Copertina

Orthogonal Weight Modification Enhances Learning Scalability and Convergence Efficiency without Gradient Backpropagation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ma, Guoqing, Yu, Shan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Clustering-Based Weight Orthogonalization for Stabilizing Deep Reinforcement Learning
di: Ma, Guoqing, et al.
Pubblicazione: (2025)

Towards Scalable Backpropagation-Free Gradient Estimation
di: Wang, Daniel, et al.
Pubblicazione: (2025)

Is Backpropagation Optimal? When Synthetic Gradients Improve Sample Efficiency
di: Zhang, Yibo Jacky, et al.
Pubblicazione: (2026)

Scalable Learning in Structured Recurrent Spiking Neural Networks without Backpropagation
di: Tang, Bo, et al.
Pubblicazione: (2026)

Learning without Global Backpropagation via Synergistic Information Distillation
di: Ye, Chenhao, et al.
Pubblicazione: (2025)

Stochastic Layer-wise Learning: Scalable and Efficient Alternative to Backpropagation
di: Yin, Bojian, et al.
Pubblicazione: (2025)

Rethinking Deep Learning: Propagating Information in Neural Networks without Backpropagation and Statistical Optimization
di: Itoh, Kei
Pubblicazione: (2024)

HKAN: Hierarchical Kolmogorov-Arnold Network without Backpropagation
di: Dudek, Grzegorz, et al.
Pubblicazione: (2025)

Beyond Backpropagation: Optimization with Multi-Tangent Forward Gradients
di: Flügel, Katharina, et al.
Pubblicazione: (2024)

GRADE: Replacing Policy Gradients with Backpropagation for LLM Alignment
di: Nel, Lukas Abrie
Pubblicazione: (2025)

TurboBoA: Faster and Exact Attention-aware Quantization without Backpropagation
di: Kim, Junhan, et al.
Pubblicazione: (2026)

Semi-Gradient SARSA Routing with Theoretical Guarantee on Traffic Stability and Weight Convergence
di: Wu, Yidan, et al.
Pubblicazione: (2025)

Descent-Guided Policy Gradient for Scalable Cooperative Multi-Agent Learning
di: Yang, Shan, et al.
Pubblicazione: (2026)

Efficient Deep Learning with Decorrelated Backpropagation
di: Dalm, Sander, et al.
Pubblicazione: (2024)

Escaping Spectral Bias without Backpropagation: Fast Implicit Neural Representations with Extreme Learning Machines
di: Cho, Woojin, et al.
Pubblicazione: (2026)

BoA: Attention-aware Post-training Quantization without Backpropagation
di: Kim, Junhan, et al.
Pubblicazione: (2024)

ZNorm: Z-Score Gradient Normalization Accelerating Skip-Connected Network Training without Architectural Modification
di: Yun, Juyoung
Pubblicazione: (2024)

DPZero: Private Fine-Tuning of Language Models without Backpropagation
di: Zhang, Liang, et al.
Pubblicazione: (2023)

Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagation
di: Yu, Chengting, et al.
Pubblicazione: (2024)

GANs as Gradient Flows that Converge
di: Huang, Yu-Jui, et al.
Pubblicazione: (2022)

Backpropagation Neural Tree
di: Ojha, Varun, et al.
Pubblicazione: (2022)

The Cost of Avoiding Backpropagation
di: Panchal, Kunjal, et al.
Pubblicazione: (2025)

Phasor Memory Networks: Stable Backpropagation Through Time for Scalable Explicit Memory
di: Goo, Sungwoo, et al.
Pubblicazione: (2026)

Can Local Learning Match Self-Supervised Backpropagation?
di: Zihan, Wu S., et al.
Pubblicazione: (2026)

Towards Scalable and Versatile Weight Space Learning
di: Schürholt, Konstantin, et al.
Pubblicazione: (2024)

SOMP: Scalable Gradient Inversion for Large Language Models via Subspace-Guided Orthogonal Matching Pursuit
di: Li, Yibo, et al.
Pubblicazione: (2026)

Gradient Deconfliction via Orthogonal Projections onto Subspaces For Multi-task Learning
di: Zhu, Shijie, et al.
Pubblicazione: (2025)

Fisher-Orthogonal Projected Natural Gradient Descent for Continual Learning
di: Garg, Ishir, et al.
Pubblicazione: (2026)

A Theoretical View of Linear Backpropagation and Its Convergence
di: Li, Ziang, et al.
Pubblicazione: (2021)

Enhancing Visual Feature Attribution via Weighted Integrated Gradients
di: Tuan, Kien Tran Duc, et al.
Pubblicazione: (2025)

Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation
di: Sun, Mingfei
Pubblicazione: (2026)

ONG: Orthogonal Natural Gradient Descent
di: Yadav, Yajat, et al.
Pubblicazione: (2025)

Convergence Analysis of Natural Gradient Descent for Over-parameterized Physics-Informed Neural Networks
di: Xu, Xianliang, et al.
Pubblicazione: (2024)

Fairness without Demographics through Learning Graph of Gradients
di: Luo, Yingtao, et al.
Pubblicazione: (2024)

Orthogonal Gradient Boosting for Simpler Additive Rule Ensembles
di: Yang, Fan, et al.
Pubblicazione: (2024)

Generalized Euler Logarithm and its Applications in Machine Learning: Natural Gradient, Backpropagation, Generalized EG, Mirror Descent and OLPS
di: Cichocki, Andrzej
Pubblicazione: (2025)

On the Convergence of Multicalibration Gradient Boosting
di: Haimovich, Daniel, et al.
Pubblicazione: (2026)

Muon-OGD: Muon-based Spectral Orthogonal Gradient Projection for LLM Continual Learning
di: Lu, Binghang, et al.
Pubblicazione: (2026)

Task Weighting through Gradient Projection for Multitask Learning
di: Bohn, Christian, et al.
Pubblicazione: (2024)

Learning Provably Improves the Convergence of Gradient Descent
di: Song, Qingyu, et al.
Pubblicazione: (2025)