RbX: Region-based explanations of prediction models
- URL: http://arxiv.org/abs/2210.08721v1
- Date: Mon, 17 Oct 2022 03:38:06 GMT
- Title: RbX: Region-based explanations of prediction models
- Authors: Ismael Lemhadri, Harrison H. Li, and Trevor Hastie
- Abstract summary: Region-based explanations (RbX) is a model-agnostic method to generate local explanations of scalar outputs from a black-box prediction model.
RbX is guaranteed to satisfy a "sparsity axiom," which requires that features which do not enter into the prediction model are assigned zero importance.
- Score: 69.3939291118954
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We introduce region-based explanations (RbX), a novel, model-agnostic method
to generate local explanations of scalar outputs from a black-box prediction
model using only query access. RbX is based on a greedy algorithm for building
a convex polytope that approximates a region of feature space where model
predictions are close to the prediction at some target point. This region is
fully specified by the user on the scale of the predictions, rather than on the
scale of the features. The geometry of this polytope - specifically the change
in each coordinate necessary to escape the polytope - quantifies the local
sensitivity of the predictions to each of the features. These "escape
distances" can then be standardized to rank the features by local importance.
RbX is guaranteed to satisfy a "sparsity axiom," which requires that features
which do not enter into the prediction model are assigned zero importance. At
the same time, real data examples and synthetic experiments show how RbX can
more readily detect all locally relevant features than existing methods.
Related papers
- Guarantee Regions for Local Explanations [29.429229877959663]
We propose an anchor-based algorithm for identifying regions in which local explanations are guaranteed to be correct.
Our method produces an interpretable feature-aligned box where the prediction of the local surrogate model is guaranteed to match the predictive model.
arXiv Detail & Related papers (2024-02-20T06:04:44Z) - Multi-Modal Conformal Prediction Regions with Simple Structures by Optimizing Convex Shape Templates [19.504348671777006]
Conformal prediction is a statistical tool for producing prediction regions for machine learning models that are valid with high probability.
A key component of conformal prediction algorithms is a emphnon-conformity score function that quantifies how different a model's prediction is from the unknown ground truth value.
We propose a method that optimize parameterized emphshape template functions over calibration data, which results in non-conformity score functions that produce prediction regions with minimum volume.
arXiv Detail & Related papers (2023-12-12T17:00:13Z) - PRISM: Probabilistic Real-Time Inference in Spatial World Models [52.878769723544615]
PRISM is a method for real-time filtering in a probabilistic generative model of agent motion and visual perception.
The proposed solution runs at 10Hz real-time and is similarly accurate to state-of-the-art SLAM in small to medium-sized indoor environments.
arXiv Detail & Related papers (2022-12-06T13:59:06Z) - LOPR: Latent Occupancy PRediction using Generative Models [49.15687400958916]
LiDAR generated occupancy grid maps (L-OGMs) offer a robust bird's eye-view scene representation.
We propose a framework that decouples occupancy prediction into: representation learning and prediction within the learned latent space.
arXiv Detail & Related papers (2022-10-03T22:04:00Z) - B\'ezier Curve Gaussian Processes [8.11969931278838]
This paper proposes a new probabilistic sequence model building on probabilistic B'ezier curves.
Combined with a Mixture Density network, Bayesian conditional inference can be performed without the need for mean field variational approximation.
The model is used for pedestrian trajectory prediction, where a generated prediction also serves as a GP prior.
arXiv Detail & Related papers (2022-05-03T19:49:57Z) - Distributional Gradient Boosting Machines [77.34726150561087]
Our framework is based on XGBoost and LightGBM.
We show that our framework achieves state-of-the-art forecast accuracy.
arXiv Detail & Related papers (2022-04-02T06:32:19Z) - Semantic Segmentation by Early Region Proxy [53.594035639400616]
We present a novel and efficient modeling that starts from interpreting the image as a tessellation of learnable regions.
To model region-wise context, we exploit Transformer to encode regions in a sequence-to-sequence manner.
Semantic segmentation is now carried out as per-region prediction on top of the encoded region embeddings.
arXiv Detail & Related papers (2022-03-26T10:48:32Z) - MD-split+: Practical Local Conformal Inference in High Dimensions [0.5439020425819]
MD-split+ is a practical local conformal approach that creates X partitions based on localized model performance.
We discuss how our local partitions philosophically align with expected behavior from an unattainable conditional conformal inference approach.
arXiv Detail & Related papers (2021-07-07T15:19:16Z) - Making Affine Correspondences Work in Camera Geometry Computation [62.7633180470428]
Local features provide region-to-region rather than point-to-point correspondences.
We propose guidelines for effective use of region-to-region matches in the course of a full model estimation pipeline.
Experiments show that affine solvers can achieve accuracy comparable to point-based solvers at faster run-times.
arXiv Detail & Related papers (2020-07-20T12:07:48Z) - Gaussian Process Regression with Local Explanation [28.90948136731314]
We propose GPR with local explanation, which reveals the feature contributions to the prediction of each sample.
In the proposed model, both the prediction and explanation for each sample are performed using an easy-to-interpret locally linear model.
For a new test sample, the proposed model can predict the values of its target variable and weight vector, as well as their uncertainties.
arXiv Detail & Related papers (2020-07-03T13:22:24Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.