Image de couverture de livre

Understanding the Mechanisms of Fast Hyperparameter Transfer

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ghosh, Nikhil, Wu, Denny, Bietti, Alberto
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

GSM-Agent: Understanding Agentic Reasoning Using Controllable Environments
par: Zhu, Hanlin, et autres
Publié: (2025)

Learning Associative Memories with Gradient Descent
par: Cabannes, Vivien, et autres
Publié: (2024)

BAnG: Bidirectional Anchored Generation for Conditional RNA Design
par: Klypa, Roman, et autres
Publié: (2025)

Multimodal Alignment and Preference Optimization for Zero-Shot Conditional RNA Generation
par: Klypa, Roman, et autres
Publié: (2026)

Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention Layers
par: Chen, Lei, et autres
Publié: (2024)

Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration
par: Mlodozeniec, Bruno, et autres
Publié: (2025)

ORTHOBO: Orthogonal Bayesian Hyperparameter Optimization
par: Schröder, Maresa, et autres
Publié: (2026)

Hyperparameters in Score-Based Membership Inference Attacks
par: Pradhan, Gauri, et autres
Publié: (2025)

Hyperparameter Optimization via Interacting with Probabilistic Circuits
par: Seng, Jonas, et autres
Publié: (2025)

Sequential Policy Gradient for Adaptive Hyperparameter Optimization
par: Li, Zheng, et autres
Publié: (2025)

Combining Automated Optimisation of Hyperparameters and Reward Shape
par: Dierkes, Julian, et autres
Publié: (2024)

Using Large Language Models for Hyperparameter Optimization
par: Zhang, Michael R., et autres
Publié: (2023)

Calibrated Dataset Condensation for Faster Hyperparameter Search
par: Ding, Mucong, et autres
Publié: (2024)

Quantifying Hyperparameter Transfer and the Importance of Embedding Layer Learning Rate
par: Kalra, Dayal Singh, et autres
Publié: (2026)

A Unified Hyperparameter Optimization Pipeline for Transformer-Based Time Series Forecasting Models
par: Xu, Jingjing, et autres
Publié: (2025)

Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation
par: Kim, Juno, et autres
Publié: (2025)

A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning
par: Adkins, Jacob, et autres
Publié: (2024)

Hyperparameter Importance Analysis for Multi-Objective AutoML
par: Theodorakopoulos, Daphne, et autres
Publié: (2024)

Hyperparameter Trajectory Inference with Conditional Lagrangian Optimal Transport
par: Amad, Harry, et autres
Publié: (2026)

Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP
par: Chen, Zixiang, et autres
Publié: (2023)

HyperSHAP: Shapley Values and Interactions for Explaining Hyperparameter Optimization
par: Wever, Marcel, et autres
Publié: (2025)

Frozen Layers: Memory-efficient Many-fidelity Hyperparameter Optimization
par: Carstensen, Timur, et autres
Publié: (2025)

A Unified Gaussian Process for Branching and Nested Hyperparameter Optimization
par: Zhang, Jiazhao, et autres
Publié: (2024)

Beware of the Batch Size: Hyperparameter Bias in Evaluating LoRA
par: Lee, Sangyoon, et autres
Publié: (2026)

Physics Steering: Causal Control of Cross-Domain Concepts in a Physics Foundation Model
par: Fear, Rio Alexa, et autres
Publié: (2025)

Relative Policy-Transition Optimization for Fast Policy Transfer
par: Xu, Jiawei, et autres
Publié: (2022)

A Method for Fast Autonomy Transfer in Reinforcement Learning
par: Sahabandu, Dinuka, et autres
Publié: (2024)

The Impact of Initialization on LoRA Finetuning Dynamics
par: Hayou, Soufiane, et autres
Publié: (2024)

LoRA+: Efficient Low Rank Adaptation of Large Models
par: Hayou, Soufiane, et autres
Publié: (2024)

Understanding Model Ensemble in Transferable Adversarial Attack
par: Yao, Wei, et autres
Publié: (2024)

Hyperparameter Optimisation with Practical Interpretability and Explanation Methods in Probabilistic Curriculum Learning
par: Salt, Llewyn, et autres
Publié: (2025)

Conditional PED-ANOVA: Hyperparameter Importance in Hierarchical & Dynamic Search Spaces
par: Baba, Kaito, et autres
Publié: (2026)

Interactive Hyperparameter Optimization in Multi-Objective Problems via Preference Learning
par: Giovanelli, Joseph, et autres
Publié: (2023)

ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning
par: Yuan, Mingqi, et autres
Publié: (2025)

Exploring the impact of Optimised Hyperparameters on Bi-LSTM-based Contextual Anomaly Detector
par: Toor, Aafan Ahmad, et autres
Publié: (2025)

Assessing Simplification Levels in Neural Networks: The Impact of Hyperparameter Configurations on Complexity and Sensitivity
par: Guan, Huixin
Publié: (2024)

Integrating Hyperparameter Search into Model-Free AutoML with Context-Free Grammars
par: Vázquez, Hernán Ceferino, et autres
Publié: (2024)

Default Machine Learning Hyperparameters Do Not Provide Informative Initialization for Bayesian Optimization
par: Prieto, Nicolás Villagrán, et autres
Publié: (2026)

Self-Tuning Sparse Attention: Multi-Fidelity Hyperparameter Optimization for Transformer Acceleration
par: Dev, Arundhathi, et autres
Publié: (2026)

Learning to Recall with Transformers Beyond Orthogonal Embeddings
par: Vural, Nuri Mert, et autres
Publié: (2026)