Newton GALET
Newton GALET is a bilevel optimization algorithm that handles singular lower-level Hessian matrices under the positive spectral gap condition, avoiding squared-Hessian multiplier systems.
Timeline (last 90 days)
A recent paper proposes two Newton methods that go beyond lower-level strong convexity: Newton GALET and Newton BAMM, and introduces a unified framework, GNBO.
Under the positive spectral gap condition, Newton GALET uses the range-space structure to avoid the squared-Hessian multiplier system used in GALET.
The authors establish convergence guarantees for Newton GALET and Newton BAMM, and give complexity bounds improved relative to GALET and sl-BAMM under the corresponding assumptions.
All Facts (3)
A recent paper proposes two Newton methods that go beyond lower-level strong convexity: Newton GALET and Newton BAMM, and introduces a unified framework, GNBO.
50%UnverifiedUnder the positive spectral gap condition, Newton GALET uses the range-space structure to avoid the squared-Hessian multiplier system used in GALET.
50%UnverifiedThe authors establish convergence guarantees for Newton GALET and Newton BAMM, and give complexity bounds improved relative to GALET and sl-BAMM under the corresponding assumptions.
50%