arXiv subjects

Teodor Rotaru

Publications and source records attributed to Teodor Rotaru.

5 recordsLinked to original sources

arXiv2025

Tight Convergence Rates in Gradient Mapping for the Difference-of-Convex Algorithm

We establish new theoretical convergence guarantees for the difference-of-convex algorithm (DCA), where the second function is allowed to be weakly-convex, measuring progress via composite gradient mapping. Based on a tight analysis of two iterations of DCA, we identify six parameter regimes leading to sublinear convergence rates toward critical points and establish those rates by proving adapted descent lemmas. We recover existing rates for the standard difference-of-convex decompositions of nonconvex-nonconcave functions, while for all other curvature settings our results are new, complementing recently obtained rates on the gradient residual. Three of our sublinear rates are tight for any number of DCA iterations, while for the other three regimes we conjecture exact rates, using insights from the tight analysis of gradient descent and numerical validation using the performance estimation methodology. Finally, we show how the equivalence between proximal gradient descent (PGD) and DCA allows the derivation of exact PGD rates for any constant stepsize.

math.OC↗

arXiv2025

Tight Analysis of Difference-of-Convex Algorithm (DCA) Improves Convergence Rates for Proximal Gradient Descent

We investigate a difference-of-convex (DC) formulation where the second term is allowed to be weakly convex. We examine the precise behavior of a single iteration of the difference-of-convex algorithm (DCA), providing a tight characterization of the objective function decrease, distinguishing between six distinct parameter regimes. Our proofs, inspired by the performance estimation framework, are notably simplified compared to related prior research. We subsequently derive sublinear convergence rates for the DCA towards critical points, assuming at least one of the functions is smooth. Additionally, we explore the underexamined equivalence between proximal gradient descent (PGD) and DCA iterations, demonstrating how DCA, a parameter-free algorithm, without the need for a stepsize, serves as a tool for studying the exact convergence rates of PGD.

math.OC↗

arXiv2024

Exact worst-case convergence rates of gradient descent: a complete analysis for all constant stepsizes over nonconvex and convex functions

We consider gradient descent with constant stepsizes and derive exact worst-case convergence rates on the minimum gradient norm of the iterates. Our analysis covers all possible stepsizes and arbitrary upper/lower bounds on the curvature of the objective function, thus including convex, strongly convex and weakly convex (hypoconvex) objective functions. Among the challenging parts of the analysis, we note the necessity to exploit dependencies between non-consecutive iterates. While this complicates the proofs to some extent, it enables us to achieve an exact full-range analysis of gradient descent for any constant stepsize (covering, in particular, normalized stepsizes greater than one), whereas the literature contained only conjectured rates of this type. In the nonconvex case, allowing arbitrary bounds on upper and lower curvatures extends existing partial results that are valid only for gradient Lipschitz functions (i.e., where lower and upper bounds on curvature are equal), leading to improved rates for weakly convex functions. From our exact worst-case performance bounds, we deduce the optimal constant stepsize for gradient descent. Leveraging our analysis, we also introduce a new variant of gradient descent based on a unique, fixed sequence of variable stepsizes, demonstrating its superiority in the worst-case over any constant stepsize schedule.

math.OC↗

arXiv2024

Improved convergence rates for the Difference-of-Convex algorithm

We consider a difference-of-convex formulation where one of the terms is allowed to be hypoconvex (or weakly convex). We first examine the precise behavior of a single iteration of the Difference-of-Convex algorithm (DCA), giving a tight characterization of the objective function decrease. This requires distinguishing between eight distinct parameter regimes. Our proofs are inspired by the performance estimation framework, but are much simplified compared to similar previous work. We then derive sublinear DCA convergence rates towards critical points, distinguishing between cases where at least one of the functions is smooth and where both functions are nonsmooth. We conjecture the tightness of these rates for four parameter regimes, based on strong numerical evidence obtained via performance estimation, as well as the leading constant in the asymptotic sublinear rate for two more regimes.

math.OC↗

arXiv2022

Tight convergence rates of the gradient method on smooth hypoconvex functions

We perform the first tight convergence analysis of the gradient method with varying step sizes when applied to smooth hypoconvex (weakly convex) functions. Hypoconvex functions are smooth nonconvex functions whose curvature is bounded and assumed to belong to the interval $[\mu, L]$, with $\mu<0$. Our convergence rates improve and extend the existing analysis for smooth nonconvex functions with $L$-Lipschitz gradient (which corresponds to the case $\mu=-L$), and smoothly interpolates between that class and the class of smooth convex functions. We obtain our results using the performance estimation framework adapted to hypoconvex functions, for which new interpolation conditions are derived. We derive explicit upper bounds on the minimum gradient norm of the iterates for a large range of step sizes, explain why all such rates share a common structure, and prove that these rates are tight when step sizes are smaller or equal to $1/L$. Finally, we identify the optimal constant step size that minimizes the worst-case of the gradient method applied to hypoconvex functions.

math.OC↗