arXiv Machine Learning By V. S. Usatyuk, D. A. Sapozhnikov, S. I. Egorov

Kohn-Sham Spectral Embedding on Sparse Graphs at the Nishimori Temperature for Image Classification

Read the original on arXiv Machine Learning →

arXiv:2607. 28428v1 Announce Type: new Abstract: We introduce Kohn--Sham Spectral Embedding (KSSE), a physics-inspired energy-based model replacing dense CNN classifiers with a sparse-graph spectral embedding evaluated at the Nishimori temperature of an associated Random-Bond Ising Model.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
Jul 14

Eigenbasis-Independent Learnable Spectral Positional Encodings for Directed Graphs via Hermitian Block Krylov Subspaces

arXiv:2607. 07032v2 Announce Type: replace Abstract: Spectral positional encodings (PEs) for \emph{directed} graphs face two obstacles: magnetic Laplacians require an $O(n^3)$ Hermitian eigendecomposition per potential, and their complex eigenvectors are defined only up to unitary gauge, which prior work handles with basis-invariant architectures.

By Jiaqing Xie, Yuxin Wang
arXiv Machine Learning
Jul 9

Gauge-Invariant Learnable Spectral Positional Encodings for Directed Graphs via Hermitian Block Krylov Subspaces

arXiv:2607. 07032v1 Announce Type: new Abstract: Spectral positional encodings (PEs) for \emph{directed} graphs face two obstacles: magnetic Laplacians require an $O(n^3)$ Hermitian eigendecomposition per potential, and their complex eigenvectors are defined only up to unitary gauge, which prior work handles with basis-invariant architectures.

By Jiaqing Xie, Yuxin Wang
arXiv AI
Jul 3

Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability

arXiv:2607. 01799v1 Announce Type: cross Abstract: 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 inferring a sparse code $\mathbf{x}\in\mathbb{R}^n$ from $\mathbf{h}\approx\mathbf{W}\mathbf{x}$.

By Rodrigo Mendoza-Smith