y

2.1K posts

y

y

@djohnson3272

Sinn Féin

Fort Wayne, IN Katılım Aralık 2013
269 Takip Edilen23 Takipçiler
Sabitlenmiş Tweet
y
y@djohnson3272·
November 3rd should not just be election day but it should also be the day of a general strike.
English
0
0
1
282
y
y@djohnson3272·
@mikepompeo You look like shit Mike. Go to a doctor, you look like you got cancer and RFK's brainworm tried to fuck it out of you.
English
0
0
0
10
y
y@djohnson3272·
@pmarca Amazing!
y tweet mediay tweet media
English
0
0
1
25
Marc Andreessen 🇺🇸
Amazing!
Edgar Dobriban@EdgarDobriban

AI has helped resolve an important question in statistics. In the area of multiple hypothesis testing, the goal of controlling the false discovery rate (FDR) has been introduced in a seminal paper by Benjamini and Hochberg (1995). They also introduced a method (the Benjamini-Hochberg or BH method) and proved it controls the FDR. This method has been widely adopted in modern high-throughput science, including in genomics, astronomy, economics, etc. The paper has has garnered more than 130,000 citations to date. However Benjamini and Hochberg showed FDR control only when the data for the individual tests are *independent*. In practice, these data are often dependent; a good example is data on genetic variants due to linkage disequilibrium. Later work has focused on extending the validity of the BH procedure, e.g., to a form of positive dependence by Benjamini and Yekutieli (2001). The question of when the BH procedure controls the FDR has remained open. Over the last twenty years, many authors, including Reiner-Benaim (2007), Kim and van de Wiel (2008), Benjamini (2010), Sarkar (2023), Sarkar and Zhang (2025), have conjectured that the BH procedure controls the FDR for two-sided tests using any correlated Gaussian data. These authors have presented both theoretical and empirical evidence supporting, but not directly showing, the conjecture. With the help of AI (specifically GPT-5.6 Sol Pro), I have settled the question in the negative: The Benjamini-Hochberg procedure does *not* generally control the false discovery rate at the desired level for correlated two-sided Gaussian tests. This was done by exhibiting a Gaussian factor model for which, at a nominal level alpha=0.01, the false discovery rate is proved to be FDR>0.0104. There is a lot of interesting commentary to be made: 1. This result should be of interest to everybody in the field of statistics. Emmanuel Candes of Stanford University once called the false discovery rate and the Benjamini-Hochberg procedure "one of the two most important developments in statistics after 1950" (the other being James-Stein shrinkage). The present conjecture is probably the most central question about FDR/BH that was unresolved to date. 2. GPT-5.6 one-shot the problem after 90 minutes of reasoning, whereas with 5.5 I was not able to solve it even after iterating with multiple parallel agents for perhaps 20 hours. So the capability improvement is quite real. Exciting times to live in! 3. The argument is not especially surprising, but it does combine an asymptotic approach (standard for FDR analysis, see e.g., Genovese and Wasserman, Efron, etc) with a numerical certificate in a way that would be pretty non-standard in the field. Once we have the specific example, then straightforward simulations also support that the false discovery rate is indeed higher than the nominal value (see attached fig). 4. The current degree of violation over the nominal level is relatively small (0.104 vs 0.1). So the importance of this result is mainly conceptual. The practical implications remain to be determined. Overall, an exciting development! Preprint is available here (faculty.wharton.upenn.edu/wp-content/upl…) and will be on arxiv tonight; supporting code is here (github.com/dobriban/BH).

English
22
19
201
86.2K
y
y@djohnson3272·
@LLkewlG @Indy_reporter_ You voted 3 times for a pedo and continue to support him, go back to England.
English
1
0
0
9
indy reporter
indy reporter@Indy_reporter_·
The Punjabi community is so upset with Indy Reporter that they had to make a video about it. Of course, it’s in another language, so I had to use AI to translate it. They accuse Indy Reporter of spreading false propaganda, using abusive language, and being racist for covering the Sikh/Indian Invasion. If the Punjabi's want a sit down, we are MORE than happy to do that. @desi.junction.indy/video/7662522016293014797?is_from_webapp=1&sender_device=pc&web_id=7658781741859751454" target="_blank" rel="nofollow noopener">tiktok.com/@desi.junction…
English
108
204
774
13.7K
Laura Hill
Laura Hill@LLkewlG·
@Indy_reporter_ My problem with the Sikh community is that they are taking jobs from ancestral Americans..it’s our 250th birthday and Walmart had July 4th decorations but, Indian workers..seems very unpatriotic to me!
Laura Hill tweet mediaLaura Hill tweet mediaLaura Hill tweet media
English
4
0
12
255
y
y@djohnson3272·
@SecWar More like Tiny-d department of War.
English
0
0
1
11
y
y@djohnson3272·
@TheWildOneV1 @HLC_actual You literally support Lindsay "Bubble Wand" Graham and the pedophile president in chief.
English
0
0
0
10
Habitual Linecrosser
Habitual Linecrosser@HLC_actual·
So what’s interesting is a day or so ago I was getting real time info on what Iran hit and where and I shit you not 30 seconds after I found out I saw the IRGC claim responsibility of where was hit on here. They don’t have ISR observing hits. Just saying I ALWAYS KNEW THE LOCALS ON THE BASES WERE IRANIAN SPIES.
English
50
71
2.3K
56.6K
y
y@djohnson3272·
@windy_shrimp @Fat_Electrician If the ceo makes a mistake so bad to put the company in jeopardy of going under he/she shouldn't have been ceo in the first place...
English
0
0
4
83
Windy Shrimp
Windy Shrimp@windy_shrimp·
@Fat_Electrician Also, oversimplified, if the barista makes a mistake the company is out a drink or maybe an appliance. If the CEO makes a mistake possibly the entire corporation collapses and everyone loses their job.
English
4
1
61
1.3K
The Fat Electrician
The Fat Electrician@Fat_Electrician·
Correct. It’s not about the $5 coffee. It’s about the fact that the government keeps adding more regulations and zoning requirements, which increases the cost of building new homes. They do this because the largest voting demographic (baby boomers), who already own homes, benefit when home values continue rising year after year. We have real-life examples. Austin, Texas, eased permitting and some restrictions, built a significant amount of new housing, and has seen lower rents and housing costs as a result. The government is intentionally creating this problem by limiting supply, thus artificially inflating costs to pander to the largest voting demographic.
Elizabeth Warren@SenWarren

CEOs of the largest companies in America make 281 times what the typical worker makes. Since 1978, pay for these CEOs has skyrocketed 1,094%. Typical worker pay? 26%. So no, your $5 coffee isn’t why you can’t afford rent.

English
193
467
5.7K
124.5K
Rep Josh Gottheimer
Rep Josh Gottheimer@RepJoshG·
AI is changing how millions of Americans access information — including about our elections. We can't wait until misinformation spreads to act. That's why @RepMikeLawler and I are pushing the administration to take a coordinated approach to protect every American and make sure AI tools provide accurate, reliable election information. thehill.com/policy/technol…
English
11
1
12
3.5K
y
y@djohnson3272·
@RepJoshG Let's be honest, you are not American. You should go back to Israel and defend "your promised land" with all your heart.
English
0
0
1
21
Rep Josh Gottheimer
Rep Josh Gottheimer@RepJoshG·
I've said it from Day 1: The Administration must come to Congress and brief us and the American people about military action in Iran. Iran cannot be taken at its word. That's why we need to be tough, so Iran can't rebuild its terror, ballistic missile, and nuclear programs — and we can't let them retain control of the Strait of Hormuz. Congress and the American people can't be kept in the dark.
English
15
3
14
2.1K
y
y@djohnson3272·
@telhoff2 @tonykatz @CNBC This is Twitter not school you dumb cunt. If you don't like the way people talk get off the app and get off of life.
English
1
0
0
30
y
y@djohnson3272·
@karol You don't have to include that you're a fucking retarded Russian, you can just go back and be Putin sex bitch til he drops you off a 5th floor balcony.
y tweet media
English
0
0
1
137
y
y@djohnson3272·
@RepStutzman @POTUS @RoKhanna If they claim the West Bank is theirs then there should be no border where he was stopped, so why are terrorists stopping a sitting US Senator is the better question.
English
0
0
0
12
y
y@djohnson3272·
@telhoff2 @tonykatz @CNBC Old people like you are what is keeping Indiana and the rest of country behind. There's some education for you.
y tweet media
English
1
0
0
41
y
y@djohnson3272·
@BrendenWood40 @tonykatz Try it pussy, you can say you want to shot me, be a big boy... too late.
English
0
0
0
32
Brenden Wood
Brenden Wood@BrendenWood40·
@tonykatz Who cares what some random Sinn Féin-loving Communist thinks? As my uncle once said in his Air Force days, "The only thing commies are good for is testing new and improved freedom seeds.' Still true to this day! 🤣🤣🤣
English
2
0
0
37
Tony Katz
Tony Katz@tonykatz·
Just a Monday.
y@djohnson3272

@tonykatz @CNBC You help aid israel you can go fuck yourself. As far as burning an Israeli flag i will do it proudly and there is shit like you cunts can do about except cry antisemitism.

English
7
1
8
2.4K
y
y@djohnson3272·
@telhoff2 @tonykatz @CNBC Aww, I'm sorry, do my words hurt your feelings? Well his actions and dollars are killing kids so fuck your feelings.
English
1
0
0
49
y
y@djohnson3272·
@AndrewIrelandIN If you're Irish, how are you such a fucking cucked pussy bitch.
English
0
0
0
60
Aaron A Roberts
Aaron A Roberts@AaronARoberts·
@djohnson3272 @tonykatz @CNBC Real Americans died so you would have the right to burn whatever flag you want. What do you think happens to people who burn 🇵🇸 flags in the Gaza Strip?
English
1
0
0
77