PRISM: Structured Optimization via Anisotropic Spectral Shaping
We propose PRISM, an optimizer that enhances first-order spectral descent methods like Muon with partial second-order information. It constructs an efficient, low-rank quasi-second-order preconditioner via innovation-augmented polar decomposition. This mechanism enables PRISM to perform anisotropic spectral shaping, which adaptively suppresses updates in high-variance subspaces while preserving update strength in signal-dominated directions. Crucially, this is achieved with minimal computational overhead and zero additional memory compared to first-order baselines. PRISM demonstrates a practical strategy for integrating curvature-adaptive properties into the spectral optimization paradigm.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Beyond Loss Guidance: Using PDE Residuals as Spectral Attention in Diffusion Neural Operators
Diffusion-based solvers for partial differential equations (PDEs) are often bottle-necked by slow gradient-based test-time optimization routines that use PDE residuals for loss guidance. They additionally suffer from opt…
PRISM: Position-encoded Regressive Inverse Spectral Model for Multilayer Thin-Film Design
The inverse problem of multilayer thin-film optical coatings design represents a complex combinatorial-continuous optimization challenge. We present PRISM (Position-encoded Regressive Inverse Spectral Model), a unified d…
Spectral Phase Transition and Optimal PCA in Block-Structured Spiked models
We discuss the inhomogeneous spiked Wigner model, a theoretical framework recently introduced to study structured noise in various learning scenarios, through the prism of random matrix theory, with a specific focus on i…
Learning What Matters: Steering Diffusion via Spectrally Anisotropic Forward Noise
Diffusion Probabilistic Models (DPMs) have achieved strong generative performance, yet their inductive biases remain largely implicit. In this work, we aim to build inductive biases into the training and sampling of diff…
ASSR-Net: Anisotropic Structure-Aware and Spectrally Recalibrated Network for Hyperspectral Image Fusion
Hyperspectral image fusion aims to reconstruct high-spatial-resolution hyperspectral images (HR-HSI) by integrating complementary information from multi-source inputs. Despite recent progress, existing methods still face…