Cover Image

Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shi, Yubin, Chen, Yixuan, Dong, Mingzhi, Yang, Xiaochen, Li, Dongsheng, Wang, Yujiang, Dick, Robert P., Lv, Qin, Zhao, Yingying, Yang, Fan, Lu, Tun, Gu, Ning, Shang, Li
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Denoising Reuse: Exploiting Inter-frame Motion Consistency for Efficient Video Latent Generation
by: Wang, Chenyu, et al.
Published: (2024)

Metis: Training LLMs with FP4 Quantization
by: Cao, Hengjie, et al.
Published: (2025)

The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training
by: Cao, Hengjie, et al.
Published: (2026)

Faster Convergence of Local SGD for Over-Parameterized Models
by: Qin, Tiancheng, et al.
Published: (2022)

Unbiased Collaborative Filtering with Fair Sampling
by: Liu, Jiahao, et al.
Published: (2025)

Frequency-aware Graph Signal Processing for Collaborative Filtering
by: Xia, Jiafeng, et al.
Published: (2024)

A Comprehensive Summarization and Evaluation of Feature Refinement Modules for CTR Prediction
by: Wang, Fangye, et al.
Published: (2023)

Oracle-guided Dynamic User Preference Modeling for Sequential Recommendation
by: Xia, Jiafeng, et al.
Published: (2024)

FABSVer: Faster Training and Better Self-Verification for LLM Mathematical Reasoning
by: Pan, Haihui, et al.
Published: (2026)

GraphTransfer: A Generic Feature Fusion Framework for Collaborative Filtering
by: Xia, Jiafeng, et al.
Published: (2024)

Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better
by: Zhao, Ji, et al.
Published: (2026)

Sharp Generalization for Nonparametric Regression in Interpolation Space by Over-Parameterized Neural Networks Trained with Preconditioned Gradient Descent and Early Stopping
by: Yang, Yingzhen, et al.
Published: (2024)

Spectra: Rethinking Optimizers for LLMs Under Spectral Anisotropy
by: Huang, Zhendong, et al.
Published: (2026)

Improving Controllable Generation: Faster Training and Better Performance via $x_0$-Supervision
by: Sangare, Amadou S., et al.
Published: (2026)

Knoop: Practical Enhancement of Knockoff with Over-Parameterization for Variable Selection
by: Zhang, Xiaochen, et al.
Published: (2025)

Faster and Better 3D Splatting via Group Training
by: Wang, Chengbo, et al.
Published: (2024)

AOTree: Aspect Order Tree-based Model for Explainable Recommendation
by: Zhao, Wenxin, et al.
Published: (2024)

Multi-Head Attention as a Source of Catastrophic Forgetting in MoE Transformers
by: Chen, Anrui, et al.
Published: (2026)

Improving Adaptivity via Over-Parameterization in Sequence Models
by: Li, Yicheng, et al.
Published: (2024)

Improving LLM-powered Recommendations with Personalized Information
by: Liu, Jiahao, et al.
Published: (2025)

SD-MoE: Spectral Decomposition for Effective Expert Specialization
by: Huang, Ruijun, et al.
Published: (2026)

LLM-Based User Simulation for Low-Knowledge Shilling Attacks on Recommender Systems
by: Gu, Shengkang, et al.
Published: (2025)

AgentCF++: Memory-enhanced LLM-based Agents for Popularity-aware Cross-domain Recommendations
by: Liu, Jiahao, et al.
Published: (2025)

Better Models, Faster Training: Sigmoid Attention for single-cell Foundation Models
by: Sadashivaiah, Vijay, et al.
Published: (2026)

Feature-Indexed Federated Recommendation with Residual-Quantized Codebooks
by: Han, Mingzhe, et al.
Published: (2026)

Bidirectional Knowledge Distillation for Enhancing Sequential Recommendation with Large Language Models
by: Wu, Jiongran, et al.
Published: (2025)

Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance
by: Lin, Liting, et al.
Published: (2024)

FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality
by: Lv, Zhengyao, et al.
Published: (2024)

Dispelling the Curse of Singularities in Neural Network Optimizations
by: Cao, Hengjie, et al.
Published: (2026)

Gradient Descent Finds Over-Parameterized Neural Networks with Sharp Generalization for Nonparametric Regression
by: Yang, Yingzhen, et al.
Published: (2024)

Pointer Networks Trained Better via Evolutionary Algorithms
by: Zhong, Muyao, et al.
Published: (2023)

Faster Parameterized Vertex Multicut
by: Chu, Huairui, et al.
Published: (2026)

Better World Models Can Lead to Better Post-Training Performance
by: Gupta, Prakhar, et al.
Published: (2025)

Probing CLIP's Comprehension of 360-Degree Textual and Visual Semantics
by: Wang, Hai, et al.
Published: (2026)

Drift-Aware Continual Tokenization for Generative Recommendation
by: Feng, Yuebo, et al.
Published: (2026)

FedCIA: Federated Collaborative Information Aggregation for Privacy-Preserving Recommendation
by: Han, Mingzhe, et al.
Published: (2025)

Transparent and Controllable Recommendation Filtering via Multimodal Multi-Agent Collaboration
by: Zhang, Chi, et al.
Published: (2026)

Provable Acceleration of Nesterov's Accelerated Gradient Method over Heavy Ball Method in Training Over-Parameterized Neural Networks
by: Liu, Xin, et al.
Published: (2022)

Training-Driven Representational Geometry Modularization Predicts Brain Alignment in Language Models
by: Liu, Yixuan, et al.
Published: (2026)

Training Language Model to Critique for Better Refinement
by: Yu, Tianshu, et al.
Published: (2025)