On Feature Scaling of Recursive Feature Machines

• URL: http://arxiv.org/abs/2303.15745v1
• Date: Tue, 28 Mar 2023 06:00:41 GMT
• Title: On Feature Scaling of Recursive Feature Machines
• Abstract summary: We explore the behavior of Recursive Feature Machines (RFMs) RFMs learn features via the average outer product gradient. We observe intriguing patterns in the Mean Squared Error (MSE) curves with the test MSE exhibiting a decrease-increase-decrease pattern.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this technical report, we explore the behavior of Recursive Feature Machines (RFMs), a type of novel kernel machine that recursively learns features via the average gradient outer product, through a series of experiments on regression datasets. When successively adding random noise features to a dataset, we observe intriguing patterns in the Mean Squared Error (MSE) curves with the test MSE exhibiting a decrease-increase-decrease pattern. This behavior is consistent across different dataset sizes, noise parameters, and target functions. Interestingly, the observed MSE curves show similarities to the "double descent" phenomenon observed in deep neural networks, hinting at new connection between RFMs and neural network behavior. This report lays the groundwork for future research into this peculiar behavior.

Related papers

• K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks [0.16921396880325779]
  Recursive Feature Machines (RFMs) are kernel machines that utilize the Average Gradient Outer Product (AGOP) as a mechanism for feature learning.<n>RFMs exhibit significantly lower performance than neural networks in certain data-corrupted scenarios.<n>We introduce a remarkably effective transformation applied to the training labels which promotes learning in noisy, complexly represented, and class-imbalanced data.
  arXiv  Detail & Related papers  (2026-07-01T02:08:05Z)
• Disordered Dynamics in High Dimensions: Connections to Random Matrices and Machine Learning [52.26396748560348]
  We provide an overview of high dimensional dynamical systems driven by random matrices.<n>We focus on applications to simple models of learning and generalization in machine learning theory.
  arXiv  Detail & Related papers  (2026-01-03T00:12:32Z)
• Spatial Reasoning with Denoising Models [49.83744014336816]
  We introduce a framework to perform reasoning over sets of continuous variables via denoising generative models.<n>For the first time, that order of generation can successfully be predicted by the denoising network itself.<n>Using these findings, we can increase the accuracy of specific reasoning tasks from 1% to >50%.
  arXiv  Detail & Related papers  (2025-02-28T14:08:30Z)
• Exploring Information-Theoretic Metrics Associated with Neural Collapse in Supervised Training [14.9343236333741]
  We introduce matrix entropy as an analytical tool for studying supervised learning. We show that matrix entropy effectively captures the variations in information content of data representations as neural networks approach Neural Collapse. We also propose Cross-Model Alignment (CMA) loss to optimize the fine-tuning of pretrained models.
  arXiv  Detail & Related papers  (2024-09-25T09:26:06Z)
• Noise-Resilient Unsupervised Graph Representation Learning via Multi-Hop Feature Quality Estimation [53.91958614666386]
  Unsupervised graph representation learning (UGRL) based on graph neural networks (GNNs) We propose a novel UGRL method based on Multi-hop feature Quality Estimation (MQE)
  arXiv  Detail & Related papers  (2024-07-29T12:24:28Z)
• Heterogeneous Multi-Task Gaussian Cox Processes [61.67344039414193]
  We present a novel extension of multi-task Gaussian Cox processes for modeling heterogeneous correlated tasks jointly. A MOGP prior over the parameters of the dedicated likelihoods for classification, regression and point process tasks can facilitate sharing of information between heterogeneous tasks. We derive a mean-field approximation to realize closed-form iterative updates for estimating model parameters.
  arXiv  Detail & Related papers  (2023-08-29T15:01:01Z)
• Deep Graph Reprogramming [112.34663053130073]
  "Deep graph reprogramming" is a model reusing task tailored for graph neural networks (GNNs) We propose an innovative Data Reprogramming paradigm alongside a Model Reprogramming paradigm.
  arXiv  Detail & Related papers  (2023-04-28T02:04:29Z)
• Capturing dynamical correlations using implicit neural representations [85.66456606776552]
  We develop an artificial intelligence framework which combines a neural network trained to mimic simulated data from a model Hamiltonian with automatic differentiation to recover unknown parameters from experimental data. In doing so, we illustrate the ability to build and train a differentiable model only once, which then can be applied in real-time to multi-dimensional scattering data.
  arXiv  Detail & Related papers  (2023-04-08T07:55:36Z)
• Selective Memory Recursive Least Squares: Recast Forgetting into Memory in RBF Neural Network Based Real-Time Learning [2.31120983784623]
  In radial basis function neural network (RBFNN) based real-time learning tasks, forgetting mechanisms are widely used. This paper proposes a real-time training method named selective memory recursive least squares (SMRLS) in which the classical forgetting mechanisms are recast into a memory mechanism. With SMRLS, the input space of the RBFNN is evenly divided into a finite number of partitions and a synthesized objective function is developed using synthesized samples from each partition.
  arXiv  Detail & Related papers  (2022-11-15T05:29:58Z)
• The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks [51.1848572349154]
  neural network models that perfectly fit noisy data can generalize well to unseen test data. We consider interpolating two-layer linear neural networks trained with gradient flow on the squared loss and derive bounds on the excess risk.
  arXiv  Detail & Related papers  (2021-08-25T22:01:01Z)
• Sparsely constrained neural networks for model discovery of PDEs [0.0]
  We present a modular framework that determines the sparsity pattern of a deep-learning based surrogate using any sparse regression technique. We show how a different network architecture and sparsity estimator improve model discovery accuracy and convergence on several benchmark examples.
  arXiv  Detail & Related papers  (2020-11-09T11:02:40Z)
• Probabilistic Numeric Convolutional Neural Networks [80.42120128330411]
  Continuous input signals like images and time series that are irregularly sampled or have missing values are challenging for existing deep learning methods. We propose Probabilistic Convolutional Neural Networks which represent features as Gaussian processes (GPs) We then define a convolutional layer as the evolution of a PDE defined on this GP, followed by a nonlinearity. In experiments we show that our approach yields a $3times$ reduction of error from the previous state of the art on the SuperPixel-MNIST dataset and competitive performance on the medical time2012 dataset PhysioNet.
  arXiv  Detail & Related papers  (2020-10-21T10:08:21Z)
• Bayesian neural networks and dimensionality reduction [4.039245878626346]
  A class of model-based approaches for such problems includes latent variables in an unknown non-linear regression function. VAEs are artificial neural networks (ANNs) that employ approximations to make computation tractable. We deploy Markov chain Monte Carlo sampling algorithms for Bayesian inference in ANN models with latent variables.
  arXiv  Detail & Related papers  (2020-08-18T17:11:07Z)
• NeuMiss networks: differentiable programming for supervised learning with missing values [0.0]
  We derive the analytical form of the optimal predictor under a linearity assumption. We propose a new principled architecture, named NeuMiss networks. They have good predictive accuracy with both a number of parameters and a computational complexity independent of the number of missing data patterns.
  arXiv  Detail & Related papers  (2020-07-03T11:42:25Z)
• Generalisation error in learning with random features and the hidden manifold model [23.71637173968353]
  We study generalised linear regression and classification for a synthetically generated dataset. We consider the high-dimensional regime and using the replica method from statistical physics. We show how to obtain the so-called double descent behaviour for logistic regression with a peak at the threshold. We discuss the role played by correlations in the data generated by the hidden manifold model.
  arXiv  Detail & Related papers  (2020-02-21T14:49:41Z)

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.