Image de couverture de livre

Model Merging by Output-Space Projection

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Evans, Bethan, Etheridge, Benjamin, Roberts, Stephen, Tanner, Jared
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Information Theory
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Theory of Minimal Weight Perturbations in Deep Networks and its Applications for Low-Rank Activated Backdoor Attacks
par: Evans, Bethan, et autres
Publié: (2026)

How Controlling the Variance can Improve Training Stability of Sparsely Activated DNNs and CNNs
par: Dent, Emily, et autres
Publié: (2026)

Output-Constrained Lossy Source Coding With Application to Rate-Distortion-Perception Theory
par: Xie, Li, et autres
Publié: (2024)

Entropy-informed Decoding: Adaptive Information-Driven Branching
par: Evans, Benjamin Patrick, et autres
Publié: (2026)

Graph Community Augmentation with GMM-based Modeling in Latent Space
par: Fukushima, Shintaro, et autres
Publié: (2024)

Projection Head is Secretly an Information Bottleneck
par: Ouyang, Zhuo, et autres
Publié: (2025)

Rethinking Selectivity in State Space Models: A Minimal Predictive Sufficiency Approach
par: Wang, Yiyi, et autres
Publié: (2025)

Contrastive ECOC: Learning Output Codes for Adversarial Defense
par: Chou, Che-Yu, et autres
Publié: (2025)

Generalizing Supervised Contrastive learning: A Projection Perspective
par: Jeong, Minoh, et autres
Publié: (2025)

Spectral Scaling Laws in Language Models: How Effectively Do Feed-Forward Networks Use Their Latent Space?
par: Jha, Nandan Kumar, et autres
Publié: (2025)

Tighter CMI-Based Generalization Bounds via Stochastic Projection and Quantization
par: Sefidgaran, Milad, et autres
Publié: (2025)

Cyclic Group Projection for Enumerating Quasi-Cyclic Codes Trapping Sets
par: Usatyuk, Vasiliy, et autres
Publié: (2024)

StateSMix: Online Lossless Compression via Mamba State Space Models and Sparse N-gram Context Mixing
par: Tacconelli, Roberto
Publié: (2026)

Accelerating Relative Entropy Coding with Space Partitioning
par: He, Jiajun, et autres
Publié: (2024)

Learning Successive Interference Cancellation for Low-Complexity Soft-Output MIMO Detection
par: Fesl, Benedikt, et autres
Publié: (2026)

Rate-Distortion-Perception Theory for the Quadratic Wasserstein Space
par: Qu, Xiqiang, et autres
Publié: (2025)

Pruning Cannot Hurt Robustness: Certified Trade-offs in Reinforcement Learning
par: Pedley, James, et autres
Publié: (2025)

Self-supervised Latent Space Optimization with Nebula Variational Coding
par: Wang, Yida, et autres
Publié: (2025)

A Generalized Information Bottleneck Theory of Deep Learning
par: Westphal, Charles, et autres
Publié: (2025)

Irregular Sampling of High-Dimensional Functions in Reproducing Kernel Hilbert Spaces
par: Iske, Armin, et autres
Publié: (2025)

Sub-linear Regret Bounds for Bayesian Optimisation in Unknown Search Spaces
par: Tran-The, Hung, et autres
Publié: (2020)

Efficient Unbiased Sparsification
par: Barnes, Leighton, et autres
Publié: (2024)

Cost Minimization for Space-Air-Ground Integrated Multi-Access Edge Computing Systems
par: Qin, Weihong, et autres
Publié: (2025)

Comparing Comparators in Generalization Bounds
par: Hellström, Fredrik, et autres
Publié: (2023)

On Unbiased Low-Rank Approximation with Minimum Distortion
par: Barnes, Leighton Pate, et autres
Publié: (2025)

Improved Offline Contextual Bandits with Second-Order Bounds: Betting and Freezing
par: Ryu, J. Jon, et autres
Publié: (2025)

MambaJSCC: Adaptive Deep Joint Source-Channel Coding with Generalized State Space Model
par: Wu, Tong, et autres
Publié: (2024)

An Information-Theoretic Analysis of In-Context Learning
par: Jeon, Hong Jun, et autres
Publié: (2024)

Approximation Rates in Fréchet Metrics: Barron Spaces, Paley-Wiener Spaces, and Fourier Multipliers
par: Abdeljawad, Ahmed, et autres
Publié: (2024)

Change of measure through the Legendre transform
par: Picard-Weibel, Antoine, et autres
Publié: (2022)

Asymptotics of Language Model Alignment
par: Yang, Joy Qiping, et autres
Publié: (2024)

Trace Reconstruction with Language Models
par: Weindel, Franziska, et autres
Publié: (2025)

Latent Space Alignment for Semantic Channel Equalization
par: Hüttebräucker, Tomás, et autres
Publié: (2024)

Exact Recovery in the Data Block Model
par: Asadi, Amir R., et autres
Publié: (2026)

Post-Selection Distributional Model Evaluation
par: Farzaneh, Amirmohammad, et autres
Publié: (2026)

An Efficient Classification Model for Cyber Text
par: Hossen, Md Sakhawat, et autres
Publié: (2025)

Rate of Model Collapse in Recursive Training
par: Suresh, Ananda Theertha, et autres
Publié: (2024)

Klein Model for Hyperbolic Neural Networks
par: Mao, Yidan, et autres
Publié: (2024)

Group Projected Subspace Pursuit for Block Sparse Signal Reconstruction: Convergence Analysis and Applications
par: He, Roy Y., et autres
Publié: (2024)

An Elementary Approach to Scheduling in Generative Diffusion Models
par: Sun, Qiang, et autres
Publié: (2026)