-
Hello,
I appreciate your works!
I want to say it before a question.
I'm trying to use map sparsification function in [Keep it Brief: Scalable Creation of Compressed Localization Maps].
The obj…
-
### Feature request
There is a GitHub repo out with the necessary kernels and code (and a great paper) to train a transformer based models using int4.
The authors use a couple of algorithms to ge…
-
hi how are you using arcface as loss. I could only see Cross ENtropy loss in your implementation.
-
### What happened + What you expected to happen
For context see: https://discuss.ray.io/t/malformed-reparameterization-trick-in-squashed-gaussian/9651/3
Raised here as an issue at the behest of @A…
-
## 🚀 Feature
The [`opt_einsum` project](https://github.com/dgasmith/opt_einsum) provides algorithms for rearranging `einsum` expressions for best performance. It has been [integrated](https://numpy.o…
-
Nonlinear optimization algorithms that leverage just the gradient information (i.e. "first-order methods") can have trouble traversing through the cost function as the hessian becomes ill-conditioned.…
-
### 🐛 Describe the bug
On a toy regression model with pytorch 2.1.2 on cpu, `torch.autocast` is really slow.
Without `with torch.autocast(device_type="cpu", dtype=torch.bfloat16, cache_enabled=True)…
ldv1 updated
4 months ago
-
# Title
Tutorial on Efficient Hyperparameter Optimization for Machine Learning
# Responsible person(s)
Marcel Aach ([m.aach@fz-juelich.de](mailto:m.aach@fz-juelich.de)), JSC and University of Icela…
-
Hi Plasmo developers,
I just came across one of the older issues that asks about decomposition support in Plasmo.jl and also read the developer's reply. I am wondering if a combo of Plasmo.jl and P…
-
This is a 2d toy problem with no feasible region within the constraints (x-y > 0 and -1 > x - y; reported as a bug in scipy here
https://github.com/scipy/scipy/issues/7618 )
Using the R interface…