Angie(Hyunji) Moon @bayesmoon

@mcmc_stan developer, Bayesian and optimization enthusiast, BDA3 translator, CEO of NextOpt amoon.world Joined April 2020

Tweets

80
Followers

161
Following

183
Likes

261

Angie(Hyunji) Moon @bayesmoon

a year ago

🔬 Researchers at #AOM2024! Don't miss Bayesian Statistics: Conduct & Publish High-Quality Studies to learn • Bayesian vs. significance tests • Step-by-step studies • Priors, MCMC, communication Join Bayesian community! Resources available. Register: cdmcd.co/yKQa3A

2 1 9 1K 0

Peyman Milanfar @docmilanfar

3 years ago

Why don’t more people know about the gem that is Tweedie's formula? Say 𝐱 is a noisy measurement of 𝐮 𝐱 = 𝐮 + 𝐞 w/ 𝐞 ∼ 𝒩(𝟎, σ² 𝐈) min mean² estimate of 𝐮 is 𝔼 [𝐮 | 𝐱]. Obviously we need the density P(𝐮|𝐱) right? No! Tweedie says P(𝐱) is all you need! 1/2

8 150 1K 0 536

Download Image

Stan @mcmc_stan

3 years ago

CmdStan 2.30 release candidate is now available. The next release will bring complex vectors and matrices and a number of functions that support them, most notably fast Fourier transform in 1D and 2D and its inverse. 1/2

1 7 48 0 2

Angie(Hyunji) Moon @bayesmoon

4 years ago

Excited to get feedback on the simulation library I am building 🙃

0 0 9 0 1

Angie(Hyunji) Moon @bayesmoon

4 years ago

Prior modeling can be viewed as subjective optimal transport.

0 0 1 0 1

Angie(Hyunji) Moon @bayesmoon

4 years ago

@betanalpha @GuidoBiele @jbakcoleman I view SBC’s role parallel to that of defensive prior. Lesser evil, opt out. May I go one step further to argue “SBC:Valid workflow ~ KKT:Local optimum”? Hardly an iff relation which doesn’t detract KKT’s status as a cheap optimum litmus (with care)!

0 1 0 0 0

Angie(Hyunji) Moon @bayesmoon

4 years ago

@betanalpha @GuidoBiele @jbakcoleman I wish to question the need to test individual posterior when our inference would not be based on its individual version, but rather on its pooled one. SBC as a function of experimental settings would help gauge reliability closet to granularity of its actual use.

0 1 0 0 0

Angie(Hyunji) Moon @bayesmoon

4 years ago

I am honored and excited to be TAing for prof. David Yao’s stochastic modeling class! 🏛 columbia.edu/~yao/

0 0 1 0 1

Shipra Agrawal @ashipra

4 years ago

Looking to hire a Ph.D. student (Fall 2022) and a postdoctoral researcher. More info about each position on this thread. Please help me publicize 🙏

3 132 280 0 36

Angie(Hyunji) Moon @bayesmoon

4 years ago

To math gurus! What is a good mathematical representation for the following? Definitely not identity g . f = I but is there any clever expression?

1 0 4 0 0

Download Image

Angie(Hyunji) Moon @bayesmoon

4 years ago

How would you define adjective “computational”? Exiting from pure theory? Pre-asymptotic? Large scale? Computational [information geometry, biology, optimal transport] what is the difference between them and the ones without? I know the second.

2 0 1 0 0

Steven Strogatz @stevenstrogatz

4 years ago

John von Neumann, a young Richard Feynman, and Stan Ulam. Three of the most original minds of the 20th century. (ht @Ananyo)

32 219 2K 0 90

Download Image

Sam Power @sp_monte_carlo

4 years ago

ahhhhhh

Sam Power @sp_monte_carlo

4 years ago

ahhhhhh https://t.co/EWm8OH5eug

0 2 21 0 2

Download Image

2 7 45 0 6

Download Image

Richard McElreath 🐈‍⬛ @rlmcelreath

4 years ago

no matter how big still just a cat

6 43 377 0 8

Download Image

Angie(Hyunji) Moon @bayesmoon

4 years ago

Probability with structure. Imagine the extra. The answer is here : cut-the-knot.org/m/Probability/…

Alexander Bogomolny @CutTheKnotMath

7 years ago

Probability with structure. Imagine the extra. The answer is here : cut-the-knot.org/m/Probability/…

15 39 117 0 17

Download Image

0 0 0 0 0

Sam Power @sp_monte_carlo

4 years ago

very nice illustration of the difference between coupling Markov chains with a stream of common random numbers either forward or backward in time (from github.com/pierrejacob/co…)