Belted and Ensembled Neural Network for Linear and Nonlinear Sufficient Dimension Reduction

• URL: http://arxiv.org/abs/2412.08961v1
• Date: Thu, 12 Dec 2024 05:48:34 GMT
• Title: Belted and Ensembled Neural Network for Linear and Nonlinear Sufficient Dimension Reduction
• Authors: Yin Tang, Bing Li,
• Abstract summary: We introduce a unified, flexible, and easy-to-implement framework of sufficient dimension reduction. The framework is achieved by a specially structured neural network. Thanks to the advantage of the neural network, the method is very fast to compute.
• Score: 5.024172766626326
• License:
• Abstract: We introduce a unified, flexible, and easy-to-implement framework of sufficient dimension reduction that can accommodate both linear and nonlinear dimension reduction, and both the conditional distribution and the conditional mean as the targets of estimation. This unified framework is achieved by a specially structured neural network -- the Belted and Ensembled Neural Network (BENN) -- that consists of a narrow latent layer, which we call the belt, and a family of transformations of the response, which we call the ensemble. By strategically placing the belt at different layers of the neural network, we can achieve linear or nonlinear sufficient dimension reduction, and by choosing the appropriate transformation families, we can achieve dimension reduction for the conditional distribution or the conditional mean. Moreover, thanks to the advantage of the neural network, the method is very fast to compute, overcoming a computation bottleneck of the traditional sufficient dimension reduction estimators, which involves the inversion of a matrix of dimension either p or n. We develop the algorithm and convergence rate of our method, compare it with existing sufficient dimension reduction methods, and apply it to two data examples.

Related papers

• Pushing the Limits of Large Language Model Quantization via the Linearity Theorem [71.3332971315821]
  We present a "line theoremarity" establishing a direct relationship between the layer-wise $ell$ reconstruction error and the model perplexity increase due to quantization. This insight enables two novel applications: (1) a simple data-free LLM quantization method using Hadamard rotations and MSE-optimal grids, dubbed HIGGS, and (2) an optimal solution to the problem of finding non-uniform per-layer quantization levels.
  arXiv  Detail & Related papers  (2024-11-26T15:35:44Z)
• Golden Ratio-Based Sufficient Dimension Reduction [6.184279198087624]
  We propose a neural network based sufficient dimension reduction method. It identifies the structural dimension effectively and estimates the central space well. It takes advantages of approximation capabilities of neural networks for functions in Barron classes and leads to reduced computation cost.
  arXiv  Detail & Related papers  (2024-10-25T04:15:15Z)
• Cons-training tensor networks [2.8834278113855896]
  We introduce a novel family of tensor networks, termed. textitconstrained matrix product states (MPS) These networks incorporate exactly arbitrary discrete linear constraints, including inequalities, into sparse block structures. These networks are particularly tailored for modeling distributions with support strictly over the feasible space.
  arXiv  Detail & Related papers  (2024-05-15T00:13:18Z)
• Robust Stochastically-Descending Unrolled Networks [85.6993263983062]
  Deep unrolling is an emerging learning-to-optimize method that unrolls a truncated iterative algorithm in the layers of a trainable neural network. We show that convergence guarantees and generalizability of the unrolled networks are still open theoretical problems. We numerically assess unrolled architectures trained under the proposed constraints in two different applications.
  arXiv  Detail & Related papers  (2023-12-25T18:51:23Z)
• Training Recurrent Neural Networks by Sequential Least Squares and the Alternating Direction Method of Multipliers [0.20305676256390928]
  We propose the use of convex and twice-differentiable loss and regularization terms for determining optimal hidden network parameters. We combine sequential least squares with alternating direction multipliers. The performance of the algorithm is tested in a nonlinear system identification benchmark.
  arXiv  Detail & Related papers  (2021-12-31T08:43:04Z)
• Subquadratic Overparameterization for Shallow Neural Networks [60.721751363271146]
  We provide an analytical framework that allows us to adopt standard neural training strategies. We achieve the desiderata viaak-Lojasiewicz, smoothness, and standard assumptions.
  arXiv  Detail & Related papers  (2021-11-02T20:24:01Z)
• AdaLoss: A computationally-efficient and provably convergent adaptive gradient method [7.856998585396422]
  We propose a computationally-friendly learning schedule, "AnomidaLoss", which uses the information of the loss function to adjust rate numerically. We verify the scope of the numerical experiments by applications in LSTM models for text and control problems.
  arXiv  Detail & Related papers  (2021-09-17T01:45:25Z)
• Improving Metric Dimensionality Reduction with Distributed Topology [68.8204255655161]
  DIPOLE is a dimensionality-reduction post-processing step that corrects an initial embedding by minimizing a loss functional with both a local, metric term and a global, topological term. We observe that DIPOLE outperforms popular methods like UMAP, t-SNE, and Isomap on a number of popular datasets.
  arXiv  Detail & Related papers  (2021-06-14T17:19:44Z)
• Joint Dimensionality Reduction for Separable Embedding Estimation [43.22422640265388]
  Low-dimensional embeddings for data from disparate sources play critical roles in machine learning, multimedia information retrieval, and bioinformatics. We propose a supervised dimensionality reduction method that learns linear embeddings jointly for two feature vectors representing data of different modalities or data from distinct types of entities. Our approach compares favorably against other dimensionality reduction methods, and against a state-of-the-art method of bilinear regression for predicting gene-disease associations.
  arXiv  Detail & Related papers  (2021-01-14T08:48:37Z)
• A Convergence Theory Towards Practical Over-parameterized Deep Neural Networks [56.084798078072396]
  We take a step towards closing the gap between theory and practice by significantly improving the known theoretical bounds on both the network width and the convergence time. We show that convergence to a global minimum is guaranteed for networks with quadratic widths in the sample size and linear in their depth at a time logarithmic in both. Our analysis and convergence bounds are derived via the construction of a surrogate network with fixed activation patterns that can be transformed at any time to an equivalent ReLU network of a reasonable size.
  arXiv  Detail & Related papers  (2021-01-12T00:40:45Z)
• Controllable Orthogonalization in Training DNNs [96.1365404059924]
  Orthogonality is widely used for training deep neural networks (DNNs) due to its ability to maintain all singular values of the Jacobian close to 1. This paper proposes a computationally efficient and numerically stable orthogonalization method using Newton's iteration (ONI) We show that our method improves the performance of image classification networks by effectively controlling the orthogonality to provide an optimal tradeoff between optimization benefits and representational capacity reduction. We also show that ONI stabilizes the training of generative adversarial networks (GANs) by maintaining the Lipschitz continuity of a network, similar to spectral normalization (
  arXiv  Detail & Related papers  (2020-04-02T10:14:27Z)

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.