Profile avatar
hadivafaii.bsky.social
Postdoc at UC Berkeley, Redwood Center | ๐Ÿง ๐Ÿค– | ๐ŸŽน | ๐ŸŽพ | https://mysterioustune.com/
76 posts 687 followers 141 following
Getting Started
Active Commenter
comment in response to post
Thanks for the clarification! "sufficiently well defined" Too much overfitting to toy problems (i.e., physics)? I doubt this is even possible in the most important scientific challenge of our time: understanding complex systems
comment in response to post
Thanks for sharing. I am also doing my best to spread the word ๐Ÿ™‚ (see top left) From: openreview.net/forum?id=ekt...
comment in response to post
What do you mean by opportunistic? Let me guess: Science is not about truth-seeking. Rather, it's about optimizing some utility function, which may or may not contain elements of truth-seeking, depending on the context and which part of science we're discussing.
comment in response to post
That's all, folks. I'll be back with Part 2 (and beyond) once they're up. Thanks for reading this far. I hope it sparked your curiosity. (here's the link again: mysterioustune.com/2025/01/13/w...) P.S. If you enjoyed this thread, I'd love to hear your thoughts. ๐Ÿงต[16/n] ๐Ÿง ๐Ÿค–๐Ÿง ๐Ÿ“ˆ #AI
comment in response to post
I end with a call to action: We are each gifted a finite amount of time on this earth. How will you spend yours? Chasing fleeting distractions? Or contributing to humanity's deepest, longest ongoing questโ€”minimizing our collective KL divergence? Your choice. ๐Ÿงต[15/n] ๐Ÿง ๐Ÿค–๐Ÿง ๐Ÿ“ˆ #AI
comment in response to post
In the season finale (Part X), I will go all-in on speculation: p_brain is the all-encompassing object, swallowing everything. Even physics. In that sense, all of science and philosophy merge into a single pursuit: โžก๏ธ Humanity's collective KL minimization. ๐Ÿงต[14/n]
comment in response to post
But hold on a second. Weโ€™re not done yet. It turns out, I need 10 more parts to finish the full story arc. Hereโ€™s what I have in mind next: ๐Ÿงต[13/n]
comment in response to post
This "blog post" ended up being 20+ pages. I couldn't break it into smaller parts. Every section here contributes to a single cohesive message: โœ… brains adapt = minimize KL Curious about any of the details? Find the full PDF here: mysterioustune.com/2025/01/13/w... ๐Ÿงต[12/n]
comment in response to post
Here's my signature "๐‘ด๐’‚๐’•๐’‰/๐‘ฌ๐’๐’ˆ๐’๐’Š๐’”๐’‰ ๐‘ช๐’๐’“๐’“๐’†๐’”๐’‘๐’๐’๐’…๐’†๐’๐’„๐’†" table, summarizing the mathematical results, alongside their English translation: ๐Ÿงต[11/n]
comment in response to post
Recap so far: โœ… Brains: adapt to survive, survive to adapt โœ… adaptation = KL minimization โœ… most of ML = KL minimization โœ… KL asymmetry captures the flow of information โœ… KL minimization = flow of information from the world into your brain, updating your beliefs ๐Ÿงต[10/n]
comment in response to post
This Treasure Hunt example sheds light on the directional nature of KL: โœ… KL divergence must be asymmetric: because it captures the flow of information from the world to the brain (when you read a book or perform an experiment) ๐Ÿงต[9/n]
comment in response to post
In section 5, I explore the relative information interpretation of KL through an intuitive "Treasure Hunt" story. I then connect this to philosophy of science, and experiments as "truth-revealing actions." (another relevant @alexalemi.bsky.social piece: blog.alexalemi.com/kl.html) ๐Ÿงต[8/n]
comment in response to post
So, adaptation and KL minimization are intimately related. But what about learning? โœ… In section 4, I apply these foundational principles to "derive" (almost) all of machine learning from KL minimization. (first pointed out by @alexalemi.bsky.social : blog.alexalemi.com/kl-is-all-yo...) ๐Ÿงต[7/n]
comment in response to post
Importantly, KL divergence naturally emerged from the mathematics of likelihood evaluation for an observer living in a world. I didn't put it in by hand, or make crazy assumptions. โœ… There is something truly fundamental, unique, and privileged about KL divergence. ๐Ÿงต[6/n]
comment in response to post
Here's our first deep insight. The following are equivalent: you adapt to the world โ†”๏ธ you accurately predict the world โ†”๏ธ fewer nasty surprises that could get you killed โ†”๏ธ KL ( world || your beliefs ) drops ๐Ÿงต[5/n]
comment in response to post
A few simple logical steps yield our main theoretical result๐Ÿ‘‡ This magical equation connects two seemingly distinct concepts: 1โƒฃ P_obs: the subjective probability your brain assigns to its observations 2โƒฃ KL divergence between the true world and your internal beliefs ๐Ÿงต[4/n]
comment in response to post
This "blog post" ended up being 20+ pages. So I just posted the intro, conclusions, and a link to a PDF with full math derivations. Here's the table of contents to give you a sense of what's there๐Ÿ‘‡ โฉ Let's continue with summarizing the most important results. ๐Ÿงต[3/n]
comment in response to post
This post started with a simple observation: โœ… Adaptation is so central to all biological intelligence, that it may very well define it. But can we mathematize this fuzzy English termโ“ ๐Ÿงต[2/n] ๐Ÿง ๐Ÿค–๐Ÿง ๐Ÿ“ˆ #AI
comment in response to post
โžก๏ธ The most important concept in modern science does not exist [in an objective sense]. In science, we're all studying subjective states of belief, given constraints and reasonable assumptions. The real question is: ๐™ƒ๐™ค๐™ฌ ๐™–๐™ง๐™š ๐™ฉ๐™๐™ค๐™จ๐™š ๐™จ๐™ช๐™—๐™Ÿ๐™š๐™˜๐™ฉ๐™ž๐™ซ๐™š ๐™ฅ๐™ง๐™ค๐™—๐™–๐™—๐™ž๐™ก๐™ž๐™ฉ๐™ž๐™š๐™จ ๐™ž๐™ข๐™ฅ๐™ก๐™š๐™ข๐™š๐™ฃ๐™ฉ๐™š๐™™ ๐™—๐™ฎ ๐™ฃ๐™š๐™ฉ๐™ฌ๐™ค๐™ง๐™ ๐™จ ๐™ค๐™› ๐™ฃ๐™š๐™ช๐™ง๐™ค๐™ฃ๐™จ? ๐Ÿง ๐Ÿค–๐Ÿง ๐Ÿ“ˆ
comment in response to post
You framed this as Helmholtzian inference versus RL, but there is a line of work that casts RL as inference (see review by Sergey Levine: arxiv.org/abs/1805.00909). So my question is: given this connection, can we interpret your results under the unifying framework of RL as inference?
comment in response to post
Poster info: ๐Ÿ“… Thursday, Dec 12 โฒ๏ธ 4:30 โ€“ 7:30 PM PST ๐Ÿ“ East Exhibit Hall A-C, #3709 Unfortunately, I can't attend in person due to visa issues, but I'll join virtually via an iPad (special thanks to my awesome collaborator Dekel for agreeing to set this up!) Hope to see some of you there! ๐Ÿง ๐Ÿค–๐Ÿง ๐Ÿ“ˆ
comment in response to post
Links: Paper: arxiv.org/abs/2405.14473 Code: github.com/hadivafaii/P... Poster: drive.google.com/file/d/1ZyMJ... X thread summary: x.com/hadivafaii/s... ๐Ÿง ๐Ÿค–๐Ÿง ๐Ÿ“ˆ
comment in response to post
Poster info: ๐Ÿ“… Thursday, Dec 12 โฒ๏ธ 4:30 โ€“ 7:30 PM PST ๐Ÿ“ East Exhibit Hall A-C, #3709 Unfortunately, I can't attend in person due to visa issues, but I'll join virtually via an iPad (special thanks to my awesome collaborator Dekel for agreeing to set this up!) Hope to see some of you there! ๐Ÿง ๐Ÿค–๐Ÿง ๐Ÿ“ˆ
comment in response to post
Finally, check out the paper and code: ๐Ÿ“„ Paper: arxiv.org/abs/2405.14473 ๐Ÿ–ผ๏ธ Poster: drive.google.com/file/d/1ZyMJ... ๐Ÿ’ป Code: github.com/hadivafaii/P...
comment in response to post
Here is the poster information: ๐Ÿ“… Thursday, Dec 12 โฒ๏ธ 4:30 โ€“ 7:30 PM PST ๐Ÿ“ East Exhibit Hall A-C, #3709 Unfortunately, I won't be there due to visa issues, but I will join virtually through an iPad (special thanks to my awesome collaborator Dekel who agreed to set up my virtual attendance!).
comment in response to post
This X thread summarizes the motivations behind our work and describes key findings: x.com/hadivafaii/s...
comment in response to post
Hi! I work on visual perception. Could I be added?
comment in response to post
Could I be added as well? Here are two papers, pure theory, no data! openreview.net/forum?id=ekt... arxiv.org/abs/2410.19315
comment in response to post
I'm currently working on the first long post. It's about "World Models, Adaptation, and Surprise." Stay tuned! Here's the link again: mysterioustune.com
comment in response to post
On the About page, I explain the context behind the blog's name: mysterioustune.com/about/
comment in response to post
I'm currently working on the first post. It's going to be about "World Models, Adaptation, and Surprise." Stay tuned! Here's the link again: mysterioustune.com
comment in response to post
The About page provides context about the blog's name: mysterioustune.com/about/
comment in response to post
Hi Raymond, Iโ€™m in the Bay Area and Iโ€™d be down to chat over coffee! When will you be here?
comment in response to post
- before accurate measurements: ๐“ฌ๐“ธ๐“ฐ๐“ท๐“ฒ๐“ฝ๐“ฒ๐“ธ๐“ท - after accurate measurements: breathing, eye movement, etc
comment in response to post
But also... "The Oscillator Brain"! Not far off actually haha
comment in response to post
"The Involute Brain"
comment in response to post
I'd love to be added. Thanks!
comment in response to post
In your view, are there fundamental differences between stochastic optimal control and reinforcement learning? This review paper says they can be unified: arxiv.org/abs/1912.03513 I'm asking because I'm interested in modeling active vision and looking for an appropriate mathematical framework.
comment in response to post
@neuralreckoning.bsky.social could you add me as well? I don't do SNNs in the conventional sense, but I like spikes :) Here are some relevant works: openreview.net/forum?id=ekt... arxiv.org/abs/2410.19315
comment in response to post
Hey there. I'm new to spiking neural nets and look forward to learning more from this community!
comment in response to post
AI for neuroscience ๐Ÿ™‹โ€โ™‚๏ธ
comment in response to post
Can you add me as well? Here's a recent relevant work: openreview.net/forum?id=ekt...
comment in response to post
Does this resonate with your perspective, @dickretired.bsky.social? [5/5]