Imagen de Portada

When to retrain a machine learning model

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Florence, Regol, Leo, Schwinn, Kyle, Sprague, Mark, Coates, Thomas, Markovich
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Jointly-Learned Exit and Inference for a Dynamic Neural Network : JEI-DNN
por: Regol, Florence, et al.
Publicado: (2023)

Interacting Diffusion Processes for Event Sequence Forecasting
por: Zeng, Mai, et al.
Publicado: (2023)

Predicting Probabilities of Error to Combine Quantization and Early Exiting: QuEE
por: Regol, Florence, et al.
Publicado: (2024)

Dynamic layer selection in decoder-only transformers
por: Glavas, Theodore, et al.
Publicado: (2024)

Cost-sensitive retraining via posterior learning debt
por: Katz, Harrison
Publicado: (2026)

Large-Scale Dataset Pruning in Adversarial Training through Data Importance Extrapolation
por: Nieth, Björn, et al.
Publicado: (2024)

A Probabilistic Perspective on Unlearning and Alignment for Large Language Models
por: Scholten, Yan, et al.
Publicado: (2024)

On the retraining frequency of global models in retail demand forecasting
por: Zanotti, Marco
Publicado: (2025)

Uncertainty Estimation on Graphs with Structure Informed Stochastic Partial Differential Equations
por: Xu, Fred, et al.
Publicado: (2025)

Byte Pair Encoding for Efficient Time Series Forecasting
por: Götz, Leon, et al.
Publicado: (2025)

Sampling-aware Adversarial Attacks Against Large Language Models
por: Beyer, Tim, et al.
Publicado: (2025)

Efficient Time Series Processing for Transformers and State-Space Models through Token Merging
por: Götz, Leon, et al.
Publicado: (2024)

Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs
por: Scholten, Yan, et al.
Publicado: (2025)

Understanding the Design Principles of Link Prediction in Directed Settings
por: Zhai, Jun, et al.
Publicado: (2025)

Joint Relational Database Generation via Graph-Conditional Diffusion Models
por: Ketata, Mohamed Amine, et al.
Publicado: (2025)

Variation Matters: from Mitigating to Embracing Zero-Shot NAS Ranking Function Variation
por: Rumiantsev, Pavel, et al.
Publicado: (2025)

Half Search Space is All You Need
por: Rumiantsev, Pavel, et al.
Publicado: (2025)

Diffusion LLMs are Natural Adversaries for any LLM
por: Lüdke, David, et al.
Publicado: (2025)

Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space
por: Schwinn, Leo, et al.
Publicado: (2024)

Adversarial Robustness of Graph Transformers
por: Foth, Philipp, et al.
Publicado: (2024)

Score-based change point detection via tracking the best of infinitely many experts
por: Markovich, Anna, et al.
Publicado: (2024)

Joint Out-of-Distribution Filtering and Data Discovery Active Learning
por: Schmidt, Sebastian, et al.
Publicado: (2025)

Extracting Unlearned Information from LLMs with Activation Steering
por: Seyitoğlu, Atakan, et al.
Publicado: (2024)

ddml: Double/debiased machine learning in Stata
por: Ahrens, Achim, et al.
Publicado: (2023)

Graph Knowledge Distillation to Mixture of Experts
por: Rumiantsev, Pavel, et al.
Publicado: (2024)

Accelerating the prediction of inorganic surfaces with machine learning interatomic potentials
por: Noordhoek, Kyle, et al.
Publicado: (2023)

Des-q: a quantum algorithm to provably speedup retraining of decision trees
por: Kumar, Niraj, et al.
Publicado: (2023)

Efficient Adversarial Training in LLMs with Continuous Attacks
por: Xhonneux, Sophie, et al.
Publicado: (2024)

Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting
por: Kollovieh, Marcel, et al.
Publicado: (2024)

Effective Data Pruning through Score Extrapolation
por: Schmidt, Sebastian, et al.
Publicado: (2025)

Guiding the retraining of convolutional neural networks against adversarial inputs
por: López, Francisco Durán, et al.
Publicado: (2022)

Emergent specialization from participation dynamics and multi-learner retraining
por: Dean, Sarah, et al.
Publicado: (2022)

Automatic mixed precision for optimizing gained time with constrained loss mean-squared-error based on model partition to sequential sub-graphs
por: Markovich-Golan, Shmulik, et al.
Publicado: (2025)

Spherical Boltzmann machines: a solvable theory of learning and generation in energy-based models
por: Tulinski, Thomas, et al.
Publicado: (2026)

Scaling Laws for Discriminative Classification in Large Language Models
por: Wyatte, Dean, et al.
Publicado: (2024)

Understanding with toy surrogate models in machine learning
por: Páez, Andrés
Publicado: (2024)

Adversarial Alignment for LLMs Requires Simpler, Reproducible, and More Measurable Objectives
por: Schwinn, Leo, et al.
Publicado: (2025)

Neural Implicit Swept Volume Models for Fast Collision Detection
por: Joho, Dominik, et al.
Publicado: (2024)

Implicit score matching meets denoising score matching: improved rates of convergence and log-density Hessian estimation
por: Yakovlev, Konstantin, et al.
Publicado: (2025)

Same accuracy, twice as fast: continuous training surpasses retraining from scratch
por: Verwimp, Eli, et al.
Publicado: (2025)