Copertina

Model Merging is Secretly Certifiable: Non-Vacuous Generalisation Bounds for Low-Shot Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kim, Taehoon, Gouk, Henry, Kim, Minyoung, Hospedales, Timothy
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

Model Diffusion for Certifiable Few-shot Transfer Learning
di: Rezk, Fady, et al.
Pubblicazione: (2025)

Test-Time Alignment of Text-to-Image Diffusion Models via Null-Text Embedding Optimisation
di: Kim, Taehoon, et al.
Pubblicazione: (2025)

On the Limitations of General Purpose Domain Generalisation Methods
di: Gouk, Henry, et al.
Pubblicazione: (2022)

FedHB: Hierarchical Bayesian Federated Learning
di: Kim, Minyoung, et al.
Pubblicazione: (2023)

A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learning
di: Kim, Minyoung, et al.
Pubblicazione: (2024)

Is Scaling Learned Optimizers Worth It? Evaluating The Value of VeLO's 4000 TPU Months
di: Rezk, Fady, et al.
Pubblicazione: (2023)

Non-Vacuous Generalization Bounds for Large Language Models
di: Lotfi, Sanae, et al.
Pubblicazione: (2023)

Merge and Bound: Direct Manipulations on Weights for Class Incremental Learning
di: Kim, Taehoon, et al.
Pubblicazione: (2025)

Learning Non-Vacuous Generalization Bounds from Optimization
di: Tan, Chengli, et al.
Pubblicazione: (2022)

From Low Intrinsic Dimensionality to Non-Vacuous Generalization Bounds in Deep Multi-Task Learning
di: Zakerinia, Hossein, et al.
Pubblicazione: (2025)

A Bayesian Approach to Data Point Selection
di: Xu, Xinnuo, et al.
Pubblicazione: (2024)

Non-Vacuous Generalization Bounds: Can Rescaling Invariances Help?
di: Rouchouse, Damien, et al.
Pubblicazione: (2025)

The Reward Model Selection Crisis in Personalized Alignment
di: Rezk, Fady, et al.
Pubblicazione: (2025)

Navigating Noise: A Study of How Noise Influences Generalisation and Calibration of Neural Networks
di: Ferianc, Martin, et al.
Pubblicazione: (2023)

FW-Merging: Scaling Model Merging with Frank-Wolfe Optimization
di: Chen, Hao Mark, et al.
Pubblicazione: (2025)

Computing Strategic Responses to Non-Linear Classifiers
di: Geary, Jack, et al.
Pubblicazione: (2025)

Is Limited Participant Diversity Impeding EEG-based Machine Learning?
di: Bomatter, Philipp, et al.
Pubblicazione: (2025)

Strategic Classification with Randomised Classifiers
di: Geary, Jack, et al.
Pubblicazione: (2025)

A Unified Framework for Diffusion Bridge Problems: Flow Matching and Schrödinger Matching into One
di: Kim, Minyoung
Pubblicazione: (2025)

Warm-Start Flow Matching for Guaranteed Fast Text/Image Generation
di: Kim, Minyoung
Pubblicazione: (2026)

Large-scale Score-based Variational Posterior Inference for Bayesian Deep Neural Networks
di: Kim, Minyoung
Pubblicazione: (2026)

Future-Proof Yourself: An AI Era Survival Guide
di: Kim, Taehoon
Pubblicazione: (2025)

VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning
di: Zong, Yongshuo, et al.
Pubblicazione: (2024)

Magnitude Distance: A Geometric Measure of Dataset Similarity
di: Torkamani, Sahel, et al.
Pubblicazione: (2026)

The Signal in the Noise: OOD Detection Through Goodness-of-Fit Testing in Factorised Latent Spaces
di: Bomatter, Philipp, et al.
Pubblicazione: (2026)

On the Transferability of Large-Scale Self-Supervision to Few-Shot Audio Classification
di: Heggan, Calum, et al.
Pubblicazione: (2024)

Non-Vacuous Certification of Transport MCMC via Oscillation-Controlled Normalizing Flows
di: Hu, Jun
Pubblicazione: (2026)

Federated Learning with Nonvacuous Generalisation Bounds
di: Jobic, Pierre, et al.
Pubblicazione: (2023)

Cross-Class Feature Augmentation for Class Incremental Learning
di: Kim, Taehoon, et al.
Pubblicazione: (2023)

Generalisation Bounds of Zero-Shot Economic Forecasting using Time Series Foundation Models
di: Jetwiriyanon, Jittarin, et al.
Pubblicazione: (2025)

Quantum Interval Bound Propagation for Certified Training of Quantum Neural Networks
di: Andrews, Emma, et al.
Pubblicazione: (2026)

Self-Supervised Multimodal Learning: A Survey
di: Zong, Yongshuo, et al.
Pubblicazione: (2023)

Better Later Than Sooner: Neuro-Symbolic Knowledge Graph Construction via Ontology-grounded Post-extraction Correction
di: Loconte, Lorenzo, et al.
Pubblicazione: (2026)

ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning
di: Chavhan, Ruchika, et al.
Pubblicazione: (2024)

Fool Your (Vision and) Language Model With Embarrassingly Simple Permutations
di: Zong, Yongshuo, et al.
Pubblicazione: (2023)

Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models
di: Zong, Yongshuo, et al.
Pubblicazione: (2024)

Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation
di: Yang, Xinyu, et al.
Pubblicazione: (2025)

Your Diffusion Model is Secretly a Certifiably Robust Classifier
di: Chen, Huanran, et al.
Pubblicazione: (2024)

Probabilistic Wildfire Spread Prediction Using an Autoregressive Conditional Generative Adversarial Network
di: Kang, Taehoon, et al.
Pubblicazione: (2025)

Tighter Generalisation Bounds via Interpolation
di: Viallard, Paul, et al.
Pubblicazione: (2024)