Searcharxiv⌕ Search

arXiv · 2611.19611

Nonsmooth Convex and Strongly Convex Optimization from Noisy Comparisons

Abstract

We study nonsmooth convex and strongly convex optimization problems using only noisy pairwise comparisons: each query specifies two points and returns a single binary response indicating which point has the smaller function value, subject to noise. We distinguish two observation models: Stochastic Order Oracles, which compare two evaluations of the same random loss, and Preference Oracles, whose conditional response mean is a transfer function of the objective difference. For Stochastic Order Oracles, we prove that no comparison-based algorithm can guarantee vanishing expected suboptimality in general, even when sample losses are convex and Lipschitz and the mean objective is strongly convex. Under a normalized probit calibration, we recover convergence and establish matching upper and lower rates for convex and strongly convex objectives. For Preference Oracles with a linear response model, the binary response $O \in \{\pm1\}$ satisfies $\E[O\mid y,z]=λ(f(y)-f(z))$, with $λ>0$. In dimension $d$, we obtain an upper bound of $\widetilde (d^{3/2}/(λ\sqrt N))$ and establish, to our knowledge, the first minimax lower bound of $Ω(d/(λ\sqrt N))$, matching the optimal budget $N$ exponent, for both convex and strongly convex nonsmooth objectives. Beyond exact linearity, we analyze a simple projected comparison method for nonlinear transfer functions and establish convergence rates that depend on how accurately these functions can be approximated by a linear model near zero. Our analysis requires neither oddness nor twice differentiability of the transfer function.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Evgeniy Kovalev, Fedor Stonyakin, Alexander Gasnikov. 2026-11-14. Nonsmooth Convex and Strongly Convex Optimization from Noisy Comparisons. https://searcharxiv.com/abs/2611.19611

Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.

KEEP EXPLORING

Related papers

First-order methods for stochastic and finite-sum convex optimization with deterministic constraints

In this paper, we study a class of stochastic and finite-sum convex optimization problems with deterministic constraints. Existing methods typically aim to find an $ε$-$expected\ feasible\ stochastic\ optimal$ solution, in which both the expected constraint violation and the expected optimality gap are within a prescribed tolerance $ε$. However, in many practical applications, constraints must be nearly satisfied with certainty, rendering such solutions potentially unsuitable due to the risk of substantial violations. To address this issue, we propose stochastic first-order methods for finding an $ε$-$surely\ feasible\ stochastic\ optimal$ ($ε$-SFSO) solution, where the constraint violation is deterministically bounded by $ε$ and the expected optimality gap is at most $ε$. Our methods apply an accelerated stochastic gradient (ASG) scheme or a modified variance-reduced ASG scheme $only\ once$ to a sequence of quadratic penalty subproblems with appropriately chosen penalty parameters. We establish first-order oracle complexity bounds for the proposed methods in computing an $ε$-SFSO solution. Preliminary numerical results are presented to illustrate the performance of the proposed methods.

math.OC↗

Attention's forward pass and Frank-Wolfe

We study the hardmax limit of self-attention dynamics for token embeddings obtained in the zero-temperature ($β\to+\infty$) regime, and relate it to the finite-$β$ setting. In this limit, the update rule can be viewed as a Frank-Wolfe step for a quadratic objective over the convex hull of the current token embeddings. When the key-query matrix is negative semidefinite, the method linearly contracts all tokens to a single cluster at the origin. When it is positive semidefinite, extending the hardmax rule to the entire convex hull induces a Voronoi diagram: vertices are stationary, interior points remain in their initial cells, and each token moves along a straight line toward its cell's vertex, yielding (super-)exponential convergence. As a byproduct, we also establish well-posedness of the associated ODE limit in this regime. Returning to the finite-$β$ regime, we model self-attention dynamics as a Markov chain and prove dynamic metastability: with high probability, interior tokens reach near-vertex configurations in a constant number of steps and remain within a small neighborhood for times that grow exponentially in the inverse temperature $β$, before ultimately collapsing to the origin. Thus, the hardmax dynamics accurately approximate the finite-$β$ process over exponentially long time horizons.

math.OC↗

Finite de Finetti for convex bodies and Polynomial Optimization

We study polynomial optimization over convex bodies with separately affine objectives and local affine equality and inequality constraints. We construct a convergent hierarchy of conic relaxations with explicit finite-level error bounds of order $n^{-1/2}$ at level $n$, complemented by a constructive rounding scheme that produces feasible points. The relaxation bounds and rounded objective values bracket the optimum at the same rate. The analytic ingredient is a finite de Finetti representation theorem for arbitrary proper cones: bipartite marginals of symmetric extensions in maximal tensor products are $O(n^{-1/2})$-close, in base norm, to points of the minimal tensor product. Its proof combines a uniform, monogamy-type bound on a variational mutual information based on Frenkel's relative entropy with classical conditioning and informationally complete measurements. We apply the framework to the assemblage relaxation of two-player non-local games in general probabilistic theories. For polytopic state spaces, the hierarchy consists of linear programs, and experiments on the Clauser--Horne--Shimony--Holt (CHSH) game provide a numerical proof of concept for the outer approximations and feasible rounding procedure.

math.OC↗