Christian Weilbach
I study how learning systems can improve themselves and stay correct. I am most interested in the organisations around them, since the structures that check a learner have to learn and grow together with it.
I did my PhD in machine learning at the University of British Columbia with Frank Wood, on how the structure of a problem can be translated into the neural networks that solve it. Before that I wrote my Bachelor's and Master's theses at Heidelberg University, on online learning in spiking neuron models and on dictionary learning with Bayesian GANs, and studied philosophy and cultural anthropology. I am now the CEO of Simmis, where we build software for organisations of people and AI agents. The open-source stack underneath it covers versioned memory, forkable runtimes, probabilistic inference and a language whose kernel checks its own optimisations. More about me.
Projects and papers since 2006
The figure shows what I have worked on and which project grew out of which. Some branches ended, and a few came back years later. Scroll to replay the years.
How the projects relate
My projects form a stack, every level supports the same operation. A person, an agent or a program makes an attempt on a fork and compares the result with evidence. The attempt is adopted only after a check. All levels share one versioned memory, so forking is cheap.
-
On whose behalf does this work happen?
- Dvergr rooms, attempts in forks, review
-
What is worth knowing?
- Foerster probabilistic inference in forkable worlds
- A forkable Stuttgart 936,597 simulated people
-
What may run, and at whose cost?
- Spindel reactive runtime with forkable state
- partial-cps continuations only where needed
-
What must not be forgotten?
- Datahike versioned Datalog
- Konserve one storage interface for files, S3, JDBC
- Yggdrasil one fork and merge protocol across systems
- Geschichte queryable, git-compatible history
Talks
- Rationalizing a Society of Learners
- Programming as and for inference
- Partially evaluating higher-order probabilistic programs without stochastic recursion to graphical models
- Flexible diffusion models for videos, molecules, and inference in structured simulators
- Video and graphically structured diffusion models
- Graphically structured diffusion models
- Anglican: Turing-complete functional probabilistic programming as a domain-specific language
- Datalog as a distributed systems language
- Let's replicate state together
- Machine learning workshop