loda-rust VS hivemind

https://github.com/loda-lang/loda-rust/blob/develop/rust_pro...

I use 4 bloomfilters for rejecting programs that aren't present in the oeis database. First 10 terms are computed, and reject if the terms aren't present in the 1st bloomfilter. Next 10 terms more are computed, and rejected if the 20 terms aren't present in the 2nd bloomfilter. All the way up to 40 terms. If a mined program has possible 40 correct terms, there is a chance that the program may compute the entire oeis integer sequence correct.

Shameless self promotion: If you have cpu resources to spare, then please contribute to LODA, an open source project for mining oeis integer sequences.

https://github.com/loda-lang/loda-rust/blob/develop/script/t...

Example of the 100 most similar documents:

https://github.com/loda-lang/loda-rust/blob/develop/document...

OEIS has a number of references from other sequences. If it's a popular sequence then the number of references is high. Usually it's humans that specify the references.

Unlike OEIS, the LODA programs references are mined. The most popular LODA program (A132106) has only a few references in OEIS, maybe it's overlooked in OEIS.

https://github.com/learning-at-home/hivemind is also relevant

I really hope you'll join me, for the Petals support, at least! A single docker-compose.yml file is all we need, for now. If we are able to find enough people willing to host some smaller models, perhaps we could expand into the Hivemind, and create our own, custom foundation model one day?

Decentralized deep learning: https://github.com/learning-at-home/hivemind

https://github.com/learning-at-home/hivemind - same people behind it, was made before petals I think.

not if we rise to meet that challenge. here's a few tools that facilitate AI research in the face of an advanced persistent threat: Hivemind- a distributed Pytorch framework

yeah, there's Hivemind. and there's research wrt how to chunk out training workload so it can be scaled up. not sure why there's commentary that latency issues would limit this sort of enterprise, the architecture typically isn't designed for liveness. other subfields of distributed training/inference include zero-knowledge machine learning. besides all of that, there's also adversarial computation like SafetyNets and refereed delegation of computation.

We already have the software for it. There are some projects, but the one I'm most familiar with is https://github.com/learning-at-home/hivemind for training and it's sister project https://petals.ml/ for running large models distributed.

I'm not entirely how the approach they're using works [0], but I study federated learning and one of the highly-cited survey papers has several chapters (5 and 6 in particular) addressing potential attacks, failure modes, and bias [1].

0: https://github.com/learning-at-home/hivemind

1: https://arxiv.org/abs/1912.04977

The Hivemind project is just that

https://github.com/learning-at-home/hivemind