Searcharxiv⌕ Search

arXiv subjects

Xinyu Qiao

Publications and source records attributed to Xinyu Qiao.

5 recordsLinked to original sources

A Common Exponential Lower Bound for Dantzig and Modified Simplex in Deterministic Discounted Games

On a family of $N$-state deterministic two-player discounted games, every run that chooses adaptively between Dantzig's rule and modified simplex requires $2^{Ω(N)}$ switches from a specified initial strategy, regardless of tie breaking. More generally, a return-gate construction lets Dantzig reproduce any finite Bland prefix in an undiscounted deterministic Markov decision process with rational rewards whenever every visited policy reaches a common sink from all states. Applied to an acyclic binary counter, deleting the minimizer's return actions preserves every fixed maximizing strategy's value at each original state while reducing Dantzig's switch count from exponential to linear. With returns, halving the total optimality gap can take $Ω(h/\log h)$ switches at discount horizon $h=(1-γ)^{-1}$, even on games solvable in linear arithmetic time. Conversely, Dantzig is strongly polynomial when strongly connected components have bounded size, each state has a bounded number of actions, and the condensation graph has height $O(\log N)$.

cs.GT↗

Counterfactual Online Conformal Prediction Under Adaptive Logging

Online conformal prediction can fail when predictions shape actions and actions determine which outcomes enter calibration. Standard adaptive methods may retain marginal coverage while systematically miscovering the counterfactual outcomes of rarely selected actions. This paper formalizes the failure through counterfactual coverage and introduces Propensity-Weighted Online Conformal Prediction, an inverse-propensity-weighted recursion that debiases calibration. A doubly robust variant further reduces nuisance bias to the product of outcome-model and propensity errors. Under positivity and known logging probabilities, both methods attain the minimax expected coverage rate for nondegenerate calibration. Experiments on synthetic decision tasks, Open Bandit data, and financial rebalancing demonstrate counterfactual coverage gains under selection-biased logging, with prediction-set widths close to those of the oracle in the reported sharpness study.

cs.LG↗

Efficient Conformal Calibration for Paired Recommendation Decisions

Risk control can suppress useful changes to a frozen recommendation rule. We study how to recover valid activation from the same observed fractional losses. Two specified internal calibrators can lose efficiency by compressing losses into their sum or clipping auxiliary inverse counts before averaging. We propose Averaged Conformal Risk Calibration, or ACRC, which averages before clipping. A product identity proves expected-risk validity, while pointwise bounds characterize the additional activation. For fixed populations sampled without replacement, we connect activation to signed utility under heterogeneous users and switching constraints. Near the budgets, positive population mean gain and the stated nondegeneracy conditions give positive leading-order utility increments despite sampling dependence. Across six datasets, changing only calibration improves discounted net utility by $0.010226$ over raw and $0.008337$ over RB. A separately frozen Jester confirmation gives $0.011025 \pm 0.001082$ over raw with the rule and filter fixed, using a five-seed approximate 95 percent paired interval. Against information-matched SCoRE selecting risk or reward scores, the mean utility difference is $+0.015934 \pm 0.001440$. These gains use more mean realized risk within the declared budgets. Upstream failures delimit the benefit: efficient calibration releases useful modifications when the proposals themselves have value.

cs.LG↗

Preference-based opponent shaping in differentiable games

Strategy learning in game environments with multi-agent is a challenging problem. Since each agent's reward is determined by the joint strategy, a greedy learning strategy that aims to maximize its own reward may fall into a local optimum. Recent studies have proposed the opponent modeling and shaping methods for game environments. These methods enhance the efficiency of strategy learning by modeling the strategies and updating processes of other agents. However, these methods often rely on simple predictions of opponent strategy changes. Due to the lack of modeling behavioral preferences such as cooperation and competition, they are usually applicable only to predefined scenarios and lack generalization capabilities. In this paper, we propose a novel Preference-based Opponent Shaping (PBOS) method to enhance the strategy learning process by shaping agents' preferences towards cooperation. We introduce the preference parameter, which is incorporated into the agent's loss function, thus allowing the agent to directly consider the opponent's loss function when updating the strategy. We update the preference parameters concurrently with strategy learning to ensure that agents can adapt to any cooperative or competitive game environment. Through a series of experiments, we verify the performance of PBOS algorithm in a variety of differentiable games. The experimental results show that the PBOS algorithm can guide the agent to learn the appropriate preference parameters, so as to achieve better reward distribution in multiple game environments.

cs.AI↗

A Unified Hybrid Control Architecture for Multi-DOF Robotic Manipulators

Multi-degree-of-freedom (DOF) robotic manipulators exhibit strongly nonlinear, high-dimensional, and coupled dynamics, posing significant challenges for controller design. To address these issues, this work proposes a unified hybrid control architecture that integrates model predictive control (MPC) with feedback regulation, together with a stability analysis of the proposed scheme. The proposed approach mitigates the optimization difficulty associated with high-dimensional nonlinear systems and enhances overall control performance. Furthermore, a hardware implementation scheme based on machine learning (ML) is proposed to achieve high computational efficiency while maintaining control accuracy. Finally, simulation and hardware experiments under external disturbances validate the proposed architecture, demonstrating its superior performance, hardware feasibility, and generalization capability for multi-DOF manipulation tasks.

eess.SY↗