CLASP: An online learning algorithm for Convex Losses And Squared Penalties

• URL: http://arxiv.org/abs/2601.16072v2
• Date: Sat, 24 Jan 2026 07:38:34 GMT
• Title: CLASP: An online learning algorithm for Convex Losses And Squared Penalties
• Authors: Ricardo N. Ferreira, João Xavier, Cláudia Soares,
• Abstract summary: We introduce CLASP, an algorithm that minimizes cumulative loss together with squared constraint violations.<n>For convex losses, CLASP achieves regret $Oleft(Tmax,1-right)$ and cumulative squared penalty $Oleft(T1-right)$ for any $in (0,1)$.<n>Most importantly, for strongly convex problems, CLASP provides the first logarithmic guarantees on both regret and cumulative squared penalty.
• Score: 1.096028999747108
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We study Constrained Online Convex Optimization (COCO), where a learner chooses actions iteratively, observes both unanticipated convex loss and convex constraint, and accumulates loss while incurring penalties for constraint violations. We introduce CLASP (Convex Losses And Squared Penalties), an algorithm that minimizes cumulative loss together with squared constraint violations. Our analysis departs from prior work by fully leveraging the firm non-expansiveness of convex projectors, a proof strategy not previously applied in this setting. For convex losses, CLASP achieves regret $O\left(T^{\max\{β,1-β\}}\right)$ and cumulative squared penalty $O\left(T^{1-β}\right)$ for any $β\in (0,1)$. Most importantly, for strongly convex problems, CLASP provides the first logarithmic guarantees on both regret and cumulative squared penalty. In the strongly convex case, the regret is upper bounded by $O( \log T )$ and the cumulative squared penalty is also upper bounded by $O( \log T )$.

Related papers

• An Optimistic Algorithm for Online Convex Optimization with Adversarial Constraints [55.2480439325792]
  We study Online Convex Optimization (OCO) with adversarial constraints.<n>We focus on a setting where the algorithm has access to predictions of the loss and constraint functions.<n>Our results show that we can improve the current best bounds of $ O(sqrtT) $ regret and $ tildeO(sqrtT) $ cumulative constraint violations.
  arXiv  Detail & Related papers  (2024-12-11T03:06:42Z)
• Two-Timescale Gradient Descent Ascent Algorithms for Nonconvex Minimax Optimization [77.3396841985172]
  We provide a unified analysis of two-timescale gradient ascent (TTGDA) for solving structured non minimax optimization problems.<n>Our contribution is to design TTGDA algorithms are effective beyond the setting.
  arXiv  Detail & Related papers  (2024-08-21T20:14:54Z)
• Learning to Cover: Online Learning and Optimization with Irreversible Decisions [50.5775508521174]
  We define an online learning and optimization problem with discrete and irreversible decisions contributing toward a coverage target.<n>In each period, a decision-maker selects facilities to open, receives information on the success of each one, and updates a classification model to guide future decisions.<n>The goal is to minimize facility openings under a chance constraint reflecting the coverage target, in an horizon regime characterized by a large target number of facilities.
  arXiv  Detail & Related papers  (2024-06-20T23:00:25Z)
• Multi-point Feedback of Bandit Convex Optimization with Hard Constraints [1.8130068086063336]
  We study bandit convex optimization with constraints, where the learner aims to generate a sequence of decisions under partial information of loss functions. We adopt the cumulative textithard constraint violation as the metric of constraint violation. Our algorithm attains $O(d2Tmaxc,1-c)$ regret bounds and $O(d2T1-fracc2)$ cumulative hard constraint violation bounds for convex loss functions and time-varying constraints.
  arXiv  Detail & Related papers  (2023-10-17T02:43:22Z)
• Distributed Online Convex Optimization with Adversarial Constraints: Reduced Cumulative Constraint Violation Bounds under Slater's Condition [29.809415829907525]
  This paper considers distributed online convex optimization with adversarial constraints. Agents collaborate to minimize network regret and cumulative constraint violation. To the best of our knowledge, this paper is the first to achieve reduced (network) cumulative constraint violation bounds for (distributed) online convex optimization with adversarial constraints.
  arXiv  Detail & Related papers  (2023-05-31T19:39:15Z)
• Safe Posterior Sampling for Constrained MDPs with Bounded Constraint Violation [8.849815837266977]
  Constrained Markov decision processes (CMDPs) model scenarios of sequential decision making with multiple objectives that are increasingly important in many applications. We propose the Safe PSRL (posterior sampling-based RL) algorithm that does not need such assumptions and yet performs very well. We establish a sub-linear $tildemathcal Oleft(H2.5 sqrt|mathcalS|2 |mathcalA| K right)$ upper bound on the Bayesian reward objective regret along with a bounded, i.
  arXiv  Detail & Related papers  (2023-01-27T06:18:25Z)
• Towards Painless Policy Optimization for Constrained MDPs [46.12526917024248]
  We study policy optimization in an infinite horizon, $gamma$-discounted constrained Markov decision process (CMDP) Our objective is to return a policy that achieves large expected reward with a small constraint violation. We propose a generic primal-dual framework that allows us to bound the reward sub-optimality and constraint violation for arbitrary algorithms.
  arXiv  Detail & Related papers  (2022-04-11T15:08:09Z)
• Regret and Cumulative Constraint Violation Analysis for Online Convex Optimization with Long Term Constraints [24.97580261894342]
  This paper considers online convex optimization with long term constraints, where constraints can be violated in intermediate rounds, but need to be satisfied in the long run. A novel algorithm is first proposed and it achieves an $mathcalO(Tmaxc,1-c)$ bound for static regret and an $mathcalO(T(1-c)/2)$ bound for cumulative constraint violation.
  arXiv  Detail & Related papers  (2021-06-09T15:18:06Z)
• Private Stochastic Convex Optimization: Optimal Rates in $\ell_1$ Geometry [69.24618367447101]
  Up to logarithmic factors the optimal excess population loss of any $(varepsilon,delta)$-differently private is $sqrtlog(d)/n + sqrtd/varepsilon n.$ We show that when the loss functions satisfy additional smoothness assumptions, the excess loss is upper bounded (up to logarithmic factors) by $sqrtlog(d)/n + (log(d)/varepsilon n)2/3.
  arXiv  Detail & Related papers  (2021-03-02T06:53:44Z)
• Stochastic Bandits with Linear Constraints [69.757694218456]
  We study a constrained contextual linear bandit setting, where the goal of the agent is to produce a sequence of policies. We propose an upper-confidence bound algorithm for this problem, called optimistic pessimistic linear bandit (OPLB)
  arXiv  Detail & Related papers  (2020-06-17T22:32:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.