Khai Xiang Au

Data Scientist | PhD in Statistics

[Alex Thiery @alexxthiery]

I give you 100k points independently & uniformly distributed on a surface of R^3. How to estimate the total area without doing any triangulation etc..

Crude: compute the average distance to the 100th (say) nearest neighbour + do some algebra.

Anything much better?

[Khai Xiang Au @kxau_]

The last time I logged on, the site had a different name and no one could travel.

[Khai Xiang Au @kxau_]

everyone stop what you're doing https://t.co/3NBBtV5rvu

[Nal @nalkalc]

The weather space stands to benefit in a transformative way from deep learning! I am thrilled to share our latest results with MetNet-2:

Blog: https://t.co/IY5yGjbdes
Paper: https://t.co/TsqyXns7CK

[Tom Goldstein @tomgoldsteincs]

I knew this day would come. Our worst fears have finally been realized.

[Prof. Feynman @ProfFeynman]

Knowledge isn't free. You have to pay attention. 🧠

[Khai Xiang Au @kxau_]

The discrete bouncy particle sampler on a toy problem #mcmc

[Khai Xiang Au @kxau_]

https://t.co/5fA94B6OEZ

[Khai Xiang Au @kxau_]

fake footage, no way he's this calm

[Khai Xiang Au @kxau_]

Can't touch this

[MC HAMMER e/acc @MCHammer]

Fourier Neural Operator for Parametric Partial Differential Equations #Hamm400aos https://t.co/ABYRwadcT7

[Greg Brockman @gdb]

OpenAI for converting bullet points into a proper email, now as a Gmail plugin:

[Andrea Montanari @Andrea__M]

I devoted good part of the last 2 years trying to understand interpolators: models with vanishing training error. These behave well when the interpolator is selected via a `min norm' principle. Do I understand this phenomenon better now? A bit, summarized here in a cartoon. 1/n

[Stat.ML Papers @StatMLPapers]

Uncertainty Quantification and Deep Ensembles. (arXiv:2007.08792v1 [https://t.co/zjV5HgYw5a]) https://t.co/ZiRKpGTeMB

[Khai Xiang Au @kxau_]

Check out this work by my colleague @Rahul46113961!

[Alex Thiery @alexxthiery]

In https://t.co/mgUfUrNHRT led by Rahul Rahaman @Rahul46113961 we empirically show that Deep Ensembles do not necessarily lead to better Uncertainty Quantification #UQ -- the focus is on the data-scare setting when this really matters.

[Khai Xiang Au @kxau_]

🤣

[Mason Porter @masonporter]

I am here to help.

[Matt Graham @mattgrahamuk]

A (belated!) tweet thread summary of 'Manifold lifting: scaling MCMC to the vanishing noise regime' recent work with @kxau_ and @alek_thiery. We propose an efficient MCMC method for posteriors concentrated on low-dimensional structures due to highly informative observations.

1/7

[Khai Xiang Au @kxau_]

@UniversalQandA

We are playing Cox Bingo! #briancoxlive

[Khai Xiang Au @kxau_]

@UniversalQandA what will I see if I'm the one moving into the blackhole? #briancoxlive

[Khai Xiang Au @kxau_]

@UniversalQandA how will I experience the orbiting audience if I'm the one moving into the blackhole?

[Andrew Gordon Wilson @andrewgwils]

Talk on Bayesian deep learning, including a philosophy for model construction, understanding loss surfaces, and a function space view of machine learning.
https://t.co/i8uOXqwIFc