Bruno Gavranović
@bgavran.bsky.social
Categorical Deep Learning.
Different products of containers, with examples on the List container:
List ⊗ List -> rectangular array
List ∘ List -> ragged array
List × List -> two lists
List + List -> a boolean value and a list
List ⊗ List -> rectangular array
List ∘ List -> ragged array
List × List -> two lists
List + List -> a boolean value and a list
November 17, 2025 at 7:36 PM
Different products of containers, with examples on the List container:
List ⊗ List -> rectangular array
List ∘ List -> ragged array
List × List -> two lists
List + List -> a boolean value and a list
List ⊗ List -> rectangular array
List ∘ List -> ragged array
List × List -> two lists
List + List -> a boolean value and a list
Reposted by Bruno Gavranović
Remember kids, theoretical physicists have irreparably ruined public trust in science by saying they *hope* we *could* find BSM evidence at the LHC, but Elon gets to predict his products will "do the sci-fi" and be wrong 100 times per year for profit but he's just giving them hope
The brave renegade truth teller: "the people must be made to believe obvious lies to pacify them"
November 17, 2025 at 12:21 PM
Remember kids, theoretical physicists have irreparably ruined public trust in science by saying they *hope* we *could* find BSM evidence at the LHC, but Elon gets to predict his products will "do the sci-fi" and be wrong 100 times per year for profit but he's just giving them hope
Had an absolutely fantastic time in Scotland. It's been great seeing a lot of friendly faces, and making exciting research progress with Glaive
November 15, 2025 at 10:36 AM
Had an absolutely fantastic time in Scotland. It's been great seeing a lot of friendly faces, and making exciting research progress with Glaive
London ---🚅---> Glasgow
November 10, 2025 at 11:59 AM
London ---🚅---> Glasgow
Containers and quotient containers can be interpreted as choices of a category S with some constraints on it, and a functor S -> Set.
For an ordinary container, S has to be a discrete category, i.e. a set.
For an ordinary container, S has to be a discrete category, i.e. a set.
November 2, 2025 at 10:40 PM
Containers and quotient containers can be interpreted as choices of a category S with some constraints on it, and a functor S -> Set.
For an ordinary container, S has to be a discrete category, i.e. a set.
For an ordinary container, S has to be a discrete category, i.e. a set.
October 31, 2025 at 11:28 AM
Stumbled upon this on HN:
"Categorical foundations for CuTe layouts"
https://research.colfax-intl.com/categorical-foundations-for-cute-layouts/
"Categorical foundations for CuTe layouts"
https://research.colfax-intl.com/categorical-foundations-for-cute-layouts/
Categorical Foundations for CuTe Layouts
In GPU programming, performance depends critically on how data is stored and accessed in memory. While the data we care about is typically multi-dimensional, the GPU’s memory is fundamentally one-d…
research.colfax-intl.com
September 22, 2025 at 8:49 PM
Stumbled upon this on HN:
"Categorical foundations for CuTe layouts"
https://research.colfax-intl.com/categorical-foundations-for-cute-layouts/
"Categorical foundations for CuTe layouts"
https://research.colfax-intl.com/categorical-foundations-for-cute-layouts/
Stumbled upon the paper "Sorting with Bialgebras and Distributive Laws" ( https://www.cs.ox.ac.uk/people/nicolas.wu/papers/Sorting.pdf )
which introdued me to the idea that certain sorting algorithms can be considered 'duals' of others:
which introdued me to the idea that certain sorting algorithms can be considered 'duals' of others:
September 18, 2025 at 2:22 PM
Stumbled upon the paper "Sorting with Bialgebras and Distributive Laws" ( https://www.cs.ox.ac.uk/people/nicolas.wu/papers/Sorting.pdf )
which introdued me to the idea that certain sorting algorithms can be considered 'duals' of others:
which introdued me to the idea that certain sorting algorithms can be considered 'duals' of others:
I have been thinking about fixpoints of containers recently, and noticed that there seems to be a close correspondence between fixpoints of extensions of containers \mu(Ext(C)) and iterated compositions I + C + C o C + C o C o C ...
Has this been formally established somewhere?
Has this been formally established somewhere?
September 16, 2025 at 11:34 AM
I have been thinking about fixpoints of containers recently, and noticed that there seems to be a close correspondence between fixpoints of extensions of containers \mu(Ext(C)) and iterated compositions I + C + C o C + C o C o C ...
Has this been formally established somewhere?
Has this been formally established somewhere?
Interestingly, this is still a question I do not have a good answer for, and a question that I didn't see tackled by the deep learning community at all.
September 8, 2025 at 6:47 PM
Interestingly, this is still a question I do not have a good answer for, and a question that I didn't see tackled by the deep learning community at all.
Reposted by Bruno Gavranović
Unbelievable!
Today, San Diego witnessed a government-sanctioned kidnapping. ICE stormed Buona Forchetta in military gear ripping workers away, then unleashing tear gas and smoke on the terrified community. Full on police state, fascism now used on American citizens. Stay aware.
#OnYourSide
Today, San Diego witnessed a government-sanctioned kidnapping. ICE stormed Buona Forchetta in military gear ripping workers away, then unleashing tear gas and smoke on the terrified community. Full on police state, fascism now used on American citizens. Stay aware.
#OnYourSide
May 31, 2025 at 4:04 AM
Unbelievable!
Today, San Diego witnessed a government-sanctioned kidnapping. ICE stormed Buona Forchetta in military gear ripping workers away, then unleashing tear gas and smoke on the terrified community. Full on police state, fascism now used on American citizens. Stay aware.
#OnYourSide
Today, San Diego witnessed a government-sanctioned kidnapping. ICE stormed Buona Forchetta in military gear ripping workers away, then unleashing tear gas and smoke on the terrified community. Full on police state, fascism now used on American citizens. Stay aware.
#OnYourSide
Stumbled upon a peculiar paper:
Aggregating time-series and image data:
functors and double functors
https://arxiv.org/abs/2504.05274
Aggregating time-series and image data:
functors and double functors
https://arxiv.org/abs/2504.05274
May 19, 2025 at 3:33 PM
Stumbled upon a peculiar paper:
Aggregating time-series and image data:
functors and double functors
https://arxiv.org/abs/2504.05274
Aggregating time-series and image data:
functors and double functors
https://arxiv.org/abs/2504.05274
I've always wanted someone to write a type-safe framework for tensor manipulation that
a) fully leverages first-class types, and
b) is ergonomic
Maybe that someone has to be me; I wrote a proof-of-concept in Idris and used it to implement transformers:
github.com/bgavran/Type...
a) fully leverages first-class types, and
b) is ergonomic
Maybe that someone has to be me; I wrote a proof-of-concept in Idris and used it to implement transformers:
github.com/bgavran/Type...
GitHub - bgavran/TypeSafe_Tensors: Framework for type-safe pure functional tensor processing, supporting non-cubical tensors
Framework for type-safe pure functional tensor processing, supporting non-cubical tensors - bgavran/TypeSafe_Tensors
github.com
May 7, 2025 at 11:07 AM
I've always wanted someone to write a type-safe framework for tensor manipulation that
a) fully leverages first-class types, and
b) is ergonomic
Maybe that someone has to be me; I wrote a proof-of-concept in Idris and used it to implement transformers:
github.com/bgavran/Type...
a) fully leverages first-class types, and
b) is ergonomic
Maybe that someone has to be me; I wrote a proof-of-concept in Idris and used it to implement transformers:
github.com/bgavran/Type...
Reposted by Bruno Gavranović
London --🚄--> Edinburgh
April 6, 2025 at 4:54 PM
London --🚄--> Edinburgh
Stumbled upon an Idris implementation of type-safe tensor computation (alongside many other things)
https://github.com/joelberkeley/spidr/tree/master
https://github.com/joelberkeley/spidr/tree/master
GitHub - joelberkeley/spidr: Accelerated machine learning with dependent types
Accelerated machine learning with dependent types. Contribute to joelberkeley/spidr development by creating an account on GitHub.
github.com
March 25, 2025 at 8:44 PM
Stumbled upon an Idris implementation of type-safe tensor computation (alongside many other things)
https://github.com/joelberkeley/spidr/tree/master
https://github.com/joelberkeley/spidr/tree/master
I've been playing with provably correct list sorting ( https://gist.github.com/bgavran/e6ef899a86223d32e25adde4ce884a64 ), and internalising a very unintuitive fact: there exists a *type of sorted lists*.
It's something I would have never came up with myself. Hence makes me wonder, what *else* is
It's something I would have never came up with myself. Hence makes me wonder, what *else* is
March 5, 2025 at 10:29 PM
I've been playing with provably correct list sorting ( https://gist.github.com/bgavran/e6ef899a86223d32e25adde4ce884a64 ), and internalising a very unintuitive fact: there exists a *type of sorted lists*.
It's something I would have never came up with myself. Hence makes me wonder, what *else* is
It's something I would have never came up with myself. Hence makes me wonder, what *else* is
Reposted by Bruno Gavranović
After a multi-year collaboration with Martin Biehl, @mattecapu.bsky.social and @nathanielvirgo.bsky.social, I’m stoked to share the first of (hopefully) many outputs:
“A Bayesian Interpretation of the Internal Model Principle”
arxiv.org/abs/2503.00511.
1/
“A Bayesian Interpretation of the Internal Model Principle”
arxiv.org/abs/2503.00511.
1/
March 5, 2025 at 2:31 AM
After a multi-year collaboration with Martin Biehl, @mattecapu.bsky.social and @nathanielvirgo.bsky.social, I’m stoked to share the first of (hopefully) many outputs:
“A Bayesian Interpretation of the Internal Model Principle”
arxiv.org/abs/2503.00511.
1/
“A Bayesian Interpretation of the Internal Model Principle”
arxiv.org/abs/2503.00511.
1/
March 3, 2025 at 10:54 PM
I never thought about the underlying implementation of typed holes in languages like Idris/Agda before.
Are they just implemented as a nullary constructor of an inductive type?
```
data Expr : Type where
Num : Nat -> Expr
Add : Expr -> Expr -> Expr
Hole : Expr
```
Are they just implemented as a nullary constructor of an inductive type?
```
data Expr : Type where
Num : Nat -> Expr
Add : Expr -> Expr -> Expr
Hole : Expr
```
March 3, 2025 at 9:12 PM
I never thought about the underlying implementation of typed holes in languages like Idris/Agda before.
Are they just implemented as a nullary constructor of an inductive type?
```
data Expr : Type where
Num : Nat -> Expr
Add : Expr -> Expr -> Expr
Hole : Expr
```
Are they just implemented as a nullary constructor of an inductive type?
```
data Expr : Type where
Num : Nat -> Expr
Add : Expr -> Expr -> Expr
Hole : Expr
```
Reading about linters, and I ran into a lovely example of what they keep you from doing:
(from the International obfuscated C code contest https://github.com/ioccc-src/winner/blob/master/2011/goren/goren.c )
(from the International obfuscated C code contest https://github.com/ioccc-src/winner/blob/master/2011/goren/goren.c )
February 26, 2025 at 2:25 PM
Reading about linters, and I ran into a lovely example of what they keep you from doing:
(from the International obfuscated C code contest https://github.com/ioccc-src/winner/blob/master/2011/goren/goren.c )
(from the International obfuscated C code contest https://github.com/ioccc-src/winner/blob/master/2011/goren/goren.c )
Fun fact I just learned: gunpowder was created by alchemists as a byproduct of trying to create the elixir of life.
https://en.wikipedia.org/wiki/Gunpowder
https://en.wikipedia.org/wiki/Gunpowder
February 23, 2025 at 5:42 PM
Fun fact I just learned: gunpowder was created by alchemists as a byproduct of trying to create the elixir of life.
https://en.wikipedia.org/wiki/Gunpowder
https://en.wikipedia.org/wiki/Gunpowder
Discovered a gem of a paper, which merges two things I am very excited about: DeepRL + (dependently) type-directed program search.
Highly recommended read.
https://arxiv.org/abs/2407.00695
Highly recommended read.
https://arxiv.org/abs/2407.00695
February 21, 2025 at 5:18 PM
Discovered a gem of a paper, which merges two things I am very excited about: DeepRL + (dependently) type-directed program search.
Highly recommended read.
https://arxiv.org/abs/2407.00695
Highly recommended read.
https://arxiv.org/abs/2407.00695
Reposted by Bruno Gavranović
I'm writing a new blog series on practical implementation of substructural type systems, in Idris!
The first blog post will look at substructural polymorphism and why it's *hard*, harder than people assume on first glance!
zanzix.github.io/posts/5-subs...
The first blog post will look at substructural polymorphism and why it's *hard*, harder than people assume on first glance!
zanzix.github.io/posts/5-subs...
Compiler Engineering for Substructural Languages I: The Problem with
Polymorphism
Can a correct-by-construction implementation of a substructural language
be extended to a polymorphic lambda calculus?
zanzix.github.io
February 17, 2025 at 2:13 PM
I'm writing a new blog series on practical implementation of substructural type systems, in Idris!
The first blog post will look at substructural polymorphism and why it's *hard*, harder than people assume on first glance!
zanzix.github.io/posts/5-subs...
The first blog post will look at substructural polymorphism and why it's *hard*, harder than people assume on first glance!
zanzix.github.io/posts/5-subs...