Contrastive Entropy Bounds for Density and Conditional Density Decomposition

• URL: http://arxiv.org/abs/2511.12903v1
• Date: Mon, 17 Nov 2025 02:49:08 GMT
• Title: Contrastive Entropy Bounds for Density and Conditional Density Decomposition
• Abstract summary: We use Hilbert space and decomposition to address cases where a multiple-output network produces multiple centers defining a Gaussian mixture.<n>We propose an encoder-mixture-decoder architecture whose decoder is multiple-output, producing multiple centers per sample, potentially tightening the bound.
• Score: 6.697324698653934
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper studies the interpretability of neural network features from a Bayesian Gaussian view, where optimizing a cost is reaching a probabilistic bound; learning a model approximates a density that makes the bound tight and the cost optimal, often with a Gaussian mixture density. The two examples are Mixture Density Networks (MDNs) using the bound for the marginal and autoencoders using the conditional bound. It is a known result, not only for autoencoders, that minimizing the error between inputs and outputs maximizes the dependence between inputs and the middle. We use Hilbert space and decomposition to address cases where a multiple-output network produces multiple centers defining a Gaussian mixture. Our first finding is that an autoencoder's objective is equivalent to maximizing the trace of a Gaussian operator, the sum of eigenvalues under bases orthonormal w.r.t. the data and model distributions. This suggests that, when a one-to-one correspondence as needed in autoencoders is unnecessary, we can instead maximize the nuclear norm of this operator, the sum of singular values, to maximize overall rank rather than trace. Thus the trace of a Gaussian operator can be used to train autoencoders, and its nuclear norm can be used as divergence to train MDNs. Our second test uses inner products and norms in a Hilbert space to define bounds and costs. Such bounds often have an extra norm compared to KL-based bounds, which increases sample diversity and prevents the trivial solution where a multiple-output network produces the same constant, at the cost of requiring a sample batch to estimate and optimize. We propose an encoder-mixture-decoder architecture whose decoder is multiple-output, producing multiple centers per sample, potentially tightening the bound. Assuming the data are small-variance Gaussian mixtures, this upper bound can be tracked and analyzed quantitatively.

Related papers

• Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models [0.0]
  Heavy-tailed distributions are prevalent in performance evaluation, network traffic, and risk modeling.<n>We replace the Gaussian decoder with a Phase-Type (PH) distribution based on Markov chains.<n>We show that the PH-based model reduces tail Kolmogorov-Smirnov distance by up to x6 and extreme quantile error by up to x10.
  arXiv  Detail & Related papers  (2026-05-18T14:21:46Z)
• Variational Joint Magnetometry and Gradiometry on Dipolar Spin Chains [14.720429715932829]
  We present a variational framework that takes det(F) as the objective and a hardware-motivated layered dipolar circuit as the ansatz.<n>Both encoding generators are diagonal in the computational basis, which reduces the search for the quantum Fisher information benchmark to a probability-simplex optimization.
  arXiv  Detail & Related papers  (2026-05-05T15:59:22Z)
• Provably Adaptive Linear Approximation for the Shapley Value and Beyond [73.0940890296463]
  A fundamental and long-standing challenge is their efficient approximation.<n>We develop a linear-space algorithm that requires $P(|hatboldsymbol-boldsymbol|_2geq)leq $ for all commonly used semi-values.<n>Our algorithm allows explicit minimization of the mean square error for each specific utility function.
  arXiv  Detail & Related papers  (2026-04-09T16:38:14Z)
• Optimal Transportation and Alignment Between Gaussian Measures [80.4634530260329]
  Optimal transport (OT) and Gromov-Wasserstein (GW) alignment provide interpretable geometric frameworks for datasets.<n>Because these frameworks are computationally expensive, large-scale applications often rely on closed-form solutions for Gaussian distributions under quadratic cost.<n>This work provides a comprehensive treatment of Gaussian, quadratic cost OT and inner product GW (IGW) alignment, closing several gaps in the literature to broaden applicability.
  arXiv  Detail & Related papers  (2025-12-03T09:01:48Z)
• Fundamental limits of distributed covariance matrix estimation via a conditional strong data processing inequality [5.134222224728979]
  We study a scenario in which multiple agents each observe different components of i.i.d. samples drawn from a sub-Gaussian random vector.<n>A central server seeks to estimate the complete covariance matrix using a limited number of bits communicated by each agent.<n>Our main technical tool is a novel generalization of the strong data processing inequality (SDPI), termed the Conditional Strong Data Processing Inequality (C-SDPI) coefficient.
  arXiv  Detail & Related papers  (2025-07-22T18:50:02Z)
• Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks [54.177130905659155]
  Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks. In this paper, we study a suitable function space for over- parameterized two-layer neural networks with bounded norms.
  arXiv  Detail & Related papers  (2024-04-29T15:04:07Z)
• Solving High Frequency and Multi-Scale PDEs with Gaussian Processes [18.190228010565367]
  PINNs often struggle to solve high-frequency and multi-scale PDEs. We resort to the Gaussian process (GP) framework to solve this problem. We use Kronecker product properties and multilinear algebra to promote computational efficiency and scalability.
  arXiv  Detail & Related papers  (2023-11-08T05:26:58Z)
• A Parameter-Free Two-Bit Covariance Estimator with Improved Operator Norm Error Rate [23.116373524718988]
  We propose a new 2-bit covariance matrix estimator that simultaneously addresses both issues. By employing dithering scales varying across entries, our estimator enjoys an improved operator norm error rate. Our proposed method eliminates the need of any tuning parameter, as the dithering scales are entirely determined by the data.
  arXiv  Detail & Related papers  (2023-08-30T14:31:24Z)
• Adversarial Likelihood Estimation With One-Way Flows [44.684952377918904]
  Generative Adversarial Networks (GANs) can produce high-quality samples, but do not provide an estimate of the probability density around the samples. We show that our method converges faster, produces comparable sample quality to GANs with similar architecture, successfully avoids over-fitting to commonly used datasets and produces smooth low-dimensional latent representations of the training data.
  arXiv  Detail & Related papers  (2023-07-19T10:26:29Z)
• Complexity Matters: Rethinking the Latent Space for Generative Modeling [65.64763873078114]
  In generative modeling, numerous successful approaches leverage a low-dimensional latent space, e.g., Stable Diffusion. In this study, we aim to shed light on this under-explored topic by rethinking the latent space from the perspective of model complexity.
  arXiv  Detail & Related papers  (2023-07-17T07:12:29Z)
• Sparse-Inductive Generative Adversarial Hashing for Nearest Neighbor Search [8.020530603813416]
  We propose a novel unsupervised hashing method, termed Sparsity-Induced Generative Adversarial Hashing (SiGAH) SiGAH encodes large-scale high-scale high-dimensional features into binary codes, which solves the two problems through a generative adversarial training framework. Experimental results on four benchmarks, i.e. Tiny100K, GIST1M, Deep1M, and MNIST, have shown that the proposed SiGAH has superior performance over state-of-the-art approaches.
  arXiv  Detail & Related papers  (2023-06-12T08:07:23Z)
• Symmetric Tensor Networks for Generative Modeling and Constrained Combinatorial Optimization [72.41480594026815]
  Constrained optimization problems abound in industry, from portfolio optimization to logistics. One of the major roadblocks in solving these problems is the presence of non-trivial hard constraints which limit the valid search space. In this work, we encode arbitrary integer-valued equality constraints of the form Ax=b, directly into U(1) symmetric networks (TNs) and leverage their applicability as quantum-inspired generative models.
  arXiv  Detail & Related papers  (2022-11-16T18:59:54Z)
• Robust Inference of Manifold Density and Geometry by Doubly Stochastic Scaling [8.271859911016719]
  We develop tools for robust inference under high-dimensional noise. We show that our approach is robust to variability in technical noise levels across cell types.
  arXiv  Detail & Related papers  (2022-09-16T15:39:11Z)
• Fast Batch Nuclear-norm Maximization and Minimization for Robust Domain Adaptation [154.2195491708548]
  We study the prediction discriminability and diversity by studying the structure of the classification output matrix of a randomly selected data batch. We propose Batch Nuclear-norm Maximization and Minimization, which performs nuclear-norm on the target output matrix to enhance the target prediction ability. Experiments show that our method could boost the adaptation accuracy and robustness under three typical domain adaptation scenarios.
  arXiv  Detail & Related papers  (2021-07-13T15:08:32Z)
• Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations [154.51144248210338]
  Batch Nuclear-norm Maximization (BNM) is proposed to boost the learning under label insufficient learning scenarios. BNM outperforms competitors and works well with existing well-known methods.
  arXiv  Detail & Related papers  (2020-03-27T05:04:24Z)

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.