Imagen de Portada

Data Uniformity Improves Training Efficiency and More, with a Convergence Framework Beyond the NTK Regime

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Yuqing, Gu, Shangding
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence Optimization and Control
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LoRA Training in the NTK Regime has No Spurious Local Minima
por: Jang, Uijeong, et al.
Publicado: (2024)

Federated Dynamical Low-Rank Training with Global Loss Convergence Guarantees
por: Schotthöfer, Steffen, et al.
Publicado: (2024)

Implicit Bias of Per-sample Adam on Separable Data: Departure from the Full-batch Regime
por: Baek, Beomhan, et al.
Publicado: (2025)

Global Convergence and Rich Feature Learning in $L$-Layer Infinite-Width Neural Networks under $μ$P Parametrization
por: Chen, Zixiang, et al.
Publicado: (2025)

New Hybrid Fine-Tuning Paradigm for LLMs: Algorithm Design and Convergence Analysis Framework
por: Ma, Shaocong, et al.
Publicado: (2026)

Accelerating RLHF Training with Reward Variance Increase
por: Yang, Zonglin, et al.
Publicado: (2025)

Benchmarking PtO and PnO Methods in the Predictive Combinatorial Optimization Regime
por: Geng, Haoyu, et al.
Publicado: (2023)

Enhancing Stochastic Gradient Descent: A Unified Framework and Novel Acceleration Methods for Faster Convergence
por: Deng, Yichuan, et al.
Publicado: (2024)

GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language Models
por: Zhao, Pengxiang, et al.
Publicado: (2025)

Convergence of Some Convex Message Passing Algorithms to a Fixed Point
por: Voracek, Vaclav, et al.
Publicado: (2024)

Training Dynamics of Multi-Head Softmax Attention for In-Context Learning: Emergence, Convergence, and Optimality
por: Chen, Siyu, et al.
Publicado: (2024)

An Approximate Ascent Approach To Prove Convergence of PPO
por: Doering, Leif, et al.
Publicado: (2026)

On the Convergence of (Stochastic) Gradient Descent for Kolmogorov--Arnold Networks
por: Gao, Yihang, et al.
Publicado: (2024)

Gradient Descent Efficiency Index
por: Dhingra, Aviral
Publicado: (2024)

Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries
por: Ganesh, Swetha, et al.
Publicado: (2024)

$γ$-weakly $θ$-up-concavity: A Unified Framework for Non-Convex Optimization Beyond DR-Submodular and OSS Functions
por: Pedramfar, Mohammad, et al.
Publicado: (2026)

Policy Gradient Methods for Risk-Sensitive Distributional Reinforcement Learning with Provable Convergence
por: Xiao, Minheng, et al.
Publicado: (2024)

The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training
por: Wang, Jinbo, et al.
Publicado: (2025)

Global Convergence of Multiplicative Updates for the Matrix Mechanism: A Collaborative Proof with Gemini 3
por: Rush, Keith
Publicado: (2026)

A Methodology Establishing Linear Convergence of Adaptive Gradient Methods under PL Inequality
por: Chakrabarti, Kushal, et al.
Publicado: (2024)

Diagonalisation SGD: Fast & Convergent SGD for Non-Differentiable Models via Reparameterisation and Smoothing
por: Wagner, Dominik, et al.
Publicado: (2024)

A Minimalist Bayesian Framework for Stochastic Optimization
por: Wang, Kaizheng
Publicado: (2025)

Optimal Control for Transformer Architectures: Enhancing Generalization, Robustness and Efficiency
por: Kan, Kelvin, et al.
Publicado: (2025)

On the Convergence of Overparameterized Problems: Inherent Properties of the Compositional Structure of Neural Networks
por: de Oliveira, Arthur Castello Branco, et al.
Publicado: (2025)

Federated Majorize-Minimization: Beyond Parameter Aggregation
por: Dieuleveut, Aymeric, et al.
Publicado: (2025)

Convergence of Stochastic Gradient Langevin Dynamics in the Lazy Training Regime
por: Oberweis, Noah, et al.
Publicado: (2025)

Beyond Expectations: Learning with Stochastic Dominance Made Practical
por: Cen, Shicong, et al.
Publicado: (2024)

Beyond Minimax Rates in Group Distributionally Robust Optimization via a Novel Notion of Sparsity
por: Nguyen, Quan, et al.
Publicado: (2024)

Convergence and sample complexity of natural policy gradient primal-dual methods for constrained MDPs
por: Ding, Dongsheng, et al.
Publicado: (2022)

Training Infinitely Deep and Wide Transformers
por: Barboni, Raphaël, et al.
Publicado: (2026)

The Ky Fan Norms and Beyond: Dual Norms and Combinations for Matrix Optimization
por: Kravatskiy, Alexey, et al.
Publicado: (2025)

Anytime Training with Schedule-Free Spectral Optimization
por: Apte, Anuj, et al.
Publicado: (2026)

Improving the Validity of Decision Trees as Explanations
por: Nemecek, Jiri, et al.
Publicado: (2023)

Understanding Sampler Stochasticity in Training Diffusion Models for RLHF
por: Sheng, Jiayuan, et al.
Publicado: (2025)

Training Safe Neural Networks with Global SDP Bounds
por: Soletskyi, Roman, et al.
Publicado: (2024)

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

Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantization
por: Zhang, Shihao, et al.
Publicado: (2025)

Efficient and provably convergent end-to-end training of deep neural networks with linear constraints
por: Yang, Zonglin, et al.
Publicado: (2026)

Double Momentum Method for Lower-Level Constrained Bilevel Optimization
por: Shi, Wanli, et al.
Publicado: (2024)

The Optimiser Hidden in Plain Sight: Training with the Loss Landscape's Induced Metric
por: Harvey, Thomas R.
Publicado: (2025)