arXiv subjects

Yi Tian

Publications and source records attributed to Yi Tian.

27 records · Page 2Linked to original sources

arXiv2023

Dynamic Game of the Dual-Channel Supply Chain Under a Carbon Subsidy Policy

This study investigates the dynamic game behaviors of dual-channel supply chains involving an oligopoly manufacturer selling low-carbon products to online and offline retailers. The price game models under government subsidy are discussed under three scenarios: (1) simultaneous decision, (2) manufacturer dominates the market, and (3) retailer dominates the market. The equilibrium strategies are compared under the government subsidy policy. Using numerical simulation,complex characteristics of the dual-channel supply chain under the carbon subsidy policy are investigated. The complexity of wholesale price and sales commission of each channel are analyzed by bifurcation, largest Lyapunov exponent and basin of attraction diagrams. Furthermore,parameter adjustment and delayed feedback control methods are proven to be effective approaches to chaos control.

math.NA↗

arXiv2022

Byzantine-Robust Federated Linear Bandits

In this paper, we study a linear bandit optimization problem in a federated setting where a large collection of distributed agents collaboratively learn a common linear bandit model. Standard federated learning algorithms applied to this setting are vulnerable to Byzantine attacks on even a small fraction of agents. We propose a novel algorithm with a robust aggregation oracle that utilizes the geometric median. We prove that our proposed algorithm is robust to Byzantine attacks on fewer than half of agents and achieves a sublinear $\tilde{\mathcal{O}}({T^{3/4}})$ regret with $\mathcal{O}(\sqrt{T})$ steps of communication in $T$ steps. Moreover, we make our algorithm differentially private via a tree-based mechanism. Finally, if the level of corruption is known to be small, we show that using the geometric median of mean oracle for robust aggregation further improves the regret bound.

cs.LG↗

arXiv2021

Complexity Lower Bounds for Nonconvex-Strongly-Concave Min-Max Optimization

We provide a first-order oracle complexity lower bound for finding stationary points of min-max optimization problems where the objective function is smooth, nonconvex in the minimization variable, and strongly concave in the maximization variable. We establish a lower bound of $Ω\left(\sqrtκε^{-2}\right)$ for deterministic oracles, where $ε$ defines the level of approximate stationarity and $κ$ is the condition number. Our analysis shows that the upper bound achieved in (Lin et al., 2020b) is optimal in the $ε$ and $κ$ dependence up to logarithmic factors. For stochastic oracles, we provide a lower bound of $Ω\left(\sqrtκε^{-2} + κ^{1/3}ε^{-4}\right)$. It suggests that there is a significant gap between the upper bound $\mathcal{O}(κ^3 ε^{-4})$ in (Lin et al., 2020a) and our lower bound in the condition number dependence.

math.OC↗

arXiv2021

Online Learning in Unknown Markov Games

We study online learning in unknown Markov games, a problem that arises in episodic multi-agent reinforcement learning where the actions of the opponents are unobservable. We show that in this challenging setting, achieving sublinear regret against the best response in hindsight is statistically hard. We then consider a weaker notion of regret by competing with the \emph{minimax value} of the game, and present an algorithm that achieves a sublinear $\tilde{\mathcal{O}}(K^{2/3})$ regret after $K$ episodes. This is the first sublinear regret bound (to our knowledge) for online learning in unknown Markov games. Importantly, our regret bound is independent of the size of the opponents' action spaces. As a result, even when the opponents' actions are fully observable, our regret bound improves upon existing analysis (e.g., (Xie et al., 2020)) by an exponential factor in the number of opponents.

cs.LG↗

arXiv2021

Provably Efficient Algorithms for Multi-Objective Competitive RL

We study multi-objective reinforcement learning (RL) where an agent's reward is represented as a vector. In settings where an agent competes against opponents, its performance is measured by the distance of its average return vector to a target set. We develop statistically and computationally efficient algorithms to approach the associated target set. Our results extend Blackwell's approachability theorem (Blackwell, 1956) to tabular RL, where strategic exploration becomes essential. The algorithms presented are adaptive; their guarantees hold even without Blackwell's approachability condition. If the opponents use fixed policies, we give an improved rate of approaching the target set while also tackling the more ambitious goal of simultaneously minimizing a scalar cost function. We discuss our analysis for this special case by relating our results to previous works on constrained RL. To our knowledge, this work provides the first provably efficient algorithms for vector-valued Markov games and our theoretical guarantees are near-optimal.

cs.LG↗

arXiv2020

Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes

We study minimax optimal reinforcement learning in episodic factored Markov decision processes (FMDPs), which are MDPs with conditionally independent transition components. Assuming the factorization is known, we propose two model-based algorithms. The first one achieves minimax optimal regret guarantees for a rich class of factored structures, while the second one enjoys better computational complexity with a slightly worse regret. A key new ingredient of our algorithms is the design of a bonus term to guide exploration. We complement our algorithms by presenting several structure-dependent lower bounds on regret for FMDPs that reveal the difficulty hiding in the intricacy of the structures.

cs.LG↗

arXiv2018

Design of Novel 3D SERS Probes with Drastically Improved Detection Limit by Maximizing SPP - Based Multiple Coupling Effects

Quantifying formidable multiple coupling effects involved in Surface-enhanced Raman scattering (SERS) is a prerequisite for accurate design of SERS probes with superior detection limit and uniformity which are the targets for trace substance detection. Here, combining theory and experiments on novel 3D periodic Au/SiO2 hybrid nanogrids, we successfully develop a generalized methodology of accurately designing high performance SERS probes. Structural parameters and symmetry, Au roughness, and polarization are quantitatively correlated to intrinsic electromagnetic field (EMF) enhancements from surface plasmon polariton (SPP), localized surface plasmon resonance (LSPR), optical standing wave and their couplings theoretically, which is experimentally verified. The hexagonal SERS probes optimized by the methodology successfully detect 5*10^-11 M Hg ions in water, and 2.5*10^-11 M R6G with 40 times improvement of detection limit, an enhancement factor of 3.4*10^8 and uniformity of 5.56%, which results from the extra Au roughness - independent 144% contribution of LSPR effects excited by SPP interference waves as secondary sources, beyond the conventional recognization. This study opens up a pioneering way not only for providing the generalized design principles of SERS probe structures with high performance but for accurately designing their structures with particular purposes such as greatly improved detection limit and uniformity which are very significant for trace substance detection.

physics.optics↗

arXiv2018

Towards the full realization of the RIBLL2 beam line at the HIRFL-CSR complex

The RIBLL2 in-flight separator at IMP, the secondary beam line between two storage rings at the \blue{\uwave{Heavy Ion Research Facility in Lanzhou (HIRFL-CSR)}}, has been commissioned to study the rare-isotope beam (RIB) physics at around 300 MeV/nucleon for the first time, in combination of the external target facility (ETF). The unambiguous particle identification in mass and charge states for $^{18}$O and $^{40}$Ar fragments has been achieved in recent experiments. A full realization of RIBLL2 will open many potentials to address important RIB physics problems at around 300 MeV/nucleon.

physics.acc-ph↗

arXiv2016

Plastic scintillation detectors for precision time-of-flight measurements of relativistic heavy ions

Plastic scintillation detectors for Time-of-Flight (TOF) measurements are almost essential for event-by-event identification of relativistic rare isotopes. In this work, a pair of plastic scintillation detectors of 50 $\times$ 50 $\times$ 3$^{t}$ mm$^3$ and 80 $\times$ 100 $\times$ 3$^{t}$ mm$^3$ have been set up at the external target facility (ETF), Institute of Modern Physics. Their time, energy and position responses are measured with $^{18}$O primary beam at 400 MeV/nucleon. After the off-line walk-effect and position corrections, the time resolution of the two detectors are determined to be 27 ps ($σ$) and 36 ps ($σ$), respectively. Both detectors have nearly the same energy resolution of 3$\%$ ($σ$) and position resolution of 2 mm ($σ$). The detectors have been used successfully in nuclear reaction cross section measurements, and will be be employed for upgrading RIBLL2 beam line at IMP as well as for the high energy branch at HIAF.

physics.ins-det↗