Cover Image

EMA Without the Lag: Bias-Corrected Iterate Averaging Schemes

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Block, Adam, Zhang, Cyril
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL
by: Zhang, Lunjun, et al.
Published: (2026)

Revisiting the (Sub)Optimality of Best-of-N for Inference-Time Alignment
by: Sriraman, Ved, et al.
Published: (2026)

Pushing the Limits of Low-Bit Optimizers: A Focus on EMA Dynamics
by: Xu, Cong, et al.
Published: (2025)

Efficient Bias Mitigation Without Privileged Information
by: Zarlenga, Mateo Espinosa, et al.
Published: (2024)

Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning
by: Choi, Moonseok, et al.
Published: (2023)

Implicit Bias of the JKO Scheme
by: Halmos, Peter, et al.
Published: (2025)

Self-Improvement in Language Models: The Sharpening Mechanism
by: Huang, Audrey, et al.
Published: (2024)

Graph Negative Feedback Bias Correction Framework for Adaptive Heterophily Modeling
by: Lv, Jiaqi, et al.
Published: (2026)

Maximum Entropy Exploration Without the Rollouts
by: Adamczyk, Jacob, et al.
Published: (2026)

CoRPO: Adding a Correctness Bias to GRPO Improves Generalization
by: Garg, Anisha, et al.
Published: (2025)

Transparency and Proportionality in Post-Processing Algorithmic Bias Correction
by: Ferreira, Juliett Suárez, et al.
Published: (2025)

FedEMA-Distill: Exponential Moving Average Guided Knowledge Distillation for Robust Federated Learning
by: Reguieg, Hamza, et al.
Published: (2026)

MarkTune: Improving the Quality-Detectability Trade-off in Open-Weight LLM Watermarking
by: Zhao, Yizhou, et al.
Published: (2025)

Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
by: Foster, Dylan J., et al.
Published: (2024)

Improving Diffusion Posterior Samplers with Lagged Temporal Corrections for Image Restoration
by: Evangelista, Davide, et al.
Published: (2026)

Rethinking Refinement: Correcting Generative Bias without Noise Injection
by: Peng, Xin, et al.
Published: (2026)

Correcting Performance Estimation Bias in Imbalanced Classification with Minority Subconcepts
by: Maxson, Taylor, et al.
Published: (2026)

Bias Amplification in Language Model Evolution: An Iterated Learning Perspective
by: Ren, Yi, et al.
Published: (2024)

Don't Lag, RAG: Training-Free Adversarial Detection Using RAG
by: Kazoom, Roie, et al.
Published: (2025)

Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
by: Rasul, Kashif, et al.
Published: (2023)

Enhancing AI-Based Tropical Cyclone Track and Intensity Forecasting via Systematic Bias Correction
by: Niu, Peisong, et al.
Published: (2026)

Iterative Refinement Neural Operators are Learned Fixed-Point Solvers: A Principled Approach to Spectral Bias Mitigation
by: Liu, Xiaotian, et al.
Published: (2026)

Gradient Iterated Temporal-Difference Learning
by: Vincent, Théo, et al.
Published: (2026)

GaussMark: A Practical Approach for Structural Watermarking of Language Models
by: Block, Adam, et al.
Published: (2025)

Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment
by: Huang, Audrey, et al.
Published: (2025)

EvoFormer: Learning Dynamic Graph-Level Representations with Structural and Temporal Bias Correction
by: Zhong, Haodi, et al.
Published: (2025)

VCformer: Variable Correlation Transformer with Inherent Lagged Correlation for Multivariate Time Series Forecasting
by: Yang, Yingnan, et al.
Published: (2024)

Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL
by: Zheng, Kunhao, et al.
Published: (2026)

AI-Powered Inverse Design of Ku-Band SIW Resonant Structures by Iterative Residual Correction Network
by: Mashayekhi, Mohammad, et al.
Published: (2025)

Fix Initial Codes and Iteratively Refine Textual Directions Toward Safe Multi-Turn Code Correction
by: Tanaka, Yuto, et al.
Published: (2026)

Machine Unlearning under Overparameterization
by: Block, Jacob L., et al.
Published: (2025)

MillGNN: Learning Multi-Scale Lead-Lag Dependencies for Multi-Variate Time Series Forecasting
by: Wu, Binqing, et al.
Published: (2025)

LagKV: Lag-Relative Information of the KV Cache Tells Which Tokens Are Important
by: Liang, Manlai, et al.
Published: (2025)

Understanding and Improving Model Averaging in Federated Learning on Heterogeneous Data
by: Zhou, Tailin, et al.
Published: (2023)

Comprehension Without Competence: Architectural Limits of LLMs in Symbolic Computation and Reasoning
by: Zhang, Zheng
Published: (2025)

Beyond the Meta: Leveraging Game Design Parameters for Patch-Agnostic Esport Analytics
by: Chitayat, Alan Pedrassoli, et al.
Published: (2023)

Average-Reward Soft Actor-Critic
by: Adamczyk, Jacob, et al.
Published: (2025)

KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models
by: Xu, Zukang, et al.
Published: (2026)

HURRI-GAN: A Novel Approach for Hurricane Bias-Correction Beyond Gauge Stations using Generative Adversarial Networks
by: Nadera, Noujoud, et al.
Published: (2026)

Revisiting Weight Averaging for Model Merging
by: Choi, Jiho, et al.
Published: (2024)