Aditya Makkar
@adityamakkar.bsky.social
In search of mathematics and ML content.
PhD@NYU
PhD@NYU
Reposted by Aditya Makkar
We're finally out of stealth: percepta.ai
We're a research / engineering team working together in industries like health and logistics to ship ML tools that drastically improve productivity. If you're interested in ML and RL work that matters, come join us 😀
We're a research / engineering team working together in industries like health and logistics to ship ML tools that drastically improve productivity. If you're interested in ML and RL work that matters, come join us 😀
Percepta | A General Catalyst Transformation Company
Transforming critical institutions using applied AI. Let's harness the frontier.
percepta.ai
October 2, 2025 at 3:35 PM
We're finally out of stealth: percepta.ai
We're a research / engineering team working together in industries like health and logistics to ship ML tools that drastically improve productivity. If you're interested in ML and RL work that matters, come join us 😀
We're a research / engineering team working together in industries like health and logistics to ship ML tools that drastically improve productivity. If you're interested in ML and RL work that matters, come join us 😀
Reposted by Aditya Makkar
Reminded again of Kevin Murphy's excellent RL overview: arxiv.org/abs/2412.05265
A lot of the stuff covered here really is at the cutting edge and not compiled so nicely anywhere else
A lot of the stuff covered here really is at the cutting edge and not compiled so nicely anywhere else
Reinforcement Learning: An Overview
This manuscript gives a big-picture, up-to-date overview of the field of (deep) reinforcement learning and sequential decision making, covering value-based methods, policy-based methods, model-based m...
arxiv.org
September 3, 2025 at 1:47 AM
Reminded again of Kevin Murphy's excellent RL overview: arxiv.org/abs/2412.05265
A lot of the stuff covered here really is at the cutting edge and not compiled so nicely anywhere else
A lot of the stuff covered here really is at the cutting edge and not compiled so nicely anywhere else
Reposted by Aditya Makkar
My favorite open problem:
Conjecture (Frankl). Let X be a finite set, and let S ⊆ P(X) be a collection of subsets of X which is closed under union.
If S≠∅ and S≠{∅}, then some element x∈X appears in at least half of the elements of S, i.e.
2|{s ∈ S : x ∈ s}| ≥ |S|.
Conjecture (Frankl). Let X be a finite set, and let S ⊆ P(X) be a collection of subsets of X which is closed under union.
If S≠∅ and S≠{∅}, then some element x∈X appears in at least half of the elements of S, i.e.
2|{s ∈ S : x ∈ s}| ≥ |S|.
August 15, 2025 at 2:32 PM
My favorite open problem:
Conjecture (Frankl). Let X be a finite set, and let S ⊆ P(X) be a collection of subsets of X which is closed under union.
If S≠∅ and S≠{∅}, then some element x∈X appears in at least half of the elements of S, i.e.
2|{s ∈ S : x ∈ s}| ≥ |S|.
Conjecture (Frankl). Let X be a finite set, and let S ⊆ P(X) be a collection of subsets of X which is closed under union.
If S≠∅ and S≠{∅}, then some element x∈X appears in at least half of the elements of S, i.e.
2|{s ∈ S : x ∈ s}| ≥ |S|.
Reposted by Aditya Makkar
Another fun open problem:
Conjecture (Rota). Let n be a natural number. Let V be an n-dimensional vector space. Let B₁, …, Bₙ be bases of V.
Then there exist orderings of these bases
Bₖ = (bₖ₁, …, bₖₙ)
such that {b₁ₖ, …, bₙₖ} is a basis of V for all 1 ≤ k ≤ n.
Conjecture (Rota). Let n be a natural number. Let V be an n-dimensional vector space. Let B₁, …, Bₙ be bases of V.
Then there exist orderings of these bases
Bₖ = (bₖ₁, …, bₖₙ)
such that {b₁ₖ, …, bₙₖ} is a basis of V for all 1 ≤ k ≤ n.
August 16, 2025 at 3:36 PM
Another fun open problem:
Conjecture (Rota). Let n be a natural number. Let V be an n-dimensional vector space. Let B₁, …, Bₙ be bases of V.
Then there exist orderings of these bases
Bₖ = (bₖ₁, …, bₖₙ)
such that {b₁ₖ, …, bₙₖ} is a basis of V for all 1 ≤ k ≤ n.
Conjecture (Rota). Let n be a natural number. Let V be an n-dimensional vector space. Let B₁, …, Bₙ be bases of V.
Then there exist orderings of these bases
Bₖ = (bₖ₁, …, bₖₙ)
such that {b₁ₖ, …, bₙₖ} is a basis of V for all 1 ≤ k ≤ n.
Mesmerizing
Source: images.wur.nl/digital/coll...
Source: images.wur.nl/digital/coll...
August 5, 2025 at 4:57 PM
Mesmerizing
Source: images.wur.nl/digital/coll...
Source: images.wur.nl/digital/coll...
Reposted by Aditya Makkar
A critical look at intelligence explosion arguments, with references to I.J. Good, Jimmy Savage's small and large worlds, Kathleen Wilkes' argument against thought experiments in psychology, and Tolkien's theory of subcreation (+ some Sabbath references): realizable.substack.com/p/supertzar-...
Supertzar, or the Hand of Doom
The sleep of reason produces utility monsters.
realizable.substack.com
August 2, 2025 at 8:17 PM
A critical look at intelligence explosion arguments, with references to I.J. Good, Jimmy Savage's small and large worlds, Kathleen Wilkes' argument against thought experiments in psychology, and Tolkien's theory of subcreation (+ some Sabbath references): realizable.substack.com/p/supertzar-...
Reposted by Aditya Makkar
Quanta has some coverage on her solution, including from this colourful presentation. One detail that i liked -- she had worked through advanced undergrad math curriculum by herself by 14. Hopefully she is able to handle the sudden attention well.
www.quantamagazine.org/at-17-hannah...
www.quantamagazine.org/at-17-hannah...
August 1, 2025 at 2:33 PM
Quanta has some coverage on her solution, including from this colourful presentation. One detail that i liked -- she had worked through advanced undergrad math curriculum by herself by 14. Hopefully she is able to handle the sudden attention well.
www.quantamagazine.org/at-17-hannah...
www.quantamagazine.org/at-17-hannah...
Reposted by Aditya Makkar
Great intro to Optimal Stopping on those lecture notes by Thomas S. Ferguson
www.math.ucla.edu/~tom/Stoppin...
www.math.ucla.edu/~tom/Stoppin...
Local page
www.math.ucla.edu
July 23, 2025 at 1:50 PM
Great intro to Optimal Stopping on those lecture notes by Thomas S. Ferguson
www.math.ucla.edu/~tom/Stoppin...
www.math.ucla.edu/~tom/Stoppin...
Reposted by Aditya Makkar
This week's #PaperILike is "The Power of Resets in Online Reinforcement Learning" (Mhammedi et al., 2024).
If you're doing RL in sim, why not use the sim to its full potential? Reset to any state! (gym.Env.reset() is not all we need.)
PDF: arxiv.org/abs/2404.15417
If you're doing RL in sim, why not use the sim to its full potential? Reset to any state! (gym.Env.reset() is not all we need.)
PDF: arxiv.org/abs/2404.15417
The Power of Resets in Online Reinforcement Learning
Simulators are a pervasive tool in reinforcement learning, but most existing algorithms cannot efficiently exploit simulator access -- particularly in high-dimensional domains that require general fun...
arxiv.org
June 29, 2025 at 1:08 PM
This week's #PaperILike is "The Power of Resets in Online Reinforcement Learning" (Mhammedi et al., 2024).
If you're doing RL in sim, why not use the sim to its full potential? Reset to any state! (gym.Env.reset() is not all we need.)
PDF: arxiv.org/abs/2404.15417
If you're doing RL in sim, why not use the sim to its full potential? Reset to any state! (gym.Env.reset() is not all we need.)
PDF: arxiv.org/abs/2404.15417
Reposted by Aditya Makkar
my p doom? sorry that's not a valid sigma algebra
June 23, 2025 at 11:45 PM
my p doom? sorry that's not a valid sigma algebra
Reposted by Aditya Makkar
Looks like a great new foundations and trends monograph arxiv.org/abs/2506.17366
Gaussian Processes and Reproducing Kernels: Connections and Equivalences
This monograph studies the relations between two approaches using positive definite kernels: probabilistic methods using Gaussian processes, and non-probabilistic methods using reproducing kernel Hilb...
arxiv.org
June 24, 2025 at 12:29 PM
Looks like a great new foundations and trends monograph arxiv.org/abs/2506.17366
Reposted by Aditya Makkar
Born on 23 June 1912 in London, Alan Turing, a mathematician, cryptographer and a pioneer in computer science and artificial intelligence
pubs.aip.org/physicstoday...
pubs.aip.org/physicstoday...
November 18, 2024 at 7:36 PM
Born on 23 June 1912 in London, Alan Turing, a mathematician, cryptographer and a pioneer in computer science and artificial intelligence
pubs.aip.org/physicstoday...
pubs.aip.org/physicstoday...
Reposted by Aditya Makkar
Hiring a postdoc to scale up and deploy RL-based planning onto some self-driving cars! We'll be building on arxiv.org/abs/2502.03349 and learn what the limits and challenges of RL planning are. Shoot me a message if interested and help spread the word please!
Full posting to come in a bit.
Full posting to come in a bit.
Robust Autonomy Emerges from Self-Play
Self-play has powered breakthroughs in two-player and multi-player games. Here we show that self-play is a surprisingly effective strategy in another domain. We show that robust and naturalistic drivi...
arxiv.org
June 21, 2025 at 5:14 PM
Hiring a postdoc to scale up and deploy RL-based planning onto some self-driving cars! We'll be building on arxiv.org/abs/2502.03349 and learn what the limits and challenges of RL planning are. Shoot me a message if interested and help spread the word please!
Full posting to come in a bit.
Full posting to come in a bit.
Reposted by Aditya Makkar
It was a dream come true to teach the course I wish existed at the start of my PhD. We built up the algorithmic foundations of modern-day RL, imitation learning, and RLHF, going deeper than the usual "grab bag of tricks". All 25 lectures + 150 pages of notes are now public!
June 20, 2025 at 3:53 AM
It was a dream come true to teach the course I wish existed at the start of my PhD. We built up the algorithmic foundations of modern-day RL, imitation learning, and RLHF, going deeper than the usual "grab bag of tricks". All 25 lectures + 150 pages of notes are now public!
Reposted by Aditya Makkar
Does everyone in your community agree on some folk knowledge that isn’t published anywhere? Put it in a paper! It’s a pretty valuable contribution
November 26, 2024 at 10:31 PM
Does everyone in your community agree on some folk knowledge that isn’t published anywhere? Put it in a paper! It’s a pretty valuable contribution
Reposted by Aditya Makkar
—I want a painting of a solar eclipse. Have you seen one?
—You bet!
—You bet!
June 4, 2025 at 8:05 AM
—I want a painting of a solar eclipse. Have you seen one?
—You bet!
—You bet!
Reposted by Aditya Makkar
Yeah they’re getting quite good. I think the model I have is something like “clever but sort of dishonest undergrad with an encyclopedic but idiosyncratic knowledge of the arxiv.” “Prove [well-known result with a short-ish proof]” is well within their capabilities though they do sometimes screw up.
May 21, 2025 at 1:25 AM
Yeah they’re getting quite good. I think the model I have is something like “clever but sort of dishonest undergrad with an encyclopedic but idiosyncratic knowledge of the arxiv.” “Prove [well-known result with a short-ish proof]” is well within their capabilities though they do sometimes screw up.
Reposted by Aditya Makkar
If the last time you tried to use an LLM for math was ~4 or 5 months ago it’s worth firing up Gemini 2.5 (which you can try for free) or ChatGPT o3 and getting a sense of how rapidly things have progressed.
May 20, 2025 at 1:31 PM
If the last time you tried to use an LLM for math was ~4 or 5 months ago it’s worth firing up Gemini 2.5 (which you can try for free) or ChatGPT o3 and getting a sense of how rapidly things have progressed.
Reposted by Aditya Makkar
crushing it on the free will machine (people.ischool.berkeley.edu/~nick/aarons...)
May 8, 2025 at 2:02 PM
crushing it on the free will machine (people.ischool.berkeley.edu/~nick/aarons...)
Reposted by Aditya Makkar
A cute lil writeup of our work trying to scale up meta-learning for partner adaptation:
engineering.nyu.edu/news/nyu-tan...
Also, my first grant!
engineering.nyu.edu/news/nyu-tan...
Also, my first grant!
NYU Tandon receives Google DeepMind grant to advance AI adaptation | NYU Tandon School of Engineering
engineering.nyu.edu
May 6, 2025 at 2:01 AM
A cute lil writeup of our work trying to scale up meta-learning for partner adaptation:
engineering.nyu.edu/news/nyu-tan...
Also, my first grant!
engineering.nyu.edu/news/nyu-tan...
Also, my first grant!
Reposted by Aditya Makkar
The Stone-Weierstrass theorem states that any continuous function on a compact Hausdorff space can be uniformly approximated by elements of a subalgebra, provided the subalgebra separates points and contains constants. buff.ly/MbZOAG0
April 28, 2025 at 5:01 AM
The Stone-Weierstrass theorem states that any continuous function on a compact Hausdorff space can be uniformly approximated by elements of a subalgebra, provided the subalgebra separates points and contains constants. buff.ly/MbZOAG0
Reposted by Aditya Makkar
Theorem of the Day (April 28, 2025) : Kuratowski’s 14-Set Theorem
Source : Theorem of the Day / Robin Whitty
pdf : buff.ly/ZKGM3fm
notes : buff.ly/A2DK4wC
#mathematics #maths #math #theorem
Source : Theorem of the Day / Robin Whitty
pdf : buff.ly/ZKGM3fm
notes : buff.ly/A2DK4wC
#mathematics #maths #math #theorem
April 28, 2025 at 10:01 AM
Theorem of the Day (April 28, 2025) : Kuratowski’s 14-Set Theorem
Source : Theorem of the Day / Robin Whitty
pdf : buff.ly/ZKGM3fm
notes : buff.ly/A2DK4wC
#mathematics #maths #math #theorem
Source : Theorem of the Day / Robin Whitty
pdf : buff.ly/ZKGM3fm
notes : buff.ly/A2DK4wC
#mathematics #maths #math #theorem
Reposted by Aditya Makkar
I like papers that have such intros. From the snippet you wouldn't guess (unless you already have the background) what [application] the paper is about. arxiv.org/abs/2504.16349
April 25, 2025 at 8:07 AM
I like papers that have such intros. From the snippet you wouldn't guess (unless you already have the background) what [application] the paper is about. arxiv.org/abs/2504.16349
Reposted by Aditya Makkar
A Monge map, i.e., a solution to optimal transport Monge problems, may not always exist, be unique, or be symmetric with respect to the source and target distributions. It was one of the motivation to introduce Kantorovich relaxation. math.univ-lyon1.fr/~santambrogi...
April 21, 2025 at 5:01 AM
A Monge map, i.e., a solution to optimal transport Monge problems, may not always exist, be unique, or be symmetric with respect to the source and target distributions. It was one of the motivation to introduce Kantorovich relaxation. math.univ-lyon1.fr/~santambrogi...
Reposted by Aditya Makkar
Colours correspond to infinite-dimensional vectors, since there are infinitely many wavelengths of light.
But humans can only perceive a three-dimensional projection of colour (red, green, & blue).
What's interesting is that it's *not* an orthogonal projection. Here's a plot of the basis vectors.
But humans can only perceive a three-dimensional projection of colour (red, green, & blue).
What's interesting is that it's *not* an orthogonal projection. Here's a plot of the basis vectors.
April 19, 2025 at 10:12 PM
Colours correspond to infinite-dimensional vectors, since there are infinitely many wavelengths of light.
But humans can only perceive a three-dimensional projection of colour (red, green, & blue).
What's interesting is that it's *not* an orthogonal projection. Here's a plot of the basis vectors.
But humans can only perceive a three-dimensional projection of colour (red, green, & blue).
What's interesting is that it's *not* an orthogonal projection. Here's a plot of the basis vectors.