The paper proves the first optimal O(n^{-1/2}) Wasserstein-1 CLT rates for locally dependent sequences and geometrically ergodic Markov chains, plus new W_p rates for p greater than or equal to 2 under mild moments, with an application to U-statistics.
John Wiley & Sons
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
years
2026 9verdicts
UNVERDICTED 9representative citing papers
SDP constructs a task-induced state space from raw text by having agents commit to and certify natural-language predicates as states, enabling structured planning and analysis in unstructured language environments.
A latent Q-Barrier shield learns context, dynamics, and cost critic to enforce safety constraints at action level in in-context RL, with a conditional barrier-margin guarantee and benchmark gains.
A critique-and-routing controller cast as a finite-horizon MDP with policy-gradient optimization outperforms one-shot routing baselines on reasoning benchmarks while using the strongest agent for under 25% of calls.
State augmentation converts static risk measures on total cost into dynamic programs, yielding sample-complexity bounds for risk-averse MDPs and stochastic optimal control under φ-divergence robustness.
Robust minimax task inference in BFMs achieves dynamics-shift robustness from nominal offline data alone and outperforms standard baselines.
Framework uses LLMs to map natural-language questions about MCTS to explanations based on tree statistics like visit counts and values, without hand-crafted formal logic.
Value mirror descent integrates mirror descent into value iteration for discounted MDPs, delivering near-optimal sample complexity of order |S||A|(1-γ)^{-3}ε^{-2} for general convex regularizers and bounded Bregman divergence between generated and optimal policies.
Error propagation mitigation in digital twins is cast as an MDP/POMDP with HMM-derived regimes as states, where the MDP policy maximizes reward and the POMDP recovers 95% of that performance.
citing papers explorer
-
Wasserstein-p Central Limit Theorem Rates: From Local Dependence to Markov Chains
The paper proves the first optimal O(n^{-1/2}) Wasserstein-1 CLT rates for locally dependent sequences and geometrically ergodic Markov chains, plus new W_p rates for p greater than or equal to 2 under mild moments, with an application to U-statistics.
-
State-Centric Decision Process
SDP constructs a task-induced state space from raw text by having agents commit to and certify natural-language predicates as states, enabling structured planning and analysis in unstructured language environments.
-
Latent Q-Barrier Shielding for Safe In-Context Reinforcement Learning
A latent Q-Barrier shield learns context, dynamics, and cost critic to enforce safety constraints at action level in in-context RL, with a conditional barrier-margin guarantee and benchmark gains.
-
Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs
A critique-and-routing controller cast as a finite-horizon MDP with policy-gradient optimization outperforms one-shot routing baselines on reasoning benchmarks while using the strongest agent for under 25% of calls.
-
Sample Complexity for Markov Decision Processes and Stochastic Optimal Control with Static Risk Measures
State augmentation converts static risk measures on total cost into dynamic programs, yielding sample-complexity bounds for risk-averse MDPs and stochastic optimal control under φ-divergence robustness.
-
When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited
Robust minimax task inference in BFMs achieves dynamics-shift robustness from nominal offline data alone and outperforms standard baselines.
-
Toward Template-Free Explainability for Monte Carlo Tree Search
Framework uses LLMs to map natural-language questions about MCTS to explanations based on tree statistics like visit counts and values, without hand-crafted formal logic.
-
Value Mirror Descent for Reinforcement Learning
Value mirror descent integrates mirror descent into value iteration for discounted MDPs, delivering near-optimal sample complexity of order |S||A|(1-γ)^{-3}ε^{-2} for general convex regularizers and bounded Bregman divergence between generated and optimal policies.
-
Optimal sequential decision-making for error propagation mitigation in digital twins
Error propagation mitigation in digital twins is cast as an MDP/POMDP with HMM-derived regimes as states, where the MDP policy maximizes reward and the POMDP recovers 95% of that performance.