Reposted by Yan
I can't* fathom why the top picture, and not the bottom picture, is the standard diagram for an autoencoder.
The whole idea of an autoencoder is that you complete a round trip and seek cycle consistency—why lay out the network linearly?
The whole idea of an autoencoder is that you complete a round trip and seek cycle consistency—why lay out the network linearly?
August 29, 2025 at 10:46 PM
I can't* fathom why the top picture, and not the bottom picture, is the standard diagram for an autoencoder.
The whole idea of an autoencoder is that you complete a round trip and seek cycle consistency—why lay out the network linearly?
The whole idea of an autoencoder is that you complete a round trip and seek cycle consistency—why lay out the network linearly?
Reposted by Yan
If you're playing rock, paper, scissors against a Republican, pick paper. www.pbump.net/o/how-to-win...
August 14, 2025 at 6:33 PM
If you're playing rock, paper, scissors against a Republican, pick paper. www.pbump.net/o/how-to-win...
Reposted by Yan
After 3 1/2 years of work my course on quantum computing is finally finished — the "Director's Cut" of Understanding Quantum Information and Computation is now available.
arxiv.org/abs/2507.11536
arxiv.org/abs/2507.11536
Understanding Quantum Information and Computation
This is a course on the theory of quantum computing. It consists of 16 lessons, each with a video and written component, covering the basics of quantum information, quantum algorithms (including query...
arxiv.org
July 16, 2025 at 11:06 AM
After 3 1/2 years of work my course on quantum computing is finally finished — the "Director's Cut" of Understanding Quantum Information and Computation is now available.
arxiv.org/abs/2507.11536
arxiv.org/abs/2507.11536
Reposted by Yan
Jensen's inequality gives the difference between the average value of a convex function φ, and its value at the center, where both “average” and “center” are defined in terms of some distribution p_X.
When the function φ is flat, or the distribution is narrow, they agree.
When the function φ is flat, or the distribution is narrow, they agree.
May 2, 2025 at 7:28 PM
Jensen's inequality gives the difference between the average value of a convex function φ, and its value at the center, where both “average” and “center” are defined in terms of some distribution p_X.
When the function φ is flat, or the distribution is narrow, they agree.
When the function φ is flat, or the distribution is narrow, they agree.
Reposted by Yan
Overfitting is among the conceptually most interesting problems in machine learning.
I am happy of several new phenomena we began to understand with Pierfrancesco Urbani.
Alert: mostly non-rigorous! (Celebrating Jorge Kurchan)
web.stanford.edu/~montanar/OT...
I am happy of several new phenomena we began to understand with Pierfrancesco Urbani.
Alert: mostly non-rigorous! (Celebrating Jorge Kurchan)
web.stanford.edu/~montanar/OT...
web.stanford.edu
April 30, 2025 at 8:23 PM
Overfitting is among the conceptually most interesting problems in machine learning.
I am happy of several new phenomena we began to understand with Pierfrancesco Urbani.
Alert: mostly non-rigorous! (Celebrating Jorge Kurchan)
web.stanford.edu/~montanar/OT...
I am happy of several new phenomena we began to understand with Pierfrancesco Urbani.
Alert: mostly non-rigorous! (Celebrating Jorge Kurchan)
web.stanford.edu/~montanar/OT...
Reposted by Yan
You can bound Rényi divergences in terms of KL divergences for tilted distributions. This is useful e.g. for Gaussians, where tilting just corresponds to shifting the distribution.
April 26, 2025 at 8:03 PM
Reposted by Yan
We’re proud to share that 46 members have been elected as 2025 ASA Fellows! This honor recognizes contributions to research, education, industry, government, and service to ASA and the broader statistical community. Congrats to this year’s class of Fellows! www.amstat.org/news-listing...
April 22, 2025 at 12:28 PM
We’re proud to share that 46 members have been elected as 2025 ASA Fellows! This honor recognizes contributions to research, education, industry, government, and service to ASA and the broader statistical community. Congrats to this year’s class of Fellows! www.amstat.org/news-listing...
Reposted by Yan
Reposted by Yan
In the Notices of the AMS: "Selected Results from the Mathematical Conventions Survey." Is 0 a natural number? Does ⊂ mean subset or proper subset? Is f(x)=3 an increasing function? Is f(x)=3x+1 a linear function?
www.ams.org/journals/not...
www.ams.org/journals/not...
AMS :: Notices of the American Mathematical Society
www.ams.org
March 20, 2025 at 2:53 PM
In the Notices of the AMS: "Selected Results from the Mathematical Conventions Survey." Is 0 a natural number? Does ⊂ mean subset or proper subset? Is f(x)=3 an increasing function? Is f(x)=3x+1 a linear function?
www.ams.org/journals/not...
www.ams.org/journals/not...
Reposted by Yan
Research briefing: A quantum microsatellite that has been developed and launched can perform space-to-ground quantum communication using portable ground stations.
https://go.nature.com/41Bzouc
https://go.nature.com/41Bzouc
A practical leap towards secure quantum communication over long distances
A lightweight microsatellite and portable ground stations enable efficient quantum key distribution from space to Earth.
go.nature.com
March 20, 2025 at 11:00 AM
Research briefing: A quantum microsatellite that has been developed and launched can perform space-to-ground quantum communication using portable ground stations.
https://go.nature.com/41Bzouc
https://go.nature.com/41Bzouc
Reposted by Yan
oh cool news in the red there!
March 9, 2025 at 7:37 PM
oh cool news in the red there!
Reposted by Yan
You may have seen the handy inequality n! ≥ (n/e)ⁿ.
I didn't know its proof, at least not this short, beautiful one. It's so elegant.
I didn't know its proof, at least not this short, beautiful one. It's so elegant.
March 4, 2025 at 8:37 AM
You may have seen the handy inequality n! ≥ (n/e)ⁿ.
I didn't know its proof, at least not this short, beautiful one. It's so elegant.
I didn't know its proof, at least not this short, beautiful one. It's so elegant.
Reposted by Yan
It’s by no means something they had to do! The American Physical Society has kept their DEI pages up. I think I might write them an email to thank them
www.aps.org/initiatives/...
www.aps.org/initiatives/...
Inclusive Physics
We're committed to fostering a welcoming physics community where everyone passionate about science can succeed.
www.aps.org
February 3, 2025 at 9:12 AM
It’s by no means something they had to do! The American Physical Society has kept their DEI pages up. I think I might write them an email to thank them
www.aps.org/initiatives/...
www.aps.org/initiatives/...
Reposted by Yan
This review paper by @guillaume-garrigos.com on SGD-related algorithms is a fantastic resource, offering elegant, self-contained, and concise proofs in a single, accessible reference. arxiv.org/pdf/2301.11235
January 29, 2025 at 4:15 PM
This review paper by @guillaume-garrigos.com on SGD-related algorithms is a fantastic resource, offering elegant, self-contained, and concise proofs in a single, accessible reference. arxiv.org/pdf/2301.11235
Reposted by Yan
Bravo to 1st-year undergraduate Tyler Yang at CMU, who was the first person to write up and make videos for all* 100 exercises in my "Quantum Computer Programming in 100 Easy Lessons" series! (www.youtube.com/watch?v=XtDJ...)
*more or less all
*more or less all
#1/100: Toggling qubits || Quantum Computer Programming in 100 Easy Lessons
YouTube video by Ryan O'Donnell
www.youtube.com
January 8, 2025 at 3:03 AM
Bravo to 1st-year undergraduate Tyler Yang at CMU, who was the first person to write up and make videos for all* 100 exercises in my "Quantum Computer Programming in 100 Easy Lessons" series! (www.youtube.com/watch?v=XtDJ...)
*more or less all
*more or less all
Reposted by Yan
ArXiv continues to grow. Here is the year-on-year comparison for the categories with 1000+ submissions. Overall, 17% growth in submissions from 2023 to 2024 (208,493 -> 244,031)
January 6, 2025 at 4:21 AM
ArXiv continues to grow. Here is the year-on-year comparison for the categories with 1000+ submissions. Overall, 17% growth in submissions from 2023 to 2024 (208,493 -> 244,031)
Reposted by Yan
Humans vs Ants: Problem-solving Skills
December 25, 2024 at 5:12 PM
Humans vs Ants: Problem-solving Skills
Reposted by Yan
The set of ways to learn linear algebra is convex
December 24, 2024 at 5:57 PM
The set of ways to learn linear algebra is convex
Reposted by Yan
ALT 2025 Conference
Welcome to the OpenReview homepage for ALT 2025 Conference
openreview.net
December 18, 2024 at 5:45 PM
Reposted by Yan
Is life fair? Short answer: no. Long answer: noooooooooo.
December 15, 2024 at 11:09 PM
Is life fair? Short answer: no. Long answer: noooooooooo.
Reposted by Yan
The slides of my NeurIPS lecture "From Diffusion Models to Schrödinger Bridges - Generative Modeling meets Optimal Transport" can be found here
drive.google.com/file/d/1eLa3...
drive.google.com/file/d/1eLa3...
BreimanLectureNeurIPS2024_Doucet.pdf
drive.google.com
December 15, 2024 at 6:40 PM
The slides of my NeurIPS lecture "From Diffusion Models to Schrödinger Bridges - Generative Modeling meets Optimal Transport" can be found here
drive.google.com/file/d/1eLa3...
drive.google.com/file/d/1eLa3...
Reposted by Yan
In case you missed my awesome post doc Arthur da Cunha's Oral Presentation of our "Optimal Parallelization of Boosting" at #NeurIPS2024, I recorded a (slightly extended) version here.
youtu.be/BGZJMwhQc4U
youtu.be/BGZJMwhQc4U
December 13, 2024 at 5:53 PM
In case you missed my awesome post doc Arthur da Cunha's Oral Presentation of our "Optimal Parallelization of Boosting" at #NeurIPS2024, I recorded a (slightly extended) version here.
youtu.be/BGZJMwhQc4U
youtu.be/BGZJMwhQc4U
Reposted by Yan
If at NeurIPS on Friday, consider stopping by Eren Sasoglu's poster on 'Scaling laws for learning with real and surrogate data' arxiv.org/abs/2402.04376
Often training on a mixture of data from the target distribution and from a surrogate distribution yields better models than training on either.
Often training on a mixture of data from the target distribution and from a surrogate distribution yields better models than training on either.
December 12, 2024 at 8:37 PM
If at NeurIPS on Friday, consider stopping by Eren Sasoglu's poster on 'Scaling laws for learning with real and surrogate data' arxiv.org/abs/2402.04376
Often training on a mixture of data from the target distribution and from a surrogate distribution yields better models than training on either.
Often training on a mixture of data from the target distribution and from a surrogate distribution yields better models than training on either.
Reposted by Yan
I'm pleased to share that our recent paper with @2ptmvd has been accepted to the Philoshophical Transactions of the Royal Society. Here's the ‘Accepted Author Version’:
drive.google.com/file/d/1jdtr...
And here it is on arxiv without the fancy formatting:
arxiv.org/abs/2409.06219
1/3
drive.google.com/file/d/1jdtr...
And here it is on arxiv without the fancy formatting:
arxiv.org/abs/2409.06219
1/3
December 11, 2024 at 3:36 AM
I'm pleased to share that our recent paper with @2ptmvd has been accepted to the Philoshophical Transactions of the Royal Society. Here's the ‘Accepted Author Version’:
drive.google.com/file/d/1jdtr...
And here it is on arxiv without the fancy formatting:
arxiv.org/abs/2409.06219
1/3
drive.google.com/file/d/1jdtr...
And here it is on arxiv without the fancy formatting:
arxiv.org/abs/2409.06219
1/3
Reposted by Yan
How are Kernel Smoothing in statistics, Data-Adaptive Filters in image processing, and Attention in Machine Learning related?
My goal is not to argue who should get credit for what, but to show a progression of closely related ideas over time and across neighboring fields.
1/n
My goal is not to argue who should get credit for what, but to show a progression of closely related ideas over time and across neighboring fields.
1/n
December 8, 2024 at 9:45 PM
How are Kernel Smoothing in statistics, Data-Adaptive Filters in image processing, and Attention in Machine Learning related?
My goal is not to argue who should get credit for what, but to show a progression of closely related ideas over time and across neighboring fields.
1/n
My goal is not to argue who should get credit for what, but to show a progression of closely related ideas over time and across neighboring fields.
1/n