Cover Image

How does the optimizer implicitly bias the model merging loss landscape?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Chenxiang, Theus, Alexander, Teney, Damien, Orvieto, Antonio, Pang, Jun, Mauw, Sjouke
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Spurious Privacy Leakage in Neural Networks
by: Zhang, Chenxiang, et al.
Published: (2025)

Bits for Privacy: Evaluating Post-Training Quantization via Membership Inference
by: Zhang, Chenxiang, et al.
Published: (2025)

Meta-RL Induces Exploration in Language Agents
by: Jiang, Yulun, et al.
Published: (2025)

Scalable Ensemble Diversification for OOD Generalization and Detection
by: Rubinstein, Alexander, et al.
Published: (2024)

Recurrent neural networks: vanishing and exploding gradients are not the end of the story
by: Zucchet, Nicolas, et al.
Published: (2024)

Neural Redshift: Random Networks are not Random Functions
by: Teney, Damien, et al.
Published: (2024)

Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles
by: Scimeca, Luca, et al.
Published: (2023)

Robust training of implicit generative models for multivariate and heavy-tailed distributions with an invariant statistical loss
by: de Frutos, José Manuel, et al.
Published: (2024)

Can you Finetune your Binoculars? Embedding Text Watermarks into the Weights of Large Language Models
by: Elhassan, Fay, et al.
Published: (2025)

Design Principles for Sequence Models via Coefficient Dynamics
by: Sieber, Jerome, et al.
Published: (2025)

Recovering implicit physics model under real-world constraints
by: Banerjee, Ayan, et al.
Published: (2024)

How does Bayesian Sampling help Membership Inference Attacks?
by: Liu, Zhenlong, et al.
Published: (2025)

Causal vs. Anticausal merging of predictors
by: Mejia, Sergio Hernan Garrido, et al.
Published: (2025)

Generalized Linear Mode Connectivity for Transformers
by: Theus, Alexander, et al.
Published: (2025)

What model does MuZero learn?
by: He, Jinke, et al.
Published: (2023)

Rolling Ball Optimizer: Learning by ironing out loss landscape wrinkles
by: Belgoumri, Mohammed Djameleddine, et al.
Published: (2025)

OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable?
by: Jiang, Liangze, et al.
Published: (2024)

Fréchet regression with implicit denoising and multicollinearity reduction
by: Mansouri, Dou El Kefel, et al.
Published: (2024)

Closed-form merging of parameter-efficient modules for Federated Continual Learning
by: Salami, Riccardo, et al.
Published: (2024)

(Almost) Free Modality Stitching of Foundation Models
by: Singh, Jaisidh, et al.
Published: (2025)

How to systematically develop an effective AI-based bias correction model?
by: Zhou, Xiao, et al.
Published: (2025)

Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling
by: Rodriguez-Opazo, Cristian, et al.
Published: (2024)

Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks
by: Sieber, Jerome, et al.
Published: (2024)

How to be fair? A study of label and selection bias
by: Favier, Marco, et al.
Published: (2024)

Uncertainty modeling for fine-tuned implicit functions
by: Susmelj, Anna, et al.
Published: (2024)

Enhancing robustness of data-driven SHM models: adversarial training with circle loss
by: Yang, Xiangli, et al.
Published: (2024)

Generalized Interpolating Discrete Diffusion
by: von Rütte, Dimitri, et al.
Published: (2025)

GDP nowcasting with artificial neural networks: How much does long-term memory matter?
by: Németh, Kristóf, et al.
Published: (2023)

Exploring multimodal implicit behavior learning for vehicle navigation in simulated cities
by: Antonelo, Eric Aislan, et al.
Published: (2025)

GRASP: Deterministic argument ranking in interaction graphs
by: Misra, Diganta, et al.
Published: (2026)

Understanding the dynamics of the frequency bias in neural networks
by: Molina, Juan, et al.
Published: (2024)

Detecting labeling bias using influence functions
by: Jørgensen, Frida, et al.
Published: (2026)

Improving the classification of extreme classes by means of loss regularisation and generalised beta distributions
by: Vargas, Víctor Manuel, et al.
Published: (2024)

On student-teacher deviations in distillation: does it pay to disobey?
by: Nagarajan, Vaishnavh, et al.
Published: (2023)

Chemist-aligned retrosynthesis by ensembling diverse inductive bias models
by: Maziarz, Krzysztof, et al.
Published: (2024)

Inducing anxiety in large language models can induce bias
by: Coda-Forno, Julian, et al.
Published: (2023)

Text-guided multi-property molecular optimization with a diffusion language model
by: Xiong, Yida, et al.
Published: (2024)

Generative method for aerodynamic optimization based on classifier-free guided denoising diffusion probabilistic model
by: Deng, Shisong, et al.
Published: (2025)

Bayesian Low-Rank LeArning (Bella): A Practical Approach to Bayesian Neural Networks
by: Doan, Bao Gia, et al.
Published: (2024)

Towards certifiable AI in aviation: landscape, challenges, and opportunities
by: Bello, Hymalai, et al.
Published: (2024)