arXiv Machine Learning
Robust and Learned Online Matching in Growing Trees
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Computation and Language
3d ago
OPTS-TTPO: Enhancing Finite-Sample Policy-Gradient Learning with Tree Search
arXiv:2609.40035v1 Announce Type: new Abstract: The policy-gradient theorem gives the exact gradient under the current policy, but finite on-policy samples may miss rare high-return trajectories. We...
arXiv AI
Aug 14
Fast A/B/n Testing: Exact Multi-Policy Comparison via Tree-Coupled Feedback Sharing
arXiv:2608. 12831v1 Announce Type: cross Abstract: Online platforms increasingly compare many adaptive decision policies---ranking systems, recommendation algorithms, pricing rules, and language-model agents---while each reward-bearing interaction can be costly or risky.
arXiv AI
Sep 25
Canopy: Exploiting Piecewise Smooth Tree Priors for Multi-Fidelity Bandits
CANOPY is a multi‑fidelity tree bandit algorithm that learns where a piecewise‑smooth prior holds instead of assuming global smoothness. It uses cheap random‑path probes to certify local aggregation bias and then focuses expensive leaf evaluations on cells where smoothness is violated. The method achieves provable fixed‑budget and regret guarantees that scale with the number of discontinuities, matching smooth‑tree rates when no violations exist and approaching structure‑blind search when violations are dense.
arXiv Machine Learning
Sep 11
Bilateral Trade Under Heavy-Tailed Valuations: Minimax Regret without a Variance Bound
The paper studies contextual bilateral trade with full feedback, showing that action-independent observations eliminate the usual polynomial adaptation penalty seen in heavy-tailed bandits. It presents fully parameter-free algorithms that achieve oracle minimax regret rates without knowing the moment order or scale, and derives new regret bounds for both parametric and nonparametric settings. The key technical insight is a paired squared‑loss statistic whose noise cancels, enabling model selection and yielding regret rates that interpolate between classical nonparametric and linear extremes.
arXiv AI
3d ago
Free Everywhere, Exact on Trees: PPO's Dropped Correction Buys Sample Efficiency Under Aggressive Reuse
arXiv:2609.39634v1 Announce Type: cross Abstract: Common policy improvement methods, including TRPO, PPO, and GRPO, estimate policy improvement under the behavioral policy's state-visitation distribu...
arXiv Machine Learning
Jul 23
Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence
arXiv:2607. 19854v1 Announce Type: new Abstract: We study horizon-free regret minimization for finite-horizon time-homogeneous tabular Markov decision processes with $S$ states, $A$ actions, horizon $H$, and per-trajectory total reward bounded by $1$.