-
e.g.,
```python
res = ensure_zenodo(
key,
data=data,
paths=[
f"../../data/processed/{task_name_underscore}/sobol_regression.csv",
f"../../data/processed/{task_name…
-
**Motivation**
Although the surrogate type defines the surrogate construction, it cannot act as a generic algorithmic dispatch if the user already has a set of points `(x, y)`.
The proposed desi…
-
As described in Readme file, the ResNet, ViT, and MLP-Mixer checkpoints optimized using "Surrogate Gap Minimization Improves Sharpness-Aware Training" are provided. However, I can only find ViT-SAM, V…
-
-Desktop
---FCRN-DepthPrediction-master
------tensorflow
----------models
-------------------NYU_FCRN.ckpt.data-00000-of-00001
-------------------NYU_FCRN.ckpt.index
-------------------NYU_FCRN.…
-
I have a simple question: is it possible to apply your tool for surrogate models with two series blocks such as Hammerstein-Wiener structure? If so, your guidance would be much appreciated.
-
For many real world applications **exploration only** strategies are very useful to obtain precisely trained GP models on the whole design space. Up till now, this can be done by utilizing the UCB acq…
-
Pulling it from GALE paper
@Ginfung @timm
**Present**
Models:
BNH, Golinski, Srinivas, Two0bar Truss, Viennet2, water, ZDT(1, 2, 3, 4 and 6), DTLZX,
SE Models: FeatureModels(Web portal, eshop, cel…
-
Allow to use surrogate models in non-final iterations, and only the full, expensive, model in the last iteration. This will make things more efficient. What to do? One way that would suffice would be …
-
Investigate different classifiers that optimize AUC directly instead of some surrogate .
I'm aware of the following classifiers that support AUC optimization::
- Ranking SVM (e.g. svmlight or Fabian'…
-
Dear developers,
I trying to use the converter to convert a vgg16 pretrained on imagenet. The original model acc is around 71%, however after after conversion acc is 0.1%.
I'd like to know if the…