arXiv subjects

Yidong Zhang

Publications and source records attributed to Yidong Zhang.

8 recordsLinked to original sources

arXiv2026

A Systematic Analysis of Automatic Differentiation versus Discretization-based Constraints for Physics-Informed PDE Solvers

Physics-informed neural networks (PINNs) represent a growing frontier in using artificial intelligence to solve partial differential equations (PDEs). Automatic differentiation (AD) plays a central role in this paradigm, which is mesh-free and replaces traditional iterative solvers with gradient-based optimization in continuous space. However, the inherent limitations of AD, particularly in handling higher-order derivatives and discontinuous solutions, pose significant challenges for complex problems. This has motivated a growing number of researchers to explore discretization-based constraints as an alternative path. Yet, the respective applicability of these two paradigms remains largely unexplored. In this work, we conduct systematic experiments across a wide spectrum of problems, from simple linear Poisson to high-Mach hypersonic flows with strong discontinuities. Through a rigorous decomposition of approximation, optimization, and truncation errors, we systematically elucidate the fundamental trade-offs and error-governing mechanisms of both paradigms, as well as two representative network architectures: multi-layer perceptron (MLP) and graph neural network (GNN). Our results reveal a consistent trend: as nonlinearity strengthens, the accuracy advantage of discretization-based constraints becomes increasingly pronounced, with smaller optimization errors compensating for the truncation errors. Moreover, the more complex the nonlinearity and boundary conditions, the greater the advantage of GNN over MLP. These insights offer a robust practical guideline for configuring neural PDE solvers in demanding engineering applications. Our source data and code are available at https://github.com/guoxing0809/neuropde_analysis.

math.NA↗

arXiv2026

EndoLIFT: Language-Disambiguated Latent-Conditioned Rectified Flow for Bidirectional Endoscopic Control

Routine gastrointestinal endoscopy is intrinsically bidirectional: the instrument is advanced to reach target anatomy and later withdrawn or retroflexed for inspection, while an external cue may require earlier reversal. When the requested phase changes before the visual scene does, nearly identical observations can require opposite axial actions. We identify and formalize this ambiguity in bidirectional endoscopic control as intent aliasing. We propose EndoLIFT (Endoscopic Language-Instruction Flow with Trajectory Latents), a vision-language-action policy that combines explicit language-based intent conditioning with a latent-conditioned rectified-flow action expert. The policy receives RGB, a language instruction, and the previous-action state; a 32-D variational trajectory latent stochastically conditions continuous action-chunk generation. Controlled same-observation instruction swaps establish that language selects the axial mode, independently of whether the trajectory latent is present. Relative to the matched model without latent conditioning, EndoLIFT improves navigation-direction accuracy by 11.1 percentage points and reduces wrong-direction advance by 83\%. An architecture-controlled 1-bit mode-flag reference exhibits weaker canonical-anchor switching, while EndoLIFT retains 82.8\% intent-following accuracy across 44 held-out linguistic variants. In closed-loop evaluation, EndoLIFT improves overall success by 30 percentage points over EndoLIFT w/o VTL on both the seen colon phantom and the unseen lung and stomach phantoms, and completes 10/10 ex-vivo porcine-trachea trials. These results separate language-based intent selection from the trajectory latent's contribution to directional correctness and robust retraction.

cs.RO↗

arXiv2026

DeepStock: Reinforcement Learning with Policy Regularizations for Inventory Management

Deep Reinforcement Learning (DRL) provides a general-purpose methodology for training inventory policies that can leverage big data and compute. However, off-the-shelf implementations of DRL have seen mixed success, often plagued by high sensitivity to the hyperparameters used during training. In this paper, we show that by imposing policy regularizations, grounded in classical inventory concepts such as "Base Stock", we can significantly accelerate hyperparameter tuning and improve the final performance of several DRL methods. We report details from a 100% deployment of DRL with policy regularizations on Alibaba's e-commerce platform, Tmall. We also include extensive synthetic experiments, which show that policy regularizations reshape the narrative on what is the best DRL method for inventory management.

cs.LG↗

arXiv2026

Balanced Anomaly-guided Ego-graph Diffusion Model for Inductive Graph Anomaly Detection

Graph anomaly detection (GAD) is crucial in applications like fraud detection and cybersecurity. Despite recent advancements using graph neural networks (GNNs), two major challenges persist. At the model level, most methods adopt a transductive learning paradigm, which assumes static graph structures, making them unsuitable for dynamic, evolving networks. At the data level, the extreme class imbalance, where anomalous nodes are rare, leads to biased models that fail to generalize to unseen anomalies. These challenges are interdependent: static transductive frameworks limit effective data augmentation, while imbalance exacerbates model distortion in inductive learning settings. To address these challenges, we propose a novel data-centric framework that integrates dynamic graph modeling with balanced anomaly synthesis. Our framework features: (1) a discrete ego-graph diffusion model, which captures the local topology of anomalies to generate ego-graphs aligned with anomalous structural distribution, and (2) a curriculum anomaly augmentation mechanism, which dynamically adjusts synthetic data generation during training, focusing on underrepresented anomaly patterns to improve detection and generalization. Experiments on five datasets demonstrate that the effectiveness of our framework.

cs.LG↗

arXiv2024

A Deep Q-Network Based on Radial Basis Functions for Multi-Echelon Inventory Management

This paper addresses a multi-echelon inventory management problem with a complex network topology where deriving optimal ordering decisions is difficult. Deep reinforcement learning (DRL) has recently shown potential in solving such problems, while designing the neural networks in DRL remains a challenge. In order to address this, a DRL model is developed whose Q-network is based on radial basis functions. The approach can be more easily constructed compared to classic DRL models based on neural networks, thus alleviating the computational burden of hyperparameter tuning. Through a series of simulation experiments, the superior performance of this approach is demonstrated compared to the simple base-stock policy, producing a better policy in the multi-echelon system and competitive performance in the serial system where the base-stock policy is optimal. In addition, the approach outperforms current DRL approaches.

cs.LG↗

arXiv2022

Demonstration of room-temperature continuous-wave operation of InGaAs/AlGaAs quantum well lasers directly grown on on-axis silicon (001)

Room-temperature continuous-wave operation of InGaAs/AlGaAs quantum well lasers directly grown on on-axis silicon (001) has been demonstrated. A 420 nm thick GaAs epilayer completely free of antiphase domains was initially grown on the silicon substrate in a metal-organic chemical vapor deposition system and the other epilayers including four sets of five-period strained-layer superlattices and the laser-structural layers were successively grown in a molecular beam epitaxy system. The lasers were prepared as broad-stripe Fabry-Perot ones with a stripe width of 21.5 um and a cavity length of 1 mm. Typically, the threshold current and the corresponding threshold current density are 186.4 mA and 867 A/cm2, respectively. The lasing wavelength is around 980 nm and the slope efficiency is 0.097 W/A with a single-facet output power of 22.5 mW at an injection current of 400 mA. This advancement makes the silicon-based monolithic optoelectronic integration relevant to quantum well lasers more promising with an enhanced feasibility.

physics.optics↗

arXiv2022

Context-Based Dynamic Pricing with Online Clustering

We consider a context-based dynamic pricing problem of online products, which have low sales. Sales data from Alibaba, a major global online retailer, illustrate the prevalence of low-sale products. For these products, existing single-product dynamic pricing algorithms do not work well due to insufficient data samples. To address this challenge, we propose pricing policies that concurrently perform clustering over product demand and set individual pricing decisions on the fly. By clustering data and identifying products that have similar demand patterns, we utilize sales data from products within the same cluster to improve demand estimation for better pricing decisions. We evaluate the algorithms using regret, and the result shows that when product demand functions come from multiple clusters, our algorithms significantly outperform traditional single-product pricing policies. Numerical experiments using a real dataset from Alibaba demonstrate that the proposed policies, compared with several benchmark policies, increase the revenue. The results show that online clustering is an effective approach to tackling dynamic pricing problems associated with low-sale products.

stat.ML↗

arXiv2021

Dynamic Pricing on E-commerce Platform with Deep Reinforcement Learning: A Field Experiment

In this paper we present an end-to-end framework for addressing the problem of dynamic pricing (DP) on E-commerce platform using methods based on deep reinforcement learning (DRL). By using four groups of different business data to represent the states of each time period, we model the dynamic pricing problem as a Markov Decision Process (MDP). Compared with the state-of-the-art DRL-based dynamic pricing algorithms, our approaches make the following three contributions. First, we extend the discrete set problem to the continuous price set. Second, instead of using revenue as the reward function directly, we define a new function named difference of revenue conversion rates (DRCR). Third, the cold-start problem of MDP is tackled by pre-training and evaluation using some carefully chosen historical sales data. Our approaches are evaluated by both offline evaluation method using real dataset of Alibaba Inc., and online field experiments starting from July 2018 with thousands of items, lasting for months on Tmall.com. To our knowledge, there is no other DP field experiment using DRL before. Field experiment results suggest that DRCR is a more appropriate reward function than revenue, which is widely used by current literature. Also, continuous price sets have better performance than discrete sets and our approaches significantly outperformed the manual pricing by operation experts.

cs.LG↗