paper-with-me

Papers

Spectral Tensor Train Parameterization of Deep Learning Layers

2021-03-07 · Anton Obukhov, Maxim Rakhuba, Alexander Liniger, Zhiwu Huang, Stamatios Georgoulis, Dengxin Dai, Luc van Gool

We study low-rank parameterizations of weight matrices with embedded spectral properties in the Deep Learning context. The low-rank property leads to parameter efficiency and permits taking computational shortcuts when computing mappings. Spectral properties are often subject to constraints in optimization problems, leading to better models and stability of optimization. We start by looking at the compact SVD parameterization of weight matrices and identifying redundancy sources in the parameterization. We further apply the Tensor Train (TT) decomposition to the compact SVD components, and propose a non-redundant differentiable parameterization of fixed TT-rank tensor manifolds, termed the Spectral Tensor Train Parameterization (STTP). We demonstrate the effects of neural network compression in the image classification setting and both compression and improved training stability in the generative adversarial training setting.

📄 PDF Abstract BibTeX arXiv:2103.04217

Code (1)

toshas/sttp 공식 구현 pytorch

Tasks

Deep Learningimage-classificationImage ClassificationImage GenerationNeural Network Compression

Methods 이 논문이 사용한 방법론

STTP 설명 없음
SVD Parameterization 설명 없음
Spectral Normalization Spectral Normalization is a normalization technique used for generative adversarial networks, used to stabilize training of the discriminator. Spectral normalization has the…

Similar Papers 제목 키워드 기반

Fast and Structured Block-Term Tensor Decomposition For Hyperspectral Unmixing

2022-05-08 · Meng Ding, Xiao Fu, Xi-Le Zhao

The block-term tensor decomposition model with multilinear rank-$(L_r,L_r,1)$ terms (or, the "LL1 tensor decomposition" in short) offers a valuable alternative for hyperspectral unmixing (HU) under the linear mixture mod…

Hyperspectral UnmixingTensor Decomposition

Extending $μ$P: Spectral Conditions for Feature Learning Across Optimizers

2026-02-24 · Akshita Gupta, Marieme Ngom, Sam Foreman, Venkatram Vishwanath arxiv

Several variations of adaptive first-order and second-order optimization methods have been proposed to accelerate and scale the training of large language models. The performance of these optimization routines is highly …

Zero-Shot Learning

FUTON: Fourier Tensor Network for Implicit Neural Representations

2026-02-13 · Pooya Ashtari, Pourya Behmandpoor, Nikos Deligiannis, Aleksandra Pizurica arxiv

Implicit neural representations (INRs) have emerged as powerful tools for encoding signals, yet dominant MLP-based designs often suffer from slow convergence, overfitting to noise, and poor extrapolation. We introduce FU…

Image Denoising

Transformed Low-Rank Parameterization Can Help Robust Generalization for Tensor Neural Networks

2023-03-01 · NeurIPS 2023 11 · Andong Wang, Chao Li, Mingyuan Bai, Zhong Jin 외

Achieving efficient and robust multi-channel data learning is a challenging task in data science. By exploiting low-rankness in the transformed domain, i.e., transformed low-rankness, tensor Singular Value Decomposition …

Generalization Bounds

Tensor-on-Tensor Regression: Riemannian Optimization, Over-parameterization, Statistical-computational Gap, and Their Interplay

2022-06-17 · Yuetian Luo, Anru R. Zhang

We study the tensor-on-tensor regression, where the goal is to connect tensor responses to tensor covariates with a low Tucker rank parameter tensor/matrix without the prior knowledge of its intrinsic rank. We propose th…

regressionRiemannian optimization