CORTEXA
← Browse
arxivcs.LG2026-07-12

Lower Bound on the Cumulative Constrained Violation for the OGD+Projection algorithm for Constrained Online Convex Optimization (COCO)

Haricharan Balasundaram, Karthick Krishna Mahendran, Rahul Vaze

The problem of constrained online convex optimization is considered, where at each round, once a learner commits to an action $x_t \in \mathcal{X} \subset \mathbb{R}^d$, a convex loss function $f_t$ and a convex constraint function $g_t$ that drives the constraint $g_t(x)\le 0$ are revealed. The objective is to simultaneously minimize the static regret and cumulative constraint violation (CCV) compared to the benchmark that knows the loss functions and constraint functions $f_t$ and $g_t$ for all $t$ ahead of time, and chooses a static optimal action that is feasible with respect to all $g_t(x)\le 0$. Currently, the best known algorithm is OGD+Projection algorithm of [Vaze and Sinha, 2025] that has simultaneous regret of $O(\sqrt{T})$ and CCV of $O(T^{1/3})$ for $d=2$ [Balasundaram et al., 2026], and simultaneous regret of $O(\sqrt{T})$ and CCV of $O(\sqrt{T})$ for any $d$ [Sarkar and Sinha, 2026]. In this paper, we show that the CCV of the OGD+Projection algorithm is $Ω(T^{\frac{d-1}{2d}})$. This is the first such lower bound result.

View free PDFSource page

Related papers

arxivmath.OCcs.LGcs.MA2026-07-22

Decentralized Online Riemannian Optimization for Strongly Geodesically Convex Functions

Zhanyuan Cai, Emre Sahinoglu, Shahin Shahrampour

We study decentralized online optimization for strongly geodesically convex (strongly g-convex) losses on Riemannian manifolds with bounded sectional curvature, including positively curved manifolds. In centralized Riemannian optimization, strong g-convexity tightens the optimal…

View free PDFSource page
arxivstat.MLcs.LG2026-07-24

Graph-Based Correlation Matrix Generation: A Convex Optimization Approach

Ali Fakhar, K{é}vin Polisano, Ir{è}ne Gannaz, Sophie Achard

This work addresses the generation of theoretical correlation matrices with prescribed sparsity patterns associated to graph structures. We propose a novel convex optimization framework in which an initial matrix is projected onto an elliptope under a positive semidefiniteness co…

View free PDFSource page
arxivcs.LG2026-07-22

Memory-Computation Tradeoffs in Semi Amortized Parametric Optimization

Shijie Pan, Agustin Castellano, Zeyu Shen, Enrique Mallada

Learning-enabled decision systems often use offline data or computation to reduce online compute cost. Despite the empirical success of such approaches, there is limited general understanding of how much offline information is needed to achieve a desired accuracy under a fixed on…

View free PDFSource page