Lightnews — Scholar-powered news

Reposted by Amir-massoud Farahmand

Claas Voelcker @cvoelcker.bsky.social · 8d

cvoelcker.de/blog/2025/re...

I finally gave in and made a nice blog post about my most recent paper. This was a surprising amount of work, so please be nice and go read it!

a close up of a sad cat with the words pleeeaasse written below it

ALT: a close up of a sad cat with the words pleeeaasse written below it

media.tenor.com

7 27

Amir-massoud Farahmand @sologen.bsky.social · 9d

They characterize the convergence behaviour using the "Committal Rate" of the algorithm, quantifying how aggresive the algorithm's update rule is.

1

Amir-massoud Farahmand @sologen.bsky.social · 9d

Methods benefitting from the geometry (e.g., Natural PG) behave much better than standard PG (under softmax policy), if they have access to the exact policy gradient (or NPG). If the direction of improvement is estimated on-policy with noise, PG >> NPG.

1 1

Amir-massoud Farahmand @sologen.bsky.social · 9d

Understanding the Effect of Stochasticity in Policy Optimization (NeurIPS 2021) by Jincheng Mei, Bo Dai, Chenjun Xiao, @skiandsolve.bsky.social, Dale Schuurmans.

Interesting paper on Policy Gradient (PG) methods!
PG >> NPG or PG << NPG?! It depends on your estimator.
arxiv.org/abs/2110.15572

1 4

Amir-massoud Farahmand @sologen.bsky.social · 11d

- The Chinese room argument is apparently clever, but it has never been convincing to me.

- Some stories about him:
www.facebook.com/bernard.w.ko...

Bernard W. Kobes

RIP John Searle (1932–2025). He did influential work in philosophy of language (e.g., his work on speech acts), philosophy of mind (e.g., his Chinese Room argument against strong AI, & his work on...

www.facebook.com

1

Amir-massoud Farahmand @sologen.bsky.social · 11d

The philosopher John Searle died recently.
He was one of the famous contemporary philosophers about whom I kept reading or hearing, mostly because of his Chinese Room argument.
Reading some comments by those who have actually met him, it seems that he was a character!

1 3

Amir-massoud Farahmand @sologen.bsky.social · 17d

Shanah tovah! שנה טובה

2

Amir-massoud Farahmand @sologen.bsky.social · 24d

Three years ago today, #MahsaAmini was murdered by the Islamic Republic. Her death started the hopeful Women, Life, Freedom movement in Iran and across the globe.
Mahsa, Nika, Sarina, and 100s of others are not among us anymore, but their influence has changed Iran forever.

1 7

Amir-massoud Farahmand @sologen.bsky.social · 29d

1) The exponential growth of the field implies an exponential growth of recent papers, so even uniform sampling of papers means reading more of the recent ones.
2) With a limited time to read, there is a FOMO-type of incentive to focus on the new. The sampling distribution is not uniform.

3

Amir-massoud Farahmand @sologen.bsky.social · 29d

The citation depth of ML is shallow: most people don't meaningfully cite a more than a few years old paper (yes, textbooks and obligatory classics aside).

Why? Many reasons, including that the authors probably haven't actually read the old papers.
Why? Two reasons:

1 5

Amir-massoud Farahmand @sologen.bsky.social · Sep 8

But its output was inspirational!

1

Amir-massoud Farahmand @sologen.bsky.social · Sep 8

Surprisingly, it didn't do a good job. Maybe it needed more hand-helding and guidance. My prompt was something like this:
This is my Research Proposal, these are the Evaluation Criteria, these are suggestions of what should go in each section, and this is my actual CV. Come up with something good.

1 2

Amir-massoud Farahmand @sologen.bsky.social · Sep 7

What is expected is not clear, there is no samples to see, there is a 5-page limit (if you write in French, you get an extra page!), but I suppose this invention helps everyone keep busy and the beareaucrats continue to have their jobs.

2

Amir-massoud Farahmand @sologen.bsky.social · Sep 7

I recently learned the existence of something called Descriptive CV. This is a type of CV that must adapt to the grant application, so whenever you write a research proposal, you have to write a new CV too. Wonderful!

3 5

Amir-massoud Farahmand @sologen.bsky.social · Sep 2

Big news, everyone!

Mila - Institut québécois d'IA @mila-quebec.bsky.social · Sep 2

Exciting news! We're thrilled to announce the appointment of Professor Hugo Larochelle as Mila's new Scientific Director! A deep learning pioneer and former head of Google's AI lab in Montreal, Hugo's leadership will be pivotal in advancing AI for the benefit of all.

mila.quebec/en/news/hugo...

Hugo Larochelle becomes the new Scientific Director of Mila | Mila

Montreal (Quebec), September 2, 2025 – Mila, the Quebec Artificial Intelligence Institute, announces the appointment of Hugo Larochelle—Adjunct Professor at the Université de Montréal and former head ...

mila.quebec

2

Amir-massoud Farahmand @sologen.bsky.social · Sep 1

I don't know what exactly he was thinking of (minimax results? adaptivity? continual learning?), but I have been thinking of a version of this thought in the past 2-3 years, 50 something years after him!

1

Amir-massoud Farahmand @sologen.bsky.social · Sep 1

... I propose to study the synthesis of brain models by the parallel development of a series of matched (theoretical) environments and corresponding brain models that adapt to them."

1 1

Amir-massoud Farahmand @sologen.bsky.social · Sep 1

... Even the complex human brain first adapts to the simpler aspects of its environment and gradually builds up to the more complex features. ...

1 1

Amir-massoud Farahmand @sologen.bsky.social · Sep 1

This proposal by Claude Shannon is quite surprising to me:

"The matched environment brain model approach to automata. In general a machine or animal can only adapt to or operate in a limited class of environments. ...

1 1

Amir-massoud Farahmand @sologen.bsky.social · Sep 1

It all started with a proposal, 60 years ago!
"A Proposal for Dartmouth Summer Research Project on Artificial Intelligence".
jmc.stanford.edu/articles/dar...

jmc.stanford.edu

1 5

Amir-massoud Farahmand @sologen.bsky.social · Aug 30

Both can be useful. The top picture has 2+ nice properties:
1) It is modular. One can put other modules before or after that.
2) It emphasizes the compression aspect of AE.

You've already mentioned the nice properties of the bottom figure.

1 1

Amir-massoud Farahmand @sologen.bsky.social · Aug 22

Freaking Famine!
The situation in Gaza will be the stain on our generation and all whose support led to this.

WHO @who.int · Aug 22

Famine confirmed for first time in Gaza
FAO, UNICEF, WFP & WHO reiterate call for immediate ceasefire & unhindered humanitarian access to curb deaths from hunger & malnutrition.

4

Amir-massoud Farahmand @sologen.bsky.social · Aug 21

The Prime Minister is primed to the Policy Search methods. The AI minister, however, is more into the Critique.

Glen Berseth @glenberseth.bsky.social · Aug 20

My lab at @montrealrobotics.bsky.social was honoured to present our recent work to @mark-carney.bsky.social and Even Solomon explaining how AI enables new robotics that will drive innovation in Canada. It was a pleasure getting into the details with a quick dive into deterministic policy gradients!

5

Reposted by Amir-massoud Farahmand

Victor Zhong @vzhong.bsky.social · Aug 21

I finally finished it! www.victorzhong.com/writing/refl...

Reflections of a First-year Assistant Professor - Victor Zhong

www.victorzhong.com

2 19

Amir-massoud Farahmand @sologen.bsky.social · Aug 13

Doesn't this imply that one should not consider the comments of the rejecting committee as the reviewers will be different?
(Of course, some comments may make sense, but if they don't, ...).
The same for a paper.

1 1