Imagen de Portada

Generalization is not a universal guarantee: Estimating similarity to training data with an ensemble out-of-distribution metric

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Schreyer, W. Max, Anderson, Christopher, Thompson, Reid F.
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

Improving self-training under distribution shifts via anchored confidence with theoretical guarantees
por: Joo, Taejong, et al.
Publicado: (2024)

On the effects of similarity metrics in decentralized deep learning under distributional shift
por: Zec, Edvin Listo, et al.
Publicado: (2024)

Generalization analysis with deep ReLU networks for metric and similarity learning
por: Zhou, Junyu, et al.
Publicado: (2024)

Privacy Preserving Diffusion Models for Mixed-Type Tabular Data Generation
por: Sattarov, Timur, et al.
Publicado: (2025)

FedTabDiff: Federated Learning of Diffusion Probabilistic Models for Synthetic Mixed-Type Tabular Data Generation
por: Sattarov, Timur, et al.
Publicado: (2024)

Latent space analysis and generalization to out-of-distribution data
por: Rainey, Katie, et al.
Publicado: (2025)

A universal policy wrapper with guarantees
por: Bolychev, Anton, et al.
Publicado: (2025)

Latent-space metrics for Complex-Valued VAE out-of-distribution detection under radar clutter
por: Rouzoumka, Y. A., et al.
Publicado: (2025)

Universal generalization guarantees for Wasserstein distributionally robust models
por: Le, Tam, et al.
Publicado: (2024)

Marginal and training-conditional guarantees in one-shot federated conformal prediction
por: Humbert, Pierre, et al.
Publicado: (2024)

Tensor train completion: local recovery guarantees via Riemannian optimization
por: Budzinskiy, Stanislav, et al.
Publicado: (2021)

Layer-wise LoRA fine-tuning: a similarity metric approach
por: Ogawa, Keith Ando, et al.
Publicado: (2026)

Diffusion-Scheduled Denoising Autoencoders for Anomaly Detection in Tabular Data
por: Sattarov, Timur, et al.
Publicado: (2025)

GraphGuard: Contrastive Self-Supervised Learning for Credit-Card Fraud Detection in Multi-Relational Dynamic Graphs
por: Reynisson, Kristófer, et al.
Publicado: (2024)

Aggregating distribution forecasts from deep ensembles
por: Schulz, Benedikt, et al.
Publicado: (2022)

Unlearning in- vs. out-of-distribution data in LLMs under gradient-based method
por: Baluta, Teodora, et al.
Publicado: (2024)

Spectral Normalization and Voigt-Reuss net: A universal approach to microstructure-property forecasting with physical guarantees
por: Keshav, Sanath, et al.
Publicado: (2025)

Analytical results for uncertainty propagation through trained machine learning regression models
por: Thompson, Andrew
Publicado: (2024)

Accuracy on the wrong line: On the pitfalls of noisy data for out-of-distribution generalisation
por: Sanyal, Amartya, et al.
Publicado: (2024)

Federated Diffusion Modeling with Differential Privacy for Tabular Data Synthesis
por: Sattarov, Timur, et al.
Publicado: (2024)

Towards a theory of out-of-distribution learning
por: Dey, Jayanta, et al.
Publicado: (2021)

Neural Coherence : Find higher performance to out-of-distribution tasks from few samples
por: Guiroy, Simon, et al.
Publicado: (2025)

Sharing Knowledge without Sharing Data: Stitches can improve ensembles of disjointly trained models
por: Guijt, Arthur, et al.
Publicado: (2025)

Theoretical guarantees for neural estimators in parametric statistics
por: Rödder, Almut, et al.
Publicado: (2025)

Fairness-enhancing mixed effects deep learning improves fairness on in- and out-of-distribution clustered (non-iid) data
por: Nguyen, Son, et al.
Publicado: (2023)

Causal rule ensemble approach for multi-arm data
por: Wan, Ke, et al.
Publicado: (2025)

A binary PSO based ensemble under-sampling model for rebalancing imbalanced training data
por: Li, Jinyan, et al.
Publicado: (2025)

Revisiting RIP guarantees for sketching operators on mixture models
por: Belhadji, Ayoub, et al.
Publicado: (2023)

Theoretical guarantees in KL for Diffusion Flow Matching
por: Silveri, Marta Gentiloni, et al.
Publicado: (2024)

Incentivising the federation: gradient-based metrics for data selection and valuation in private decentralised training
por: Usynin, Dmitrii, et al.
Publicado: (2023)

A theoretical guarantee for SyncRank
por: Rao, Yang
Publicado: (2025)

Exploring validation metrics for offline model-based optimisation with diffusion models
por: Beckham, Christopher, et al.
Publicado: (2022)

Geometry-aware similarity metrics for neural representations on Riemannian and statistical manifolds
por: Cayco-Gajic, N Alex, et al.
Publicado: (2026)

What is to be gained by ensemble models in analysis of spectroscopic data?
por: Domijan, Katarina
Publicado: (2024)

Kernel-based guarantees for nonlinear parametric models in Bayesian optimization
por: Oliveira, Rafael
Publicado: (2026)

Finite-sample guarantees for data-driven forward-backward operator methods
por: Fabiani, Filippo, et al.
Publicado: (2025)

An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees
por: Tran, Hoang, et al.
Publicado: (2026)

From Generative to Episodic: Sample-Efficient Replicable Reinforcement Learning
por: Hopkins, Max, et al.
Publicado: (2025)

Statistical guarantees for denoising reflected diffusion models
por: Holk, Asbjørn, et al.
Publicado: (2024)

Proximal basin hopping: global optimization with guarantees
por: Lauga, Guillaume, et al.
Publicado: (2026)