Bandit Convex Optimization with Gradient Prediction Adaptivity

• URL: http://arxiv.org/abs/2605.22191v1
• Date: Thu, 21 May 2026 08:57:38 GMT
• Title: Bandit Convex Optimization with Gradient Prediction Adaptivity
• Abstract summary: We investigate whether optimistic gradient predictions can improve worst-case regret guarantees in a prediction-adaptive manner.<n>The key idea is a novel variance-reduced gradient estimator whose variance scales with the prediction error rather than the gradient norm.<n>We establish an information-theoretic lower bound that scales as $(sqrtmathbbE[S_T])$, providing a fundamental characterization of the best achievable prediction-adaptive regret.
• Score: 56.816177049016794
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Bandit convex optimization (BCO) is a fundamental online learning framework with partial feedback, where the learner observes only the loss incurred at the chosen decision point in each round. In this work, we investigate whether optimistic gradient predictions can improve worst-case regret guarantees in a prediction-adaptive manner. Specifically, given gradient predictions $m_t$, we seek regret bounds that scale with the cumulative prediction error $S_T=\sum_{t=1}^T \|\nabla f_t(x_t)-m_t\|^2.$ We first establish a negative result: under the single-point feedback protocol, an unavoidable $Ω(\sqrt{T})$ regret lower bound persists even when $S_T=o(T)$, showing that the variance of gradient estimation fundamentally obscures the benefit of accurate predictions. To overcome this barrier, we propose \emph{Two-Point Variance-Reduced Optimistic Gradient Descent} (TP-VR-OPT) for the two-point feedback setting. The key idea is a novel variance-reduced gradient estimator whose variance scales with the prediction error rather than the gradient norm. This yields a regret bound of $O\big(\sqrt{d\,\mathbb{E}[S_T]}\big),$ where $d$ is the decision dimension. Complementing this result, we establish an information-theoretic lower bound that scales as $Ω(\sqrt{\mathbb{E}[S_T]})$, providing a fundamental characterization of the best achievable prediction-adaptive regret and showing that TP-VR-OPT is optimal up to a factor of $\sqrt d$. We further develop adaptive variants that eliminate the need for prior knowledge of $\mathbb{E}[S_T]$ or the horizon $T$, and extend our framework to non-stationary environments, establishing dynamic regret guarantees that adapt simultaneously to the cumulative prediction error and the comparator path length.

Related papers

• Constrained Online Learning with Noisy Constraint Values [55.29259818039367]
  Under common feasibility, our LEDGER algorithm attains $O(sqrt T)$ expected regret and $O(sqrtTlog(eT))$ expected budget violation.<n>Neither a Slater condition, independence between feedback channels, nor an absolute constraint-value bound is needed.
  arXiv  Detail & Related papers  (2026-09-07T01:38:41Z)
• Optimizing the Preconditioner: A Black-box Online-to-Nonconvex Conversion with Static Regret Minimization Oracles [15.386375612838371]
  Non optimization can be reduced to ordinary static in online convex optimization in a black-box manner.<n>For smooth non objectives, our reduction maintains a predictable gradient tracker, while a black-box online selects a fixed $M.<n>A black-box online selects a.<n>black-box online selects a gradient tracker that determines how the tracker is transformed into a gradient.<n>A.<n>black-box online selects a fixed $M that determines how the tracker is transformed into a gradient.<n>A.<n>black-box online selects a gradient tracker that determines how the tracker is transformed into a
  arXiv  Detail & Related papers  (2026-07-20T06:53:59Z)
• Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback [14.912614425471915]
  Decision-focused learning (DFL) trains predictive models by optimizing downstream decision quality rather than standalone prediction accuracy.<n>For contextual linear optimization, most existing DFL methods assume offline full observations of objective vector.<n>We introduce a two-component hybrid estimator to update a conditional distributional model.
  arXiv  Detail & Related papers  (2026-05-31T07:58:28Z)
• Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot Tuning [61.07540493350384]
  Self-distillation (SD) is the process of retraining a student on a mixture of ground-truth and the teacher's own predictions.<n>We show that for any prediction risk, the optimally mixed student improves upon the ridge teacher for every regularization level.<n>We propose a consistent one-shot tuning method to estimate $star$ without grid search, sample splitting, or refitting.
  arXiv  Detail & Related papers  (2026-02-19T17:21:15Z)
• OrthoGrad Improves Neural Calibration [0.0]
  $perp$Grad constrains descent directions to address overconfidence.<n>$perp$Grad is a geometry-aware modification to optimization.
  arXiv  Detail & Related papers  (2025-06-04T22:12:46Z)
• Decision from Suboptimal Classifiers: Excess Risk Pre- and Post-Calibration [52.70324949884702]
  We quantify the excess risk incurred using approximate posterior probabilities in batch binary decision-making.<n>We identify regimes where recalibration alone addresses most of the regret, and regimes where the regret is dominated by the grouping loss.<n>On NLP experiments, we show that these quantities identify when the expected gain of more advanced post-training is worth the operational cost.
  arXiv  Detail & Related papers  (2025-03-23T10:52:36Z)
• $(\epsilon, u)$-Adaptive Regret Minimization in Heavy-Tailed Bandits [29.966828248335972]
  We study the regret minimization problem when $epsilon$ and $u$ are unknown to the learner. AdaR-UCB is the first algorithm that enjoys regret guarantees nearly matching those of the non-adaptive heavy-tailed case.
  arXiv  Detail & Related papers  (2023-10-04T17:11:15Z)
• Lazy Lagrangians with Predictions for Online Learning [24.18464455081512]
  We consider the general problem of online convex optimization with time-varying additive constraints. A novel primal-dual algorithm is designed by combining a Follow-The-Regularized-Leader iteration with prediction-adaptive dynamic steps. Our work extends the FTRL framework for this constrained OCO setting and outperforms the respective state-of-the-art greedy-based solutions.
  arXiv  Detail & Related papers  (2022-01-08T21:49:10Z)
• 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)
• Online nonparametric regression with Sobolev kernels [99.12817345416846]
  We derive the regret upper bounds on the classes of Sobolev spaces $W_pbeta(mathcalX)$, $pgeq 2, beta>fracdp$. The upper bounds are supported by the minimax regret analysis, which reveals that in the cases $beta> fracd2$ or $p=infty$ these rates are (essentially) optimal.
  arXiv  Detail & Related papers  (2021-02-06T15:05:14Z)
• Regret-Optimal Filtering [57.51328978669528]
  We consider the problem of filtering in linear state-space models through the lens of regret optimization. We formulate a novel criterion for filter design based on the concept of regret between the estimation error energy of a clairvoyant estimator. We show that the regret-optimal estimator can be easily implemented by solving three Riccati equations and a single Lyapunov equation.
  arXiv  Detail & Related papers  (2021-01-25T19:06:52Z)
• Leveraging Predictions in Smoothed Online Convex Optimization via Gradient-based Algorithms [18.64335888217192]
  We consider online convex optimization with time-varying stage costs and additional switching costs. Since the switching costs introduce coupling across all stages, long-term predictions tend to suffer from lower quality. We introduce a gradient-based online algorithm, Receding Horizon Inexact Gradient (RHIG), and analyze its performance by dynamic regrets.
  arXiv  Detail & Related papers  (2020-11-25T06:25:51Z)
• Nearest Neighbour Based Estimates of Gradients: Sharp Nonasymptotic Bounds and Applications [0.6445605125467573]
  gradient estimation is of crucial importance in statistics and learning theory. We consider here the classic regression setup, where a real valued square integrable r.v. $Y$ is to be predicted. We prove nonasymptotic bounds improving upon those obtained for alternative estimation methods.
  arXiv  Detail & Related papers  (2020-06-26T15:19:43Z)

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.