Cover Image

Dynamic Subspace Composition: Efficient Adaptation via Contractive Basis Expansion

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Khasia, Vladimer
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Hybrid Dual-Path Linear Transformations for Efficient Transformer Architectures
by: Khasia, Vladimer
Published: (2026)

Beyond Attention: True Adaptive World Models via Spherical Kernel Operator
by: Khasia, Vladimer
Published: (2026)

The Vekua Layer: Exact Physical Priors for Implicit Neural Representations via Generalized Analytic Functions
by: Khasia, Vladimer
Published: (2025)

The Adaptive Vekua Cascade: A Differentiable Spectral-Analytic Solver for Physics-Informed Representation
by: Khasia, Vladimer
Published: (2025)

DeepVekua: Geometric-Spectral Representation Learning for Physics-Informed Fields
by: Khasia, Vladimer
Published: (2025)

HAS-VQ: Hessian-Adaptive Sparse Vector Quantization for High-Fidelity LLM Compression
by: Khasia, Vladimer
Published: (2026)

BASIS: Balanced Activation Sketching with Invariant Scalars for "Ghost Backpropagation"
by: Khasia, Vladimer
Published: (2026)

Spectral-Window Hybrid (SWH)
by: Khasia, Vladimer
Published: (2026)

HoloByte: Continuous Hyperspherical Distillation for Tokenizer-Free Modeling
by: Khasia, Vladimer
Published: (2026)

Primal: A Unified Deterministic Framework for Quasi-Orthogonal Hashing and Manifold Learning
by: Khasia, Vladimer
Published: (2025)

Dynamic Online Ensembles of Basis Expansions
by: Waxman, Daniel, et al.
Published: (2024)

Efficient Orthogonal Fine-Tuning with Principal Subspace Adaptation
by: Wu, Fei, et al.
Published: (2025)

ESS-ReduNet: Enhancing Subspace Separability of ReduNet via Dynamic Expansion with Bayesian Inference
by: Yu, Xiaojie, et al.
Published: (2024)

Reparametrizing Shampoo and SOAP for Subspace Basis Updates and BFloat16 Storage
by: Milligan, Alan, et al.
Published: (2026)

Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement
by: Patel, Gaurav, et al.
Published: (2024)

ROSA: Random Subspace Adaptation for Efficient Fine-Tuning
by: Hameed, Marawan Gamal Abdel, et al.
Published: (2024)

VIPAMIN: Visual Prompt Initialization via Embedding Selection and Subspace Expansion
by: Park, Jaekyun, et al.
Published: (2025)

Mixture-of-Subspaces in Low-Rank Adaptation
by: Wu, Taiqiang, et al.
Published: (2024)

Meta-Learned Basis Adaptation for Parametric Linear PDEs
by: Dwivedi, Vikas, et al.
Published: (2026)

Efficient Resource-Constrained Training of Transformers via Subspace Optimization
by: Nguyen, Le-Trung, et al.
Published: (2025)

Native Hierarchical and Compositional Representations with Subspace Embeddings
by: Moreira, Gabriel, et al.
Published: (2025)

Domain Expansion: Parameter-Efficient Modules as Building Blocks for Composite Domains
by: Patel, Mann, et al.
Published: (2025)

Large-Scale Riemannian Meta-Optimization via Subspace Adaptation
by: Yu, Peilin, et al.
Published: (2025)

Test-time Adaptation for Regression by Subspace Alignment
by: Adachi, Kazuki, et al.
Published: (2024)

Subspace Optimization for Backpropagation-Free Continual Test-Time Adaptation
by: Sójka, Damian, et al.
Published: (2026)

EigenLoRAx: Recycling Adapters to Find Principal Subspaces for Resource-Efficient Adaptation and Inference
by: Kaushik, Prakhar, et al.
Published: (2025)

Efficient Test-Time Adaptation through Latent Subspace Coefficients Search
by: Luo, Xinyu, et al.
Published: (2025)

Pretraining Induces a Reusable Spectral Basis for Downstream Task Adaptation
by: Yu, Junjie, et al.
Published: (2026)

DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptation
by: Wang, Yingxu, et al.
Published: (2026)

Contractive Dynamical Imitation Policies for Efficient Out-of-Sample Recovery
by: Abyaneh, Amin, et al.
Published: (2024)

StelLA: Subspace Learning in Low-rank Adaptation using Stiefel Manifold
by: Li, Zhizhong, et al.
Published: (2025)

Safe-Subspace Pseudo-Label Refinement for Source-Free Graph Domain Adaptation
by: Wang, Yingxu, et al.
Published: (2026)

Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation
by: Wang, Dianyun, et al.
Published: (2025)

CERSA: Cumulative Energy-Retaining Subspace Adaptation for Memory-Efficient Fine-Tuning
by: Ge, Jingze, et al.
Published: (2026)

USBD: Universal Structural Basis Distillation for Source-Free Graph Domain Adaptation
by: Wang, Yingxu, et al.
Published: (2026)

Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging
by: Li, Lujun, et al.
Published: (2025)

Frozen in Time: Parameter-Efficient Time Series Transformers via Reservoir-Induced Feature Expansion and Fixed Random Dynamics
by: Singh, Pradeep, et al.
Published: (2025)

SOLAR: Communication-Efficient Model Adaptation via Subspace-Oriented Latent Adapter Reparametrization
by: Mohammadabadi, Seyed Mahmoud Sajjadi, et al.
Published: (2026)

ADEPT: Continual Pretraining via Adaptive Expansion and Dynamic Decoupled Tuning
by: Zhang, Jinyang, et al.
Published: (2025)

Randomized Gradient Subspaces for Efficient Large Language Model Training
by: Rajabi, Sahar, et al.
Published: (2025)