Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback

• URL: http://arxiv.org/abs/2605.26373v1
• Date: Mon, 25 May 2026 22:45:04 GMT
• Title: Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback
• Abstract summary: We adversarial online learning with hidden Ghai-Jacobian losses.<n>We replace the diagonal-Jacobian condition with a necessary-- Hessian geometry.
• Score: 19.63303297174247
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study adversarial online learning with hidden-convex losses, i.e., nonconvex losses that become convex after a nonlinear reparameterization. Ghai, Lu and Hazan (2022) proved that, under geometric and smoothness assumptions, online gradient descent (OGD) on such nonconvex losses approximately simulates online mirror descent (OMD) on the underlying convex losses with a suitable regularizer, yielding $\mathcal{O}(T^{2/3})$ regret. They left open whether the optimal $Θ(\sqrt{T})$ regret from online convex optimization can be recovered in this hidden-convex setting. We answer this question affirmatively. More specifically, via a sharper discrete-time algorithmic equivalence argument, we prove that OGD achieves $\mathcal{O}(\sqrt{T})$ regret under the same assumptions, matching the optimal worst-case rate for adversarial online convex optimization. We also address another open question of Ghai, Lu and Hazan (2022) by clarifying the geometry required for this algorithmic equivalence. We replace the diagonal-Jacobian sufficient condition with a necessary-and-sufficient Hessian compatibility condition, thereby expanding the class of admissible reparameterizations. We complement our tight regret bound with a lower bound showing that the Hessian compatibility assumption is essential for OGD; when it fails, we construct a smooth reparameterization and an adversarial sequence of hidden-convex losses for which OGD suffers $Ω(T)$ regret. Finally, we extend our analysis to one-point bandit feedback and prove a $\mathcal{O}(T^{3/4})$ expected regret bound for bandit OGD with spherical smoothing, matching its classical rate on convex losses.

Related papers

• Noise-Adaptive High-Probability Regret Bounds for Online Convex Optimization [12.903796669387809]
  We study high-probability regret bounds for online convex optimization (OCO) with strongly convex losses.<n>We establish three results that resolve open questions at the intersection of noise adaptivity, feedback structure, and constraint satisfaction.
  arXiv  Detail & Related papers  (2026-06-06T07:40:55Z)
• Regularized Online RLHF with Generalized Bilinear Preferences [68.44113000390544]
  We consider the problem of contextual online RLHF with general preferences.<n>We adopt the Generalized Bilinear Preference Model to capture preferences via low-rank, skew-symmetric matrices.<n>We prove that the dual gap of the greedy policy is bounded by the square of the estimation error.
  arXiv  Detail & Related papers  (2026-02-26T15:27:53Z)
• Swap Regret Minimization Through Response-Based Approachability [66.39400409563976]
  We consider the problem of minimizing different notions of swap regret in online optimization.<n>We develop a significantly simpler, computationally efficient algorithm that guarantees $O(d3/2 sqrtT)$ linear swap regret for a general convex set and $O(d sqrtT)$ when the set is centrally symmetric.
  arXiv  Detail & Related papers  (2026-02-05T23:43:25Z)
• Revisiting Projection-Free Online Learning with Time-Varying Constraints [35.573654458435854]
  We investigate constrained online convex optimization, in which decisions must belong to a fixed and typically complicated domain.<n>Several projection-free methods have been proposed with an $mathcalO(T3/4 sqrtlog T)$ regret bound and an $mathcalO(T3/4 sqrtlog T)$ cumulative constraint violation (CCV) bound for general convex losses.<n>In this paper, we improve this result and further establish textitnovel regret and CCV bounds when loss functions are strongly convex
  arXiv  Detail & Related papers  (2025-01-27T13:38:51Z)
• LEARN: An Invex Loss for Outlier Oblivious Robust Online Optimization [56.67706781191521]
  An adversary can introduce outliers by corrupting loss functions in an arbitrary number of k, unknown to the learner. We present a robust online rounds optimization framework, where an adversary can introduce outliers by corrupting loss functions in an arbitrary number of k, unknown.
  arXiv  Detail & Related papers  (2024-08-12T17:08:31Z)
• Universal Online Learning with Gradient Variations: A Multi-layer Online Ensemble Approach [57.92727189589498]
  We propose an online convex optimization approach with two different levels of adaptivity. We obtain $mathcalO(log V_T)$, $mathcalO(d log V_T)$ and $hatmathcalO(sqrtV_T)$ regret bounds for strongly convex, exp-concave and convex loss functions.
  arXiv  Detail & Related papers  (2023-07-17T09:55:35Z)
• Dynamic Regret for Strongly Adaptive Methods and Optimality of Online KRR [13.165557713537389]
  We show that Strongly Adaptive (SA) algorithms can be viewed as a principled way of controlling dynamic regret. We derive a new lower bound on a certain penalized regret which establishes the near minimax optimality of online Kernel Ridge Regression (KRR)
  arXiv  Detail & Related papers  (2021-11-22T21:52:47Z)
• Optimal Rates for Random Order Online Optimization [60.011653053877126]
  We study the citetgarber 2020online, where the loss functions may be chosen by an adversary, but are then presented online in a uniformly random order. We show that citetgarber 2020online algorithms achieve the optimal bounds and significantly improve their stability.
  arXiv  Detail & Related papers  (2021-06-29T09:48:46Z)
• High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails [55.561406656549686]
  We consider non- Hilbert optimization using first-order algorithms for which the gradient estimates may have tails. We show that a combination of gradient, momentum, and normalized gradient descent convergence to critical points in high-probability with best-known iteration for smooth losses.
  arXiv  Detail & Related papers  (2021-06-28T00:17:01Z)
• Projection-free Online Learning over Strongly Convex Sets [24.517908972536432]
  We study the special case of online learning over strongly convex sets, for which we first prove that OFW can enjoy a better regret bound of $O(T2/3)$ for general convex losses. We show that it achieves a regret bound of $O(sqrtT)$ over general convex sets and a better regret bound of $O(sqrtT)$ over strongly convex sets.
  arXiv  Detail & Related papers  (2020-10-16T05:42:50Z)

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.