Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach

Documenti analoghi

• Learning Provably Improves the Convergence of Gradient Descent
  di: Song, Qingyu, et al.
  Pubblicazione: (2025)
• Stochastic Compositional Minimax Optimization with Provable Convergence Guarantees
  di: Deng, Yuyang, et al.
  Pubblicazione: (2024)
• Understanding Forgetting in LLM Supervised Fine-Tuning and Preference Learning -- A Convex Optimization Perspective
  di: Fernando, Heshan, et al.
  Pubblicazione: (2024)
• Convergence of the Iterates of the Stochastic Proximal Gradient Method
  di: Madariaga, Javier I.
  Pubblicazione: (2026)
• On Penalty-based Bilevel Gradient Descent Method
  di: Shen, Han, et al.
  Pubblicazione: (2023)