paper-with-me

홈 › Papers

Matricial Free Energy as a Gaussianizing Regularizer: Enhancing Autoencoders for Gaussian Code Generation

2025-10-20 · Rishi Sonthalia, Raj Rao Nadakuditi arxiv

We introduce a novel regularization scheme for autoencoders based on matricial free energy. Our approach defines a differentiable loss function in terms of the singular values of the code matrix (code dimension x batch size). From the standpoint of free probability an d random matrix theory, this loss achieves its minimum when the singular value distribution of the code matrix coincides with that of an appropriately sculpted random metric with i.i.d. Gaussian entries. Empirical simulations demonstrate that minimizing the negative matricial free energy through standard stochastic gradient-based training yields Gaussian-like codes that generalize across training and test sets. Building on this foundation, we propose a matricidal free energy maximizing autoencoder that reliably produces Gaussian codes and show its application to underdetermined inverse problems.

📄 PDF Abstract BibTeX arXiv:2510.17120

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Similar Papers 제목 키워드 기반

Active Inference in Discrete State Spaces from First Principles

2025-11-25 · Patrick Kenny arxiv

We seek to clarify the concept of active inference by disentangling it from the Free Energy Principle. We show how the optimizations that need to be carried out in order to implement active inference in discrete state sp…

Free Component Analysis: Theory, Algorithms & Applications

2019-05-05 · Hao Wu, Raj Rao Nadakuditi

We describe a method for unmixing mixtures of freely independent random variables in a manner analogous to the independent component analysis (ICA) based method for unmixing independent random variables from their additi…

Understanding Adversarial Training with Energy-based Models

2025-05-28 · Mujtaba Hussain Mirza, Maria Rosaria Briglia, Filippo Bartolucci, Senad Beadini 외

We aim at using Energy-based Model (EBM) framework to better understand adversarial training (AT) in classifiers, and additionally to analyze the intrinsic generative capabilities of robust classifiers. By viewing standa…

An Adversarial Interpretation of Information-Theoretic Bounded Rationality

2014-04-22 · Pedro A. Ortega, Daniel D. Lee

Recently, there has been a growing interest in modeling planning with information constraints. Accordingly, an agent maximizes a regularized expected utility known as the free energy, where the regularizer is given by th…

Decision Making

Enhancing Data-Free Adversarial Distillation with Activation Regularization and Virtual Interpolation

2021-02-23 · Xiaoyang Qu, Jianzong Wang, Jing Xiao

Knowledge distillation refers to a technique of transferring the knowledge from a large learned model or an ensemble of learned models to a small model. This method relies on access to the original training set, which mi…

Knowledge Distillation