paper-with-me

홈 › Papers

Deriving Decoder-Free Sparse Autoencoders from First Principles

2026-01-10 · Alan Oursland arxiv

Gradient descent on log-sum-exp (LSE) objectives performs implicit expectation--maximization (EM): the gradient with respect to each component output equals its responsibility. The same theory predicts collapse without volume control analogous to the log-determinant in Gaussian mixture models. We instantiate the theory in a single-layer encoder with an LSE objective and InfoMax regularization for volume control. Experiments confirm the theory's predictions. The gradient--responsibility identity holds exactly; LSE alone collapses; variance prevents dead components; decorrelation prevents redundancy. The model exhibits EM-like optimization dynamics in which lower loss does not correspond to better features and adaptive optimizers offer no advantage. The resulting decoder-free model learns interpretable mixture components, confirming that implicit EM theory can prescribe architectures.

📄 PDF Abstract BibTeX arXiv:2601.06478

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Decoder Decomposition for the Analysis of the Latent Space of Nonlinear Autoencoders With Wind-Tunnel Experimental Data

2024-04-25 · Yaxin Mo, Tullio Traverso, Luca Magri

Turbulent flows are chaotic and multi-scale dynamical systems, which have large numbers of degrees of freedom. Turbulent flows, however, can be modelled with a smaller number of degrees of freedom when using the appropri…

DecoderDimensionality Reduction

Hallucinating Very Low-Resolution Unaligned and Noisy Face Images by Transformative Discriminative Autoencoders

2017-07-01 · CVPR 2017 7 · Xin Yu, Fatih Porikli

Most of the conventional face hallucination methods assume the input image is sufficiently large and aligned, and all require the input image to be noise-free. Their performance degrades drastically if the input image is…

DecoderFace HallucinationHallucination

Sparse Coding with Multi-Layer Decoders using Variance Regularization

2021-12-16 · Katrina Evtimova, Yann Lecun

Sparse representations of images are useful in many computer vision applications. Sparse coding with an $l_1$ penalty and a learned linear dictionary requires regularization of the dictionary to prevent a collapse in the…

DecoderDenoising

Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability

2026-07-02 · Rodrigo Mendoza-Smith arxiv

Sparse autoencoders (SAEs) decompose internal activations of neural networks into sparse linear combinations of learned features by fitting an overcomplete dictionary $\mathbf{W}\in\mathbb{R}^{m\times n}$ with $m<n$, and…

Rethinking Sparse Autoencoders: Select-and-Project for Fairness and Control from Encoder Features Alone

2025-09-13 · Antonio Bărbălau, Cristian Daniel Păduraru, Teodor Poncu, Alexandru Tifrea 외 arxiv

Sparse Autoencoders (SAEs) are widely employed for mechanistic interpretability and model steering. Within this context, steering is by design performed by means of decoding altered SAE intermediate representations. This…