paper-with-me

홈 › Papers

Fourier Basis Density Model

2024-02-23 · Alfredo De la Fuente, Saurabh Singh, Johannes Ballé

We introduce a lightweight, flexible and end-to-end trainable probability density model parameterized by a constrained Fourier basis. We assess its performance at approximating a range of multi-modal 1D densities, which are generally difficult to fit. In comparison to the deep factorized model introduced in [1], our model achieves a lower cross entropy at a similar computational budget. In addition, we also evaluate our method on a toy compression task, demonstrating its utility in learned compression.

📄 PDF Abstract BibTeX arXiv:2402.15345

Code (0)

등록된 구현이 없습니다.

Tasks

model

Similar Papers 제목 키워드 기반

Efficient Fourier single-pixel imaging with Gaussian random sampling

2021-06-29 · Ziheng Qiu, Xinyi Guo, Tianao Lu, Pan Qi 외

Fourier single-pixel imaging (FSI) is a branch of single-pixel imaging techniques. It uses Fourier basis patterns as structured patterns for spatial information acquisition in the Fourier domain. However, the spatial res…

Compressive Sensing

Stable and robust sampling strategies for compressive imaging

2012-10-08 · Felix Krahmer, Rachel Ward

In many signal processing applications, one wishes to acquire images that are sparse in transform domains such as spatial finite differences or wavelets using frequency domain samples. For such applications, overwhelming…

Compressive SensingImage Reconstruction

Unified Fourier bases for signals on random graphs with group symmetries

2024-06-10 · Mahya Ghandehari, Jeannette Janssen, Silo Murphy

We consider a recently proposed approach to graph signal processing (GSP) based on graphons. We show how the graphon-based approach to GSP applies to graphs sampled from a stochastic block model derived from a weighted C…

Stochastic Block Model

The Discrete-Log Clock: How a Transformer Learns Modular Multiplication

2026-06-16 · Huu Danh Nguyen arxiv

When small transformers grok modular multiplication, prior work reports that the learned embedding has a "dense" Fourier spectrum requiring all frequencies. This contrasts with modular addition, where only a sparse set o…

Fourier Transformers for Latent Crystallographic Diffusion and Generative Modeling

2026-02-12 · Jed A. Duersch, Elohan Veillon, Astrid Klipfel, Adlane Sayede 외 arxiv

The discovery of new crystalline materials calls for generative models that handle periodic boundary conditions, crystallographic symmetries, and physical constraints, while scaling to large and structurally diverse unit…