@@ -7,8 +7,8 @@ We provide interactive benchmarks hosted on Hugging Face, in which
7
7
anyone can test their own SciML method. These benchmarks involve
8
8
regression problems posed on datasets provided in PLAID format. Some of
9
9
these datasets have been introduced in the MMGP (Mesh Morphing Gaussian
10
- Process) paper ` casenave2023mmgp ` , and the PLAID paper
11
- ` casenave2025plaid ` . A ranking is automatically updated based on a score
10
+ Process) paper @ casenave2023mmgp , and the PLAID paper
11
+ @ casenave2025plaid . A ranking is automatically updated based on a score
12
12
computed on the testing set of each dataset. For the benchmarks to be
13
13
meaningful, the outputs on the testing sets are not made public.
14
14
@@ -18,13 +18,24 @@ $\{ \mathbf{U}^i_{\rm pred} \}_{i=1}^{n_\star}$ be the test observations
18
18
and predictions, respectively, of a given field of interest. The
19
19
relative RMSE is defined as
20
20
21
- $$ \mathrm{RRMSE}_f(\mathbf{U}_{\rm ref}, \mathbf{U}_{\rm pred}) = \left( \frac{1}{n_\star}\sum_{i=1}^{n_\star} \frac{\frac{1}{N^i}\|\mathbf{U}^i_{\rm ref} - \mathbf{U}^i_{\rm pred}\|_2^2}{\|\mathbf{U}^i_{\rm ref}\|_\infty^2} \right)^{1/2}, $$
21
+ Inline: $E = mc^2$
22
+
23
+ Block:
24
+ $$
25
+ \int_0^1 x^2 dx = \frac{1}{3}
26
+ $$
27
+
28
+ $$
29
+ \mathrm{RRMSE}_f(\mathbf{U}_{\rm ref}, \mathbf{U}_{\rm pred}) = \left( \frac{1}{n_\star}\sum_{i=1}^{n_\star} \frac{\frac{1}{N^i}\|\mathbf{U}^i_{\rm ref} - \mathbf{U}^i_{\rm pred}\|_2^2}{\|\mathbf{U}^i_{\rm ref}\|_\infty^2} \right)^{1/2},
30
+ $$
22
31
23
32
where $N^i$ is the number of nodes in the mesh $i$, and
24
33
$\max(\mathbf{U}^i_ {\rm ref})$ is the maximum entry in the vector
25
34
$\mathbf{U}^i_ {\rm ref}$. Similarly for scalar outputs:
26
35
27
- $$ \mathrm{RRMSE}_s(\mathbf{w}_{\rm ref}, \mathbf{w}_{\rm pred}) = \left( \frac{1}{n_\star} \sum_{i=1}^{n_\star} \frac{|w^i_{\rm ref} - w_{\rm pred}^i|^2}{|w^i_{\rm ref}|^2} \right)^{1/2}. $$
36
+ $$
37
+ \mathrm{RRMSE}_s(\mathbf{w}_{\rm ref}, \mathbf{w}_{\rm pred}) = \left( \frac{1}{n_\star} \sum_{i=1}^{n_\star} \frac{|w^i_{\rm ref} - w_{\rm pred}^i|^2}{|w^i_{\rm ref}|^2} \right)^{1/2}.
38
+ $$
28
39
29
40
## Resources
30
41
188
199
</div >
189
200
190
201
## References
191
-
192
- [ ^ bib ]
202
+ ``` bibtex
0 commit comments