Behrad Moniri

Machine Learning Researcher | Interested in High-Dimensional Phenomena.

[Behrad Moniri @bemoniri]

Our recent work on the theory of feature learning in two layer networks that we just uploaded to arXiv:

https://t.co/XU3c61Y6zb

[Dan Roy @roydanroy]

Statistics as a field has not historically oriented itself around formalized open problems. Part of the reason is that the hardest problems in the field are ones of formalizing what the problem even is. Once you formalize a problem, much of the work may be done. Of course, there are counter examples, but, if I were to cast statistics as an AI problem, I think the bulk of (impactful) statistics is closer to auto-formalization than to theorem proving.

[Behrad Moniri @bemoniri]

@EdgarDobriban I think the interesting question now is how to fix BH. I tried reading the argument carefully but I really couldn't clearly see what went wrong with BH. I think this is a problem with such AI generated proofs ... The counter example somehow feels out of context (at least to me).

[Behrad Moniri @bemoniri]

@EdgarDobriban Wow. Interesting result, Edgar!

[Behrad Moniri @bemoniri]

X has also recently turned into a casino! Why?

[Behrad Moniri @bemoniri]

Thr city is filled with gambling ads. Everywhere I go I see them. Aren't these things supposed to be highly regulated?

"Trade the beautiful game"? I don't even understand what they even mean! What does "trade" mean?

[Behrad Moniri @bemoniri]

Thr city is filled with gambling ads. Everywhere I go I see them. Aren't these things supposed to be highly regulated?

"Trade the beautiful game"? I don't even understand what they even mean! What does "trade" mean?

[Behrad Moniri @bemoniri]

They are such a great team. So sad that they were eventually eliminated. It was very inspiring to see a team with players from the third division of the German league etc. play this well against the world champion!

[Behrad Moniri @bemoniri]

Go Cape Verde!

[Behrad Moniri @bemoniri]

@samthesnkwman @roozbehp حرف شما غلط است و چند صد سال هست که انواع دیگری از احتمال وجود دارد که نیازی به پدیده‌های تکرار شونده ندارد. اتفاقاً بسیار هم به درد بخور هستند.

https://t.co/4anozRCDRP

[Behrad Moniri @bemoniri]

@roozbehp کتاب مقدماتی خوبی در این رابطه وجود دارد که به علاقه‌مندان توصیه میکنم:

Philosophical Theories of Probability
Donald Gillies

[Behrad Moniri @bemoniri]

@1058_1111 در حال تماشای بازی نبودم، ولی بله! بین انگلیس و غنا، طرفدار غنا هستم.

[Behrad Moniri @bemoniri]

@SebastienBubeck @AlexKontorovich I just can't understand on what point exactly you disagree with Alex.

I guess disagreeing with these comments is part of the job, lol.

[Behrad Moniri @bemoniri]

unreasonably delayed or unlawfully withheld immigration benefits:

[Alvaro Lozano-Robledo @mathandcobb]

The Riemann Hypothesis, the Goldbach conjecture, the Twin Prime conjecture... They have all been extensively verified numerically. So for all practical purposes, these are "true" statements. If needed for an actual practical use, they could easily be verified even farther.

The mathematical truth of these statements would only be "useful" to mathematicians that seek the truth and those who seek to understand *why* these statements are true.

If an AI agent proved these statements but there were no mathematicians to understand and digest the proofs, what would be the point of such a proof?

Even in the most optimistic of cases, where a super human mathematician agent exists that could prove or disprove (or declare undecideable) every statement, either there are human mathematicians that are there to understand the proof to explain it to other humans... Or there is simply no point for such a super human agent to exist in the first place.

[Behrad Moniri @bemoniri]

@_Mindchatter_ @minilek @grok If you are really interested (which tbh, I doubt it): I encourage you to read the research by Cato Institute (a libertarian think-tank) answering the exact same question. If you read it properly (and think about it for a minutes), It will change you view:

https://t.co/JCRI82OLlF

[Behrad Moniri @bemoniri]

If you see some weird processes are eating most of the RAM and CPU on your Mac: it’s probably a known issue that @Apple is too lazy to fix:

https://t.co/gKq5gejzzJ

[Yann LeCun @ylecun]

Why?

[Behrad Moniri @bemoniri]

@deliprao @wtgowers Not talking about Prof. Gowers (obviously, I respect him immensely). Many of these posts you are talking about are from "ex"-academics. Many of them work in the PR departments of AI companies these days and get paid.

[Behrad Moniri @bemoniri]

@KrzakalaF Thanks, Florent!

[Behrad Moniri @bemoniri]

Our recent work on the theory of feature learning in two layer networks that we just uploaded to arXiv:

https://t.co/XU3c61Y6zb