sAM POwEr

Yes!

I think Nicolas Chopin still holds the record of optimality for Gaussian simulation using this, and it was done maybe 10 years ago?

Well yes now that is hard 😂

I thought it was a 1-to-1 thing: N symmetries imply N invariants. But that's 10y old memories so probably wrong!

Is that not essentially Noether's theorem?

I just love the unabashed nerdiness.

World Quantum Day - Wikipedia World Quantum Day is an international event celebrated on April 14 every year. It aims at promoting public awareness and understanding of quantum science and quantum technology around the world.[1][2][3]

> The date April 14 was chosen because "4.14" represents the rounded first 3 digits of the Planck constant: 4.14×10−15 eV·s.

en.wikipedia.org/wiki/World_Q...

For someone people described as nocturnal, he had quite the good sense of humour.

To be precise, Happy World Quantum Day to all the weirdos who observe!

Happy World Quantum Day to all the weirdos out there who celebrate!

What? Are you me?

To be honest, I have found other cyclists' lights to be more of a problem on that front. Super bright LEDs, pointing upwards, it's completely blinding, especially on otherwise unlit paths. Particularly problematic with e-bikes/carriers where they often come in pairs (handlebar+frame).

A fun beginner stochastic calculus exercise is to see how the start (Ito) and mid (Stratonovich) integration rules generalise to any point αtᵢ₊₁ + (1-α)tᵢ and how the drift correction to Ito looks like in that case.

A recurring debate in the philosophy of statistics concerns what, exactly, should count as a measure of evidence for or against a given hypothesis. P-values, likelihood ratios, and Bayes factors all have their defenders. In this paper we add two additional candidates to this list: the e-value and its sequential analogue, the e-process. E-values enjoy several desirable properties as measures of evidence: they combine naturally across studies, handle composite hypotheses, provide long-run error rates, and admit a useful interpretation as the wealth accrued by a bettor in a game against the null distribution. E-processes additionally handle optional stopping and optional continuation. This work examines the extent to which e-values and e-processes satisfy the evidential desiderata of different statistical traditions, concluding that they combine attractive features of p-values, likelihood ratios, and Bayes factors, and merit serious consideration as interpretable and intuitive measures of statistical evidence.

arXiv📈🤖
E-values as statistical evidence: A comparison to Bayes factors, likelihoods, and p-values
By Chugg, Ramdas, Gr\"unwald

You should write a post about it.

| Flag Filename | Components for 95% Var
--------
1 | Saint_Pierre_and_Miquelon.png | 45
2 | Afghanistan.png | 39
3 | Turkmenistan.png | 39

Google Colab

colab.research.google.com/drive/1ErRQV...

-> how many components for a 95% explained variance

You can do a flag ranking based on how many components are needed to recover them.

Ahah are you calling the freedom flag boring?

Did you get your right to remain?

The registration closes on 31 March and there are only a number of slots left --- register before they run out :)

More seriously, these days I'm just pragmatic about it. Some communities care, some don't, neither of them have it right nor wrong, and we need to help them both.

Para-meters are beside the point.

The title is the real highlight though

front of medal featuring beautiful artwork of a person holding a sword, with a halo and flames around them. Also a card saying "It is an Honor to acknowledge Fractal Karma [by] Arula Ratnakar as a finalist for the 2025 Ignyte Award for Outstanding Novella"

Other side of the medal and the card, featuring the painting version of what was carved on the medal. It is beautiful art by Nilah Magruder!

My finalist medal from the Ignyte Awards arrived today for my scifi novella "Fractal Karma" which was a finalist in 2025

Made me tear up, it's beautiful

If you want to read my story, it's available here. 2050's Boston and a hivemind based on Brunnian links: clarkesworldmagazine.com/ratnakar_10_...

Bayesian Quadrature: Gaussian Processes for Integration Bayesian quadrature is a probabilistic, model-based approach to numerical integration, the estimation of intractable integrals, or expectations. Although Bayesian quadrature was popularised already in...

Clearly a must read for anyone even remotely interested in numerical integration (be it stochastic and deterministic).

Toni has been (hyper)active in studying these methods both theoretically and practically.

arxiv.org/abs/2602.16218

Couillard in french. Also means "he who has big balls".

Happy birthday!