AI & ML
Cancellation-Free Constrained SquareCB for Safe Controller Selection
arXiv stat.ML0 views
arXiv:2611.21880v1 Announce Type: cross Abstract: We study constrained contextual bandits, in which a learner chooses one of $K$ actions in each round to minimize loss while keeping the expected cost of its play below a budget. Existing reductions to online regression weight the cost by a Lagrange multiplier learned from past constraint residuals, so slack in some rounds can offset violations in others. We instead run SquareCB proposed in \citep{foster2020beyond} with a rectified weight on the cost: it is zero when the estimated cost is within the budget, and otherwise just large enough to bring it back to the budget. Under realizability and Slater's condition with margin $\delta$, the algorithm attains regret $O(\sqrt{KT\,\mathrm{Reg}_{\mathsf{Sq}}(T)}/\delta)$ and cancellation-free violation $\sum_t(V_c^{p_t}-b)^+=O(\sqrt{KT\,\mathrm{Reg}_{\mathsf{Sq}}(T)})$, where $\mathrm{Reg}_{\mathsf{Sq}}$ is the error of the regression oracle. The same bounds hold when the budget must be met in every context, potentially adversarially chosen contexts. In controller selection for a safe-control-gym quadrotor and a BOPTEST building, the violation is 6 to 9 times lower than that of primal-dual and virtual-queue baselines, with a lower or comparable regret.
Source:https://arxiv.org/abs/2611.21880PreviousAdaptive Memory for Online Reinforcement Learning under Sparse Model ChangesNextDEFTS: Data-Efficient, Training-Free Few-Shot Learning for CLIP in the Text Subspace
Related posts
BenchAudit – Auditing LLM benchmarks for leaks, data reuse, and harness gaps
0Hacker News New
Guillotine DJ – Announcement Trailer
0Hacker News New
Researchers hijack Hugging Face account for popular Kokoro AI model
0Hacker News New
Automated LLM Fine-Tuning: GPU Selection, Dataset Analysis and Feedback
0Hacker News New
Human-written Launch HN posts get more upvotes than AI-generated ones
0Hacker News New

Parallels Desktop review
0TechRadar