Learning with Guarantees of the Difference DAG Between Structural Equation Models” by Asish Ghoshal, Kevin Bello and Jean Honorio studies the problem of directly estimating the structural difference between two structural equation models (SEMs) with the same topological ordering.

double machine learning

machine learning

Variational Inference

4 minute read

Published:

1.Latent variable models and EM algorithm

We want to model a high dimension random vector $\boldsymbol{x}$, which can often be described by only a few latent factors $\boldsymbol{z}$. LVM take a two-step generation scheme:

Basic Normalizing Flow

1 minute read

Published:

1.Change of variables formula

Normalizing Flows (NF) can model flexible distributions for data sampling and density estimation. The idea is based on change of variables formula, applying a series of transformations on a simple distribution to approximate a complex distribution.

normalizing flow

Basic Normalizing Flow

1 minute read

Published:

1.Change of variables formula

Normalizing Flows (NF) can model flexible distributions for data sampling and density estimation. The idea is based on change of variables formula, applying a series of transformations on a simple distribution to approximate a complex distribution.

structural equation model

Learning the difference DAG between structural equation models

8 minute read

Published:

The paper “Direct Learning with Guarantees of the Difference DAG Between Structural Equation Models” by Asish Ghoshal, Kevin Bello and Jean Honorio studies the problem of directly estimating the structural difference between two structural equation models (SEMs) with the same topological ordering.

theory

Learning the difference DAG between structural equation models

8 minute read

Published:

The paper “Direct Learning with Guarantees of the Difference DAG Between Structural Equation Models” by Asish Ghoshal, Kevin Bello and Jean Honorio studies the problem of directly estimating the structural difference between two structural equation models (SEMs) with the same topological ordering.

time series

Covergence cross mapping

8 minute read

Published:

1.Background

Convergent Cross Mapping (CCM) is a method for establishing causality from long time series data (\(\geq 25\) observations). The method was first proposed in 1990 by Sugihara et al and revisited in 2012.

treatment effect

variational inference

Variational Inference

4 minute read

Published:

1.Latent variable models and EM algorithm

We want to model a high dimension random vector $\boldsymbol{x}$, which can often be described by only a few latent factors $\boldsymbol{z}$. LVM take a two-step generation scheme: