arXiv subjects

Andreea-Alexandra Muşat

Publications and source records attributed to Andreea-Alexandra Muşat.

3 recordsLinked to original sources

arXiv2026

A non-autonomous center-stable set theorem for saddle avoidance in optimization

Optimization algorithms are unlikely to converge to strict saddle points. Proofs to that effect rely on the Center-Stable Manifold Theorem (CSMT), casting algorithms as dynamical systems: $x_{k+1} = g_k(x_k)$. In its standard form, the CSMT is limited to autonomous systems (the maps $g_k$ are all the same). To study algorithms such as gradient descent with non-constant step-size schedules, we need a non-autonomous CSMT. There are a few, but they are unable to handle, for example, vanishing step sizes. To cover such scenarios, we establish a new Center-Stable Set Theorem (CSST) for non-autonomous systems. We use it to prove saddle avoidance for gradient descent (Euclidean and Riemannian) and for the proximal point method, without assuming Lipschitz gradients or isolated saddles, and allowing vanishing step sizes.

math.OC↗

arXiv2026

Insights on Muon from Simple Quadratics

Muon updates weight matrices along (approximate) polar factors of the gradients and has shown strong empirical performance in large-scale training. Existing attempts at explaining its performance largely focus on single-step comparisons (on quadratic proxies) and worst-case guarantees that treat the inexactness of the polar-factor as a nuisance ``to be argued away''. We show that already on simple strongly convex functions such as $L(W)=\frac12\|W\|_{\text{F}}^2$, these perspectives are insufficient, suggesting that understanding Muon requires going beyond local proxies and pessimistic worst-case bounds. Instead, our analysis exposes two observations that already affect behavior on simple quadratics and are not well captured by prevailing abstractions: (i) approximation error in the polar step can qualitatively alter discrete-time dynamics and improve reachability and finite-time performance -- an effect practitioners exploit to tune Muon, but that existing theory largely treats as a pure accuracy compromise; and (ii) structural properties of the objective affect finite-budget constants beyond the prevailing conditioning-based explanations. Thus, any general theory covering these cases must either incorporate these ingredients explicitly or explain why they are irrelevant in the regimes of interest.

math.OC↗

arXiv2025

Gradient descent avoids strict saddles with a simple line-search method too

It is known that gradient descent (GD) on a $C^2$ cost function generically avoids strict saddle points when using a small, constant step size. However, no such guarantee existed for GD with a line-search method. We provide one for a modified version of the standard Armijo backtracking method with generic, arbitrarily large initial step size. The proof underlines the double role of the Luzin $N^{-1}$ property for the iteration maps, and allows to forgo the habitual Lipschitz gradient assumption. We extend this to the Riemannian setting (RGD), assuming the retraction is real analytic (though the cost function still only needs to be $C^2$). In closing, we also improve guarantees for RGD with a constant step size in some scenarios.

math.OC↗