A Generalized Singular Value Theory for Neural Networks

• URL: http://arxiv.org/abs/2605.06938v1
• Date: Thu, 07 May 2026 20:55:14 GMT
• Title: A Generalized Singular Value Theory for Neural Networks
• Abstract summary: Most modern neural architectures admit a generalized SVD representation in which they are left-invertible before a final linear layer.<n>We show that perturbations in the left-invertible nonlinear portion of the input-output behavior can be made to be emphnorm preserving''<n>We provide a proof-of-concept that the learned representation can be used to identify adversarial perturbations to model inputs.
• Score: 0.7829352305480285
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Building on the abstract Generalized Singular Value Decomposition (GSVD) theory of Brown et al. [2025], we prove that most modern neural architectures admit a generalized SVD representation in which they are left-invertible before a final linear layer, with no change in input-output behavior. Furthermore, the left-invertible nonlinear portion of the input-output behavior can be made to be \emph{norm preserving}, meaning that perturbations in the left-invertible ``embedding'' (the activations prior to the final linear layer in this representation) correspond proportionally to changes in the input, i.e., distance in feature space can be calibrated directly to distance in input space. We provide a data-driven algorithm for estimating this representation from trained models and propose a model architecture that naturally facilitates the decomposition. We then provide a proof-of-concept that the learned representation can be used to identify adversarial perturbations to model inputs, and develop the theory necessary for future applications to areas such as model bias and invertibility.

Related papers

• Impact of Connectivity on Laplacian Representations in Reinforcement Learning [9.306521175972588]
  We show an upper bound on the approximation error of linear value function approximation under the learned spectral features.<n>We further bound the error introduced by the eigenvector estimation itself, leading to an end-to-end error decomposition.<n>Our results hold for general (non-uniform) policies without any assumptions on the symmetry of the induced transition kernel.
  arXiv  Detail & Related papers  (2026-03-09T16:20:31Z)
• Generalization in Representation Models via Random Matrix Theory: Application to Recurrent Networks [7.721672385781673]
  We first study the generalization error of models that use a fixed feature representation (frozen intermediate layers) followed by a trainable readout layer.<n>We apply Random Matrix Theory to derive a closed-form expression for the generalization error.<n>We then apply this analysis to recurrent representations and obtain concise formula that characterize their performance.
  arXiv  Detail & Related papers  (2025-11-04T09:30:31Z)
• I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data? [76.15163242945813]
  Large language models (LLMs) have led many to conclude that they exhibit a form of intelligence.<n>We introduce a novel generative model that generates tokens on the basis of human-interpretable concepts represented as latent discrete variables.
  arXiv  Detail & Related papers  (2025-03-12T01:21:17Z)
• Bilinear Convolution Decomposition for Causal RL Interpretability [0.0]
  Efforts to interpret reinforcement learning (RL) models often rely on high-level techniques such as attribution or probing.<n>This work proposes replacing nonlinearities in convolutional neural networks (ConvNets) with bilinear variants, to produce a class of models for which these limitations can be addressed.<n>We show bilinear model variants perform comparably in model-free reinforcement learning settings, and give a side by side comparison on ProcGen environments.
  arXiv  Detail & Related papers  (2024-12-01T19:32:04Z)
• State-space models can learn in-context by gradient descent [1.3087858009942543]
  We show that state-space models can perform gradient-based learning and use it for in-context learning in much the same way as transformers.<n>Specifically, we prove that a single structured state-space model layer, augmented with multiplicative input and output gating, can reproduce the outputs of an implicit linear model.<n>We also provide novel insights into the relationship between state-space models and linear self-attention, and their ability to learn in-context.
  arXiv  Detail & Related papers  (2024-10-15T15:22:38Z)
• Unsupervised Representation Learning from Sparse Transformation Analysis [79.94858534887801]
  We propose to learn representations from sequence data by factorizing the transformations of the latent variables into sparse components. Input data are first encoded as distributions of latent activations and subsequently transformed using a probability flow model.
  arXiv  Detail & Related papers  (2024-10-07T23:53:25Z)
• Disentanglement via Latent Quantization [60.37109712033694]
  In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space. We demonstrate the broad applicability of this approach by adding it to both basic data-re (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models.
  arXiv  Detail & Related papers  (2023-05-28T06:30:29Z)
• Log-linear Guardedness and its Implications [116.87322784046926]
  Methods for erasing human-interpretable concepts from neural representations that assume linearity have been found to be tractable and useful. This work formally defines the notion of log-linear guardedness as the inability of an adversary to predict the concept directly from the representation. We show that, in the binary case, under certain assumptions, a downstream log-linear model cannot recover the erased concept.
  arXiv  Detail & Related papers  (2022-10-18T17:30:02Z)
• InteL-VAEs: Adding Inductive Biases to Variational Auto-Encoders via Intermediary Latents [60.785317191131284]
  We introduce a simple and effective method for learning VAEs with controllable biases by using an intermediary set of latent variables. In particular, it allows us to impose desired properties like sparsity or clustering on learned representations. We show that this, in turn, allows InteL-VAEs to learn both better generative models and representations.
  arXiv  Detail & Related papers  (2021-06-25T16:34:05Z)
• Generative Model without Prior Distribution Matching [26.91643368299913]
  Variational Autoencoder (VAE) and its variations are classic generative models by learning a low-dimensional latent representation to satisfy some prior distribution. We propose to let the prior match the embedding distribution rather than imposing the latent variables to fit the prior.
  arXiv  Detail & Related papers  (2020-09-23T09:33:24Z)
• Exponentially Weighted l_2 Regularization Strategy in Constructing Reinforced Second-order Fuzzy Rule-based Model [72.57056258027336]
  In the conventional Takagi-Sugeno-Kang (TSK)-type fuzzy models, constant or linear functions are usually utilized as the consequent parts of the fuzzy rules. We introduce an exponential weight approach inspired by the weight function theory encountered in harmonic analysis.
  arXiv  Detail & Related papers  (2020-07-02T15:42:15Z)

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.