Second-order bilevel methods achieve Õ(ε^{-1.5}) iteration complexity for second-order stationary points, faster than first-order approaches, with a lazy variant improving computational efficiency by √d.
A constrained optimization approach to bilevel opti- 15 mization with multiple inner minima.arXiv preprint arXiv:2203.01123, page 4
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
Penalty-based first-order methods find ε-KKT points in bilevel minimax problems with Õ(ε^{-4}) deterministic and Õ(ε^{-9}) stochastic oracle complexity, improving prior bounds for constrained lower-level cases via Lagrangian duality.
EBOMLC applies dynamic barrier gradient descent with one-step inner loop, mixture upper loss, and alignment-aware barrier to make meta label correction faster and more robust on noisy data, outperforming baselines on CIFAR-10/100 especially at high noise rates.
Bilevel learning methods rely on implicit differentiation but are restricted by assumptions of unique lower-level solutions and struggle with constraints, and connections to broader bilevel optimization literature may enable more scalable general-purpose algorithms.
citing papers explorer
-
Second-Order Bilevel Optimization with Accelerated Convergence Rates
Second-order bilevel methods achieve Õ(ε^{-1.5}) iteration complexity for second-order stationary points, faster than first-order approaches, with a lazy variant improving computational efficiency by √d.
-
Penalty-Based First-Order Methods for Bilevel Optimization with Minimax and Constrained Lower-Level Problems
Penalty-based first-order methods find ε-KKT points in bilevel minimax problems with Õ(ε^{-4}) deterministic and Õ(ε^{-9}) stochastic oracle complexity, improving prior bounds for constrained lower-level cases via Lagrangian duality.
-
Bilevel learning
Bilevel learning methods rely on implicit differentiation but are restricted by assumptions of unique lower-level solutions and struggle with constraints, and connections to broader bilevel optimization literature may enable more scalable general-purpose algorithms.