Amir-massoud Farahmand

Canadian researchers should be aware the there is a motion before the Parliamentary Standing Committee on Science and Research to force Tricouncils to hand over disaggregated peer review data on all applications:
Applicant names, profiles, demographics
Reviewers names, profiles, comments, and scores

As Transactions on Machine Learning Research (TMLR) grows in number of submissions, we are looking for more reviewers and action editors. Please sign up!

Only one paper to review at a time and <= 6 per year, reviewers report greater satisfaction than reviewing for conferences!

Happy Diwali!

Apply to join one of the top AI research 🤖 institutes in the world in the wonderful city of Montréal!
I will be recruiting 1-2 students this year. Just mention my name in your application.

A table showing that different discretization of the Riemannian Gradient Flow leads to different algorithm: Geometry discretized, Objective discretized: Natural Gradient Descent Geometry not discretized, Objective discretized: Mirror Descent Geometry discretized, Objective not discretized: unknown (?)

Mirrorless Mirror Descent: A Natural Derivation of Mirror Descent (Gunasekar, Woodworth, Srebro at AISTATS, 2021)
They show that the Mirror Descent algorithm is a particular way of discretization a certain geometry-aware gradient flow.
proceedings.mlr.press/v130/gunasek...
Interesting paper!

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

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!

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

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.

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

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...

- 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...

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!

Shanah tovah! שנה טובה

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) 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.

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:

But its output was inspirational!

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.

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.

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!

Big news, everyone!

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!

... 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."

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

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. ...

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

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.

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

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

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

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.