DimGrow: Memory-Efficient Field-level Embedding Dimension Search

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Huang, Yihong, Chu, Chen
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

DimINO: Dimension-Informed Neural Operator Learning
di: Song, Yichen, et al.
Pubblicazione: (2024)

Memory Caching: RNNs with Growing Memory
di: Behrouz, Ali, et al.
Pubblicazione: (2026)

Physical Data Embedding for Memory Efficient AI
di: MacPhee, Callen, et al.
Pubblicazione: (2024)

Low-Rank Plus Sparse Matrix Transfer Learning under Growing Representations and Ambient Dimensions
di: Chai, Jinhang, et al.
Pubblicazione: (2026)

Improving Classifier-Free Guidance in Masked Diffusion: Low-Dim Theoretical Insights with High-Dim Impact
di: Rojas, Kevin, et al.
Pubblicazione: (2025)

Agentic Learner with Grow-and-Refine Multimodal Semantic Memory
di: Bo, Weihao, et al.
Pubblicazione: (2025)

Understanding Generalization from Embedding Dimension and Distributional Convergence
di: Yu, Junjie, et al.
Pubblicazione: (2026)

Grow, Assess, Compress: Adaptive Backbone Scaling for Memory-Efficient Class Incremental Learning
di: Garcia-Castañeda, Adrian, et al.
Pubblicazione: (2026)

AdaDim: Dimensionality Adaptation for SSL Representational Dynamics
di: Kokilepersaud, Kiran, et al.
Pubblicazione: (2025)

Growing the Efficient Frontier on Panel Trees
di: Cong, Lin William, et al.
Pubblicazione: (2025)

Balance of Number of Embedding and their Dimensions in Vector Quantization
di: Chen, Hang, et al.
Pubblicazione: (2024)

Search-Adaptor: Embedding Customization for Information Retrieval
di: Yoon, Jinsung, et al.
Pubblicazione: (2023)

GrowTAS: Progressive Expansion from Small to Large Subnets for Efficient ViT Architecture Search
di: Lee, Hyunju, et al.
Pubblicazione: (2025)

Measuring Intrinsic Dimension of Token Embeddings
di: Kataiwa, Takuya, et al.
Pubblicazione: (2025)

On Probabilistic Embeddings in Optimal Dimension Reduction
di: Murray, Ryan, et al.
Pubblicazione: (2024)

Sample Efficient Learning of Factored Embeddings of Tensor Fields
di: Heo, Taemin, et al.
Pubblicazione: (2022)

Physics-Informed Neural Networks with Architectural Physics Embedding for Large-Scale Wave Field Reconstruction
di: Zhang, Huiwen, et al.
Pubblicazione: (2026)

EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora
di: Zhang, Fangyuan, et al.
Pubblicazione: (2025)

Ultra-Quantisation: Efficient Embedding Search via 1.58-bit Encodings
di: Connor, Richard, et al.
Pubblicazione: (2025)

Topology-aware Embedding Memory for Continual Learning on Expanding Networks
di: Zhang, Xikun, et al.
Pubblicazione: (2024)

ShuffleGate: Scalable Feature Optimization for Recommender Systems via Batch-wise Sensitivity Learning
di: Huang, Yihong, et al.
Pubblicazione: (2025)

Optimal Embedding Dimension for Sparse Subspace Embeddings
di: Chenakkod, Shabarish, et al.
Pubblicazione: (2023)

Growing with Experience: Growing Neural Networks in Deep Reinforcement Learning
di: Fehring, Lukas, et al.
Pubblicazione: (2025)

Scaling Laws for Embedding Dimension in Information Retrieval
di: Killingback, Julian, et al.
Pubblicazione: (2026)

Dimension Mixer: Group Mixing of Input Dimensions for Efficient Function Approximation
di: Sapkota, Suman, et al.
Pubblicazione: (2023)

CityFlowER: An Efficient and Realistic Traffic Simulator with Embedded Machine Learning Models
di: Da, Longchao, et al.
Pubblicazione: (2024)

TG-NAS: Generalizable Zero-Cost Proxies with Operator Description Embedding and Graph Learning for Efficient Neural Architecture Search
di: Qiao, Ye, et al.
Pubblicazione: (2024)

Your Code Agent Can Grow Alongside You with Structured Memory
di: Deng, Yi-Xuan, et al.
Pubblicazione: (2026)

On the Spectral Flattening of Quantized Embeddings
di: Huang, Junlin, et al.
Pubblicazione: (2026)

Alada: Alternating Adaptation of Momentum Method for Memory-Efficient Matrix Optimization
di: He, Xiaoyu, et al.
Pubblicazione: (2025)

HAKES: Scalable Vector Database for Embedding Search Service
di: Hu, Guoyu, et al.
Pubblicazione: (2025)

HYPEROFA: Expanding LLM Vocabulary to New Languages via Hypernetwork-Based Embedding Initialization
di: Özeren, Enes, et al.
Pubblicazione: (2025)

Bypassing Skip-Gram Negative Sampling: Dimension Regularization as a More Efficient Alternative for Graph Embeddings
di: Liu, David, et al.
Pubblicazione: (2024)

FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training
di: Huang, Kezhao, et al.
Pubblicazione: (2023)

Memory-Efficient Optimization with Factorized Hamiltonian Descent
di: Nguyen, Son, et al.
Pubblicazione: (2024)

Matryoshka-Adaptor: Unsupervised and Supervised Tuning for Smaller Embedding Dimensions
di: Yoon, Jinsung, et al.
Pubblicazione: (2024)

When To Grow? A Fitting Risk-Aware Policy for Layer Growing in Deep Neural Networks
di: Wu, Haihang, et al.
Pubblicazione: (2024)

Bayesian Optimization that Limits Search Region to Lower Dimensions Utilizing Local GPR
di: Taguchi, Yasunori, et al.
Pubblicazione: (2024)

Growing Efficient Accurate and Robust Neural Networks on the Edge
di: Sundaresha, Vignesh, et al.
Pubblicazione: (2024)

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task
di: Bhalla, Brady, et al.
Pubblicazione: (2025)