DOC update document references & include summary for papers at home page

README.md

@@ -60,18 +60,18 @@ We use the ``spin`` CLI to abstract away build details:
 
     # run the build using Meson/Ninja
     ./spin build
-    
+
     # you can run the following command to see what other options there are
     ./spin --help
     ./spin build --help
-    
+
     # For example, you might want to start from a clean build
     ./spin build --clean
-    
+
     # or build in parallel for faster builds
     ./spin build -j 2
 
-    # you will need to double check the build-install has the proper path 
+    # you will need to double check the build-install has the proper path
     # this might be different from machine to machine
     export PYTHONPATH=${PWD}/build-install/usr/lib/python3.9/site-packages
 
@@ -105,4 +105,4 @@ Alternatively, you can use editable installs
 
 References
 ==========
-[1]: [`Li, Adam, et al. "Manifold Oblique Random Forests: Towards Closing the Gap on Convolutional Deep Networks." arXiv preprint arXiv:1909.11799 (2019)`](https://arxiv.org/abs/1909.11799)
+[1]: [`Li, Adam, et al. "Manifold Oblique Random Forests: Towards Closing the Gap on Convolutional Deep Networks" SIAM Journal on Mathematics of Data Science, 5(1), 77-96, 2023`](https://doi.org/10.1137/21M1449117)

docs/modules/ensemble.rst

@@ -52,8 +52,8 @@ By **averaging** the estimates of predictive ability over several randomized
 trees one can **reduce the variance** of such an estimate and use it
 for feature selection. This is known as the mean decrease in impurity, or MDI.
 Refer to [L2014]_ for more information on MDI and feature importance
-evaluation with Random Forests. We implement the approach taken in [Li2019]_
-and [Tomita2015]_.
+evaluation with Random Forests. We implement the approach taken in [Li2023]_
+and [Tomita2020]_.
 
 .. warning::
 
@@ -80,8 +80,10 @@ to the prediction function.
     Practice" <1407.7502>`,
     PhD Thesis, U. of Liege, 2014.
 
- .. [Li2019] Li, Adam, et al. :arxiv:`"Manifold Oblique Random Forests: Towards
-    Closing the Gap on Convolutional Deep Networks."` arXiv preprint arXiv:1909.11799 (2019).
+ .. [Li2023] Li, Adam, et al. :doi:`"Manifold Oblique Random Forests: Towards
+    Closing the Gap on Convolutional Deep Networks" <10.1137/21M1449117>`,
+    SIAM Journal on Mathematics of Data Science, 5(1), 77-96, 2023.
 
- .. [Tomita2015] Tomita, Tyler M., et al. :arxiv:`"Sparse Projection Oblique Randomer Forests."`
-    arXiv preprint arXiv:1506.03410 (2015).
+ .. [Tomita2020] Tomita, Tyler M., et al. "Sparse Projection Oblique
+    Randomer Forests", The Journal of Machine Learning Research, 21(104),
+    1-39, 2020.

docs/references.bib

@@ -11,15 +11,19 @@ @article{breiman2001random
   publisher = {Springer}
 }
 
-@article{Li2019manifold,
-  title   = {Manifold Oblique Random Forests: Towards Closing the Gap on Convolutional Deep Networks},
-  author  = {Li, Adam and Perry, Ronan and Huynh, Chester and Tomita, Tyler M and Mehta, Ronak and Arroyo, Jesus and Patsolic, Jesse and Falk, Benjamin and Vogelstein, Joshua T},
-  journal = {arXiv preprint arXiv:1909.11799},
-  year    = {2019}
+@article{Li2023manifold,
+  author = {Li, Adam and Perry, Ronan and Huynh, Chester and Tomita, Tyler M. and Mehta, Ronak and Arroyo, Jesus and Patsolic, Jesse and Falk, Ben and Sarma, Sridevi and Vogelstein, Joshua},
+  title = {Manifold Oblique Random Forests: Towards Closing the Gap on Convolutional Deep Networks},
+  journal = {SIAM Journal on Mathematics of Data Science},
+  volume = {5},
+  number = {1},
+  pages = {77-96},
+  year = {2023},
+  doi = {10.1137/21M1449117},
 }
 
 @article{perry2021random,
-    title={Random Forests for Adaptive Nearest Neighbor Estimation of Information-Theoretic Quantities}, 
+    title={Random Forests for Adaptive Nearest Neighbor Estimation of Information-Theoretic Quantities},
     author={Ronan Perry and Ronak Mehta and Richard Guo and Eva Yezerets and Jesús Arroyo and Mike Powell and Hayden Helm and Cencheng Shen and Joshua T. Vogelstein},
     year={2021},
     eprint={1907.00325},
@@ -79,4 +83,4 @@ @article{Kraskov_2004
   note     = {Publisher: American Physical Society},
   pages    = {066138},
   file     = {APS Snapshot:/Users/adam2392/Zotero/storage/GRW23BYU/PhysRevE.69.html:text/html;Full Text PDF:/Users/adam2392/Zotero/storage/NJT9QCVA/Kraskov et al. - 2004 - Estimating mutual information.pdf:application/pdf}
-}
+}

sktree/ensemble/_supervised_forest.py

@@ -653,7 +653,7 @@ class PatchObliqueRandomForestClassifier(SimMatrixMixin, ForestClassifier):
     forest that fits a number of patch oblique decision tree classifiers
     on various sub-samples of the dataset and uses averaging to
     improve the predictive accuracy and control over-fitting. For more
-    details, see :footcite:`Li2019manifold`.
+    details, see :footcite:`Li2023manifold`.
 
     Parameters
     ----------
@@ -996,7 +996,7 @@ class PatchObliqueRandomForestRegressor(SimMatrixMixin, ForestRegressor):
     forest that fits a number of patch oblique decision tree regressors
     on various sub-samples of the dataset and uses averaging to
     improve the predictive accuracy and control over-fitting. For more
-    details, see :footcite:`Li2019manifold`.
+    details, see :footcite:`Li2023manifold`.
 
     Parameters
     ----------

sktree/tree/_classes.py

@@ -1301,7 +1301,7 @@ class PatchObliqueDecisionTreeClassifier(SimMatrixMixin, DecisionTreeClassifier)
     """A oblique decision tree classifier that operates over patches of data.
 
     A patch oblique decision tree is also known as a manifold oblique decision tree
-    (called MORF in :footcite:`Li2019manifold`), where the splitter is aware of
+    (called MORF in :footcite:`Li2023manifold`), where the splitter is aware of
     the structure in the data. For example, in an image, a patch would be contiguous
     along the rows and columns of the image. In a multivariate time-series, a patch
     would be contiguous over time, but possibly discontiguous over the sensors.
@@ -1791,7 +1791,7 @@ class PatchObliqueDecisionTreeRegressor(SimMatrixMixin, DecisionTreeRegressor):
     """A oblique decision tree regressor that operates over patches of data.
 
     A patch oblique decision tree is also known as a manifold oblique decision tree
-    (called MORF in :footcite:`Li2019manifold`), where the splitter is aware of
+    (called MORF in :footcite:`Li2023manifold`), where the splitter is aware of
     the structure in the data. For example, in an image, a patch would be contiguous
     along the rows and columns of the image. In a multivariate time-series, a patch
     would be contiguous over time, but possibly discontiguous over the sensors.