Copertina

When to retrain a machine learning model

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Florence, Regol, Leo, Schwinn, Kyle, Sprague, Mark, Coates, Thomas, Markovich
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

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

Cost-sensitive retraining via posterior learning debt
di: Katz, Harrison
Pubblicazione: (2026)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Adversarial Robustness of Graph Transformers
di: Foth, Philipp, et al.
Pubblicazione: (2024)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Understanding with toy surrogate models in machine learning
di: Páez, Andrés
Pubblicazione: (2024)

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

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

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

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