arXiv:2209. 03282v5 Announce Type: replace-cross Abstract: Accelerating the convergence of second-order optimization, particularly Newton-type methods, remains a pivotal challenge in algorithmic research.
arXiv:2608.22129v2 Announce Type: replace Abstract: Cubic regularized Newton methods have the optimal $\mathcal{O}(\epsilon^{-3/2})$ global rate, but a dense subproblem solve limits the feasible bloc...
arXiv:2607. 22906v1 Announce Type: new Abstract: We study adaptive gradient descent for continuously differentiable, possibly nonconvex objectives under one-sided H\"older regularity.
arXiv:2608. 21359v1 Announce Type: cross Abstract: We develop a new direct accelerated Newton method for minimizing convex functions with Lipschitz continuous Hessian.
arXiv:2502. 00753v4 Announce Type: replace-cross Abstract: Smoothness is crucial for attaining fast rates in first-order optimization.
The paper introduces Curvature-Scaled Sharpness-Aware Minimization (CS‑SAM), a variant of SAM that scales both the perturbation and descent step by curvature bounds to uniformly control gradient distortion under generalized smoothness conditions. It proves deterministic ≥1/T convergence rates for nonconvex objectives, last‑iterate ≥1/T rates for convex objectives, and linear convergence under the Polyak‑Łojasiewicz condition, while recovering standard gradient descent rates when the perturbation is zero. Experiments on computer vision tasks show that CS‑SAM, particularly the (H0,H1) variant, achieves the highest mean best‑test accuracy across four settings compared to tuned SAM and USAM.
arXiv:2608. 01552v1 Announce Type: cross Abstract: Quadratic Gradient (QG) is a Newton-type optimization framework that bridges first-order gradient descent and second-order optimization by incorporating curvature information into gradient updates.
arXiv:2503. 04712v3 Announce Type: replace-cross Abstract: We study the optimization of non-convex functions that are not necessarily smooth (gradient and/or Hessian are Lipschitz) using first order methods.
arXiv:2409. 03682v2 Announce Type: replace Abstract: Learning new tasks by leveraging prior experience is a fundamental trait of intelligent systems.
arXiv:2605.04722v2 Announce Type: replace-cross Abstract: Input convex neural networks (ICNNs) are used to learn convex objectives whose minimizers define decisions, making efficient and reliable opt...
arXiv:2606. 30455v1 Announce Type: new Abstract: The standard convergence analysis of mini-batch stochastic gradient descent (SGD) models gradient noise using a single variance term that treats all parameter directions equally, ignoring the fact that noise in high-curvature directions has less impact because learning rates are already constrained there.
arXiv:2512. 02494v2 Announce Type: replace Abstract: Differentiable optimization layers enable learning systems to make decisions by solving embedded optimization problems.