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

Documenti analoghi

• Spurious Privacy Leakage in Neural Networks
  di: Zhang, Chenxiang, et al.
  Pubblicazione: (2025)
• Bits for Privacy: Evaluating Post-Training Quantization via Membership Inference
  di: Zhang, Chenxiang, et al.
  Pubblicazione: (2025)
• Meta-RL Induces Exploration in Language Agents
  di: Jiang, Yulun, et al.
  Pubblicazione: (2025)
• Scalable Ensemble Diversification for OOD Generalization and Detection
  di: Rubinstein, Alexander, et al.
  Pubblicazione: (2024)
• Recurrent neural networks: vanishing and exploding gradients are not the end of the story
  di: Zucchet, Nicolas, et al.
  Pubblicazione: (2024)