cs.LGOct 30, 2026

ProLand: A New Infeasible Manifold Optimization Method for LoRA Fine-Tuning

Authors: Chenyu Zhou, Yuxuan Zeng, Qi Deng, Dongdong Ge, Yinyu Ye

Organizations: Shanghai Jiao Tong University · Shanghai Institute for Mathematics and Interdisciplinary Sciences (SIMIS) · Stanford University

Abstract

Low-rank adaptation (LoRA) enables parameter-efficient fine-tuning but can suffer from redundant basis directions. Constraining the basis factor to the Stiefel manifold addresses this redundancy through orthonormality. Landing methods allow temporarily infeasible iterates to explore a neighborhood of the manifold while progressively restoring orthogonality without per-step retractions. To improve optimization efficiency while retaining this flexibility, we introduce ProLand (Product-space Landing), a retraction-free optimizer that combines coordinated factor updates with Muon-style spectral directions. By designing the updates in the space of the represented weight increment, ProLand separates objective optimization from orthogonality restoration, supporting efficient feasibility recovery. This coordinated construction also enables Muon-style directions to guide objective optimization while preserving that separation. Experiments cover four GLUE validation tasks on DeBERTa-v3-base and seven language benchmarks on Qwen2.5-3B, Llama-3.2-3B, and Moonlight-16B-A3B across multiple adapter ranks. Across these 11 tasks, ProLand achieves the highest average score among the compared methods in every tested encoder and decoder model-rank configuration.

Figures & tables

Appendix figures & tables12 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Retraction-Free Optimization over the Stiefel Manifold for the LoRA Fine-Tuning

    Jul 28, 2026Yuan Zhang, Jiang Hu, Zhijian Lai +2Stiefel Manifold OptimizationRiemannian Optimization

  2. Balanced LoRA: Removing Parameter Invariance to Accelerate Convergence

    May 29, 2026Valérie Castin, Kimia Nadjahi, Pierre Ablin +1LLM Fine-TuningLow-Rank Adaptation

  3. Rotated Manifold Optimization for Low-Rank Adaptation

    Sep 28, 2026Yuhui Ding, Javier Zazo, James HensmanRiemannian OptimizationLow-Rank Adaptation