How to get the most out of Twinned Regression Methods
- URL: http://arxiv.org/abs/2301.01383v1
- Date: Tue, 3 Jan 2023 22:37:44 GMT
- Title: How to get the most out of Twinned Regression Methods
- Authors: Sebastian J. Wetzel
- Abstract summary: Twinned regression methods are designed to solve the dual problem to the original regression problem.
A solution to the original regression problem can be obtained by ensembling predicted differences between the targets of an unknown data point and multiple known anchor data points.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Twinned regression methods are designed to solve the dual problem to the
original regression problem, predicting differences between regression targets
rather then the targets themselves. A solution to the original regression
problem can be obtained by ensembling predicted differences between the targets
of an unknown data point and multiple known anchor data points. We explore
different aspects of twinned regression methods: (1) We decompose different
steps in twinned regression algorithms and examine their contributions to the
final performance, (2) We examine the intrinsic ensemble quality, (3) We
combine twin neural network regression with k-nearest neighbor regression to
design a more accurate and efficient regression method, and (4) we develop a
simplified semi-supervised regression scheme.
Related papers
- Generalized Regression with Conditional GANs [2.4171019220503402]
We propose to learn a prediction function whose outputs, when paired with the corresponding inputs, are indistinguishable from feature-label pairs in the training dataset.
We show that this approach to regression makes fewer assumptions on the distribution of the data we are fitting to and, therefore, has better representation capabilities.
arXiv Detail & Related papers (2024-04-21T01:27:47Z) - A Novel Approach in Solving Stochastic Generalized Linear Regression via
Nonconvex Programming [1.6874375111244329]
This paper considers a generalized linear regression model as a problem with chance constraints.
The results of the proposed algorithm were over 1 to 2 percent better than the ordinary logistic regression model.
arXiv Detail & Related papers (2024-01-16T16:45:51Z) - Anchor Data Augmentation [53.39044919864444]
We propose a novel algorithm for data augmentation in nonlinear over-parametrized regression.
Our data augmentation algorithm borrows from the literature on causality and extends the recently proposed Anchor regression (AR) method for data augmentation.
arXiv Detail & Related papers (2023-11-12T21:08:43Z) - Twin Neural Network Improved k-Nearest Neighbor Regression [0.0]
Twin neural network regression is trained to predict differences between regression targets rather than the targets themselves.
A solution to the original regression problem can be obtained by ensembling predicted differences between the targets of an unknown data point and multiple known anchor data points.
arXiv Detail & Related papers (2023-10-01T13:20:49Z) - A Bayesian Robust Regression Method for Corrupted Data Reconstruction [5.298637115178182]
We develop an effective robust regression method that can resist adaptive adversarial attacks.
First, we propose the novel TRIP (hard Thresholding approach to Robust regression with sImple Prior) algorithm.
We then use the idea of Bayesian reweighting to construct the more robust BRHT (robust Bayesian Reweighting regression via Hard Thresholding) algorithm.
arXiv Detail & Related papers (2022-12-24T17:25:53Z) - Vector-Valued Least-Squares Regression under Output Regularity
Assumptions [73.99064151691597]
We propose and analyse a reduced-rank method for solving least-squares regression problems with infinite dimensional output.
We derive learning bounds for our method, and study under which setting statistical performance is improved in comparison to full-rank method.
arXiv Detail & Related papers (2022-11-16T15:07:00Z) - Poseur: Direct Human Pose Regression with Transformers [119.79232258661995]
We propose a direct, regression-based approach to 2D human pose estimation from single images.
Our framework is end-to-end differentiable, and naturally learns to exploit the dependencies between keypoints.
Ours is the first regression-based approach to perform favorably compared to the best heatmap-based pose estimation methods.
arXiv Detail & Related papers (2022-01-19T04:31:57Z) - Human Pose Regression with Residual Log-likelihood Estimation [48.30425850653223]
We propose a novel regression paradigm with Residual Log-likelihood Estimation (RLE) to capture the underlying output distribution.
RLE learns the change of the distribution instead of the unreferenced underlying distribution to facilitate the training process.
Compared to the conventional regression paradigm, regression with RLE bring 12.4 mAP improvement on MSCOCO without any test-time overhead.
arXiv Detail & Related papers (2021-07-23T15:06:31Z) - Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing
Regressions In NLP Model Updates [68.09049111171862]
This work focuses on quantifying, reducing and analyzing regression errors in the NLP model updates.
We formulate the regression-free model updates into a constrained optimization problem.
We empirically analyze how model ensemble reduces regression.
arXiv Detail & Related papers (2021-05-07T03:33:00Z) - A Hypergradient Approach to Robust Regression without Correspondence [85.49775273716503]
We consider a variant of regression problem, where the correspondence between input and output data is not available.
Most existing methods are only applicable when the sample size is small.
We propose a new computational framework -- ROBOT -- for the shuffled regression problem.
arXiv Detail & Related papers (2020-11-30T21:47:38Z)
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.