-
As pointed out in #30, the kwarg `copy_initial_weights` is hard to understand.
First, we should investigate whether it's not sufficient just to detach when branching from the outer loop model when …
-
# 🚀 Feature Request
## Motivation
https://botorch.org/api/utils.html#botorch.utils.multi_objective.hypervolume.Hypervolume
says: TODO: write this in C++ for faster looping.
There is a …
-
hello! I was reading the TFCO paper ([Cotter et al. 2018](https://arxiv.org/pdf/1809.04198.pdf)), and it has a great section on past work, including this section:
> Agarwal et al. (2018) recently ad…
-
## 🚀 Feature
As requested in the context of distributed work in #44715 #44791 (cc @jbschlosser @vincentqb @albanD @wanchaol, [internal doc](https://fb.quip.com/XMLfA0XR4tnp)) and of meta-learning i…
-
In the examples of remake.md, the order of parameters in the queried parameter object is not known.
This makes it difficult to provide reasonable initial values for each parameter.
Document, how t…
bgctw updated
5 months ago
-
Dear community, authors,
As explained in #93 I'm trying to use the MonoGS tracker to retreive a camera pose.
In my particular case I am training a gaussian splatting scene and then trying to ret…
-
Hi Team
I read about [the project](https://github.com/jump-dev/GSOC2020/blob/master/ideas-list.md#optimization-problem-differentiation) to enable `JuMP.jl` differentiate solution of problem w.r.t. …
-
### 🐛 Describe the bug
As per title. As an example, let's consider the `sampled_addmm` method which is semantically equivalent to
`sampled_addmm(s, m1, m2, alpha, beta) := alpha * (m1 @ m2).sparse…
-
## Proposal
HoloPy version 4 should rely on [`pymc`](https://www.pymc.io/welcome.html) for inference.
## Rationale
When we first included Bayesian inference in HoloPy, the options for efficient …
-
**Describe the bug**
I encountered an issue when using DeepSpeed 0.12.4 with the [OpenChat trainer](https://github.com/imoneoi/openchat), where checkpointing failed and raised an NCCL error. However,…