Conformal Transformation of Kernels: A Geometric Perspective on Text Classification

• URL: http://arxiv.org/abs/2406.00499v1
• Date: Sat, 1 Jun 2024 17:01:01 GMT
• Title: Conformal Transformation of Kernels: A Geometric Perspective on Text Classification
• Abstract summary: We investigate the effects of conformal transformations on kernel functions used in Support Vector Machines. Our experiments were conducted on the Reuters dataset on two types of binary classification tasks. The findings indicate that conformal transformations can significantly improve kernel performance, particularly for sub-optimal kernels.
• Score: 44.99833362998488
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this article we investigate the effects of conformal transformations on kernel functions used in Support Vector Machines. Our focus lies in the task of text document categorization, which involves assigning each document to a particular category. We introduce a new Gaussian Cosine kernel alongside two conformal transformations. Building upon previous studies that demonstrated the efficacy of conformal transformations in increasing class separability on synthetic and low-dimensional datasets, we extend this analysis to the high-dimensional domain of text data. Our experiments, conducted on the Reuters dataset on two types of binary classification tasks, compare the performance of Linear, Gaussian, and Gaussian Cosine kernels against their conformally transformed counterparts. The findings indicate that conformal transformations can significantly improve kernel performance, particularly for sub-optimal kernels. Specifically, improvements were observed in 60% of the tested scenarios for the Linear kernel, 84% for the Gaussian kernel, and 80% for the Gaussian Cosine kernel. In light of these findings, it becomes clear that conformal transformations play a pivotal role in enhancing kernel performance, offering substantial benefits.

Related papers

• Elastic Triangle Splatting [51.19217843214773]
  We introduce an elastic kernel function that features bilateral gradient support across the boundary and an adaptive boundary value.<n>Under isolated comparison, our elastic kernel outperforms existing kernels on shape reconstruction and in the majority of novel-view benchmarks.
  arXiv  Detail & Related papers  (2026-08-29T07:23:33Z)
• Boosting t-SNE Efficiency for Sequencing Data: Insights from Kernel Selection [7.122236250657051]
  t-distributed Neighbor Embedding (t-SNE) is widely used for visualizing and analyzing high-dimensional biological sequencing data.<n>Recent work proposed the isolation kernel as an alternative, yet it may not optimally capture sequence similarities.<n>We show that the cosine similarity kernel provides the most robust performance across different data types and embedding strategies.
  arXiv  Detail & Related papers  (2025-12-17T19:13:59Z)
• Feature maps for the Laplacian kernel and its generalizations [3.671202973761375]
  Unlike the Gaussian kernel, the Laplacian kernel is not separable. We provide random features for the Laplacian kernel and its two generalizations. We demonstrate the efficacy of these random feature maps on real datasets.
  arXiv  Detail & Related papers  (2025-02-21T16:36:20Z)
• SuperGaussians: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors [51.54964131894217]
  We introduce a new method called SuperGaussians that utilizes spatially varying colors and opacity in a single Gaussian primitive to improve its representation ability. We have implemented bilinear, movable kernels, and even tiny neural networks as spatially varying functions.
  arXiv  Detail & Related papers  (2024-11-28T07:36:22Z)
• ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining [104.34751911174196]
  We build a large-scale dataset of 3DGS using ShapeNet and ModelNet datasets. Our dataset ShapeSplat consists of 65K objects from 87 unique categories. We introduce textbftextitGaussian-MAE, which highlights the unique benefits of representation learning from Gaussian parameters.
  arXiv  Detail & Related papers  (2024-08-20T14:49:14Z)
• Variance-Reducing Couplings for Random Features [57.73648780299374]
  Random features (RFs) are a popular technique to scale up kernel methods in machine learning. We find couplings to improve RFs defined on both Euclidean and discrete input spaces. We reach surprising conclusions about the benefits and limitations of variance reduction as a paradigm.
  arXiv  Detail & Related papers  (2024-05-26T12:25:09Z)
• Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation [25.387090319723715]
  Training semantic segmentation models with few annotated samples has great potential in various real-world applications. For the few-shot segmentation task, the main challenge is how to accurately measure the semantic correspondence between the support and query samples. We propose to aggregate the learnable covariance matrices with a deformable 4D Transformer to effectively predict the segmentation map.
  arXiv  Detail & Related papers  (2022-07-30T20:41:38Z)
• Fully trainable Gaussian derivative convolutional layer [0.0]
  We propose a high-level layer based on anisotropic, oriented and shifted Gaussian derivative kernels. The results show that the proposed layer has competitive performance compared to previous works. It can be successfully included in common deep architectures such as VGG16 for image classification and U-net for image segmentation.
  arXiv  Detail & Related papers  (2022-07-18T08:16:04Z)
• Generalized Reference Kernel for One-class Classification [100.53532594448048]
  We formulate a new generalized reference kernel to improve the original base kernel using a set of reference vectors. Our analysis and experimental results show that the new formulation provides approaches to regularize, adjust the rank, and incorporate additional information into the kernel itself.
  arXiv  Detail & Related papers  (2022-05-01T18:36:55Z)
• On Learning the Transformer Kernel [13.955526058823166]
  KERNELIZED TRANSFORMER is a generic, scalable, data driven framework for learning the kernel function in Transformers. Our framework approximates the Transformer kernel as a dot product between spectral feature maps and learns the kernel by learning the spectral distribution.
  arXiv  Detail & Related papers  (2021-10-15T19:20:25Z)
• Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition [54.07797071198249]
  We introduce a new scalable variational Gaussian process approximation which provides a high fidelity approximation while retaining general applicability. We demonstrate that, on a range of regression and classification problems, our approach can exploit input space symmetries such as translations and reflections. Notably, our approach achieves state-of-the-art results on CIFAR-10 among pure GP models.
  arXiv  Detail & Related papers  (2021-06-10T18:17:57Z)
• Why Approximate Matrix Square Root Outperforms Accurate SVD in Global Covariance Pooling? [59.820507600960745]
  We propose a new GCP meta-layer that uses SVD in the forward pass, and Pad'e Approximants in the backward propagation to compute the gradients. The proposed meta-layer has been integrated into different CNN models and achieves state-of-the-art performances on both large-scale and fine-grained datasets.
  arXiv  Detail & Related papers  (2021-05-06T08:03:45Z)
• On Approximation in Deep Convolutional Networks: a Kernel Perspective [12.284934135116515]
  We study the success of deep convolutional networks on tasks involving high-dimensional data such as images or audio. We study this theoretically and empirically through the lens of kernel methods, by considering multi-layer convolutional kernels. We find that while expressive kernels operating on input patches are important at the first layer, simpler kernels can suffice in higher layers for good performance.
  arXiv  Detail & Related papers  (2021-02-19T17:03:42Z)
• Advanced Stationary and Non-Stationary Kernel Designs for Domain-Aware Gaussian Processes [0.0]
  We propose advanced kernel designs that only allow for functions with certain desirable characteristics to be elements of the reproducing kernel Hilbert space (RKHS) We will show the impact of advanced kernel designs on Gaussian processes using several synthetic and two scientific data sets.
  arXiv  Detail & Related papers  (2021-02-05T22:07:56Z)

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.