arXiv subjects

Yijia Wang

Publications and source records attributed to Yijia Wang.

At least 37 records · Page 2Linked to original sources

arXiv2025

Generative Decoding for Quantum Error-correcting Codes

Efficient and accurate decoding of quantum error-correcting codes is essential for fault-tolerant quantum computation, however, it is challenging due to the degeneracy of errors, the complex code topology, and the large space for logical operators in high-rate codes. In this work, we propose a decoding algorithm utilizing generative modeling in machine learning. We employ autoregressive neural networks to learn the joint probability of logical operators and syndromes in an unsupervised manner, eliminating the need for labeled training data. The learned model can approximately perform maximum likelihood decoding by directly generating the most likely logical operators for $k$ logical qubits with $\mathcal O(2k)$ computational complexity. Thus, it is particularly efficient for decoding high-rate codes with many logical qubits. The proposed approach is general and applies to a wide spectrum of quantum error-correcting codes including surface codes and quantum low-density parity-check codes (qLDPC), under noise models ranging from code capacity noise to circuit level noise. We conducted extensive numerical experiments to demonstrate that our approach achieves significantly higher decoding accuracy compared to the minimum weight perfect matching and belief propagation with ordered statistics on the surface codes and high-rate quantum low-density parity-check codes. Our approach highlights generative artificial intelligence as a potential solution for the real-time decoding of realistic and high-rate quantum error correction codes.

quant-ph↗

arXiv2024

A multi-source data power load forecasting method using attention mechanism-based parallel cnn-gru

Accurate power load forecasting is crucial for improving energy efficiency and ensuring power supply quality. Considering the power load forecasting problem involves not only dynamic factors like historical load variations but also static factors such as climate conditions that remain constant over specific periods. From the model-agnostic perspective, this paper proposes a parallel structure network to extract important information from both dynamic and static data. Firstly, based on complexity learning theory, it is demonstrated that models integrated through parallel structures exhibit superior generalization abilities compared to individual base learners. Additionally, the higher the independence between base learners, the stronger the generalization ability of the parallel structure model. This suggests that the structure of machine learning models inherently contains significant information. Building on this theoretical foundation, a parallel convolutional neural network (CNN)-gate recurrent unit (GRU) attention model (PCGA) is employed to address the power load forecasting issue, aiming to effectively integrate the influences of dynamic and static features. The CNN module is responsible for capturing spatial characteristics from static data, while the GRU module captures long-term dependencies in dynamic time series data. The attention layer is designed to focus on key information from the spatial-temporal features extracted by the parallel CNN-GRU. To substantiate the advantages of the parallel structure model in extracting and integrating multi-source information, a series of experiments are conducted.

cs.LG↗

arXiv2024

Regularized Contrastive Partial Multi-view Outlier Detection

In recent years, multi-view outlier detection (MVOD) methods have advanced significantly, aiming to identify outliers within multi-view datasets. A key point is to better detect class outliers and class-attribute outliers, which only exist in multi-view data. However, existing methods either is not able to reduce the impact of outliers when learning view-consistent information, or struggle in cases with varying neighborhood structures. Moreover, most of them do not apply to partial multi-view data in real-world scenarios. To overcome these drawbacks, we propose a novel method named Regularized Contrastive Partial Multi-view Outlier Detection (RCPMOD). In this framework, we utilize contrastive learning to learn view-consistent information and distinguish outliers by the degree of consistency. Specifically, we propose (1) An outlier-aware contrastive loss with a potential outlier memory bank to eliminate their bias motivated by a theoretical analysis. (2) A neighbor alignment contrastive loss to capture the view-shared local structural correlation. (3) A spreading regularization loss to prevent the model from overfitting over outliers. With the Cross-view Relation Transfer technique, we could easily impute the missing view samples based on the features of neighbors. Experimental results on four benchmark datasets demonstrate that our proposed approach could outperform state-of-the-art competitors under different settings.

cs.MM↗

arXiv2024

Kawaii Computing: Scoping Out the Japanese Notion of Cute in User Experiences with Interactive Systems

Kawaii computing is a new term for a steadily growing body of work on the Japanese notion of "cute" in human-computer interaction (HCI) research and practice. Kawaii is distinguished from general notions of cute by its experiential and culturally-sensitive nature. While it can be designed into the appearance and behaviour of interactive agents, interfaces, and systems, kawaii also refers to certain affective and cultural dimensions experienced by culturally Japanese users, i.e., kawaii user experiences (UX) and mental models of kawaii elicited by the socio-cultural context of Japan. In this scoping review, we map out the ways in which kawaii has been explored within HCI research and related fields as a factor of design and experience. We illuminate theoretical and methodological gaps and opportunities for future work on kawaii computing.

cs.HC↗

arXiv2024

Deceptive, Disruptive, No Big Deal: Japanese People React to Simulated Dark Commercial Patterns

Dark patterns and deceptive designs (DPs) are user interface elements that trick people into taking actions that benefit the purveyor. Such designs are widely deployed, with special varieties found in certain nations like Japan that can be traced to global power hierarchies and the local socio-linguistic context of use. In this breaking work, we report on the first user study involving Japanese people (n=30) experiencing a mock shopping website injected with simulated DPs. We found that Alphabet Soup and Misleading Reference Pricing were the most deceptive and least noticeable. Social Proofs, Sneaking in Items, and Untranslation were the least deceptive but Untranslation prevented most from cancelling their account. Mood significantly worsened after experiencing the website. We contribute the first empirical findings on a Japanese consumer base alongside a scalable approach to evaluating user attitudes, perceptions, and behaviours towards DPs in an interactive context. We urge for more human participant research and ideally collaborations with industry to assess real designs in the wild.

cs.HC↗

arXiv2024

Towards Generalized Inverse Reinforcement Learning

This paper studies generalized inverse reinforcement learning (GIRL) in Markov decision processes (MDPs), that is, the problem of learning the basic components of an MDP given observed behavior (policy) that might not be optimal. These components include not only the reward function and transition probability matrices, but also the action space and state space that are not exactly known but are known to belong to given uncertainty sets. We address two key challenges in GIRL: first, the need to quantify the discrepancy between the observed policy and the underlying optimal policy; second, the difficulty of mathematically characterizing the underlying optimal policy when the basic components of an MDP are unobservable or partially observable. Then, we propose the mathematical formulation for GIRL and develop a fast heuristic algorithm. Numerical results on both finite and infinite state problems show the merit of our formulation and algorithm.

cs.LG↗

arXiv2023

Data-Centric Financial Large Language Models

Large language models (LLMs) show promise for natural language tasks but struggle when applied directly to complex domains like finance. LLMs have difficulty reasoning about and integrating all relevant information. We propose a data-centric approach to enable LLMs to better handle financial tasks. Our key insight is that rather than overloading the LLM with everything at once, it is more effective to preprocess and pre-understand the data. We create a financial LLM (FLLM) using multitask prompt-based finetuning to achieve data pre-processing and pre-understanding. However, labeled data is scarce for each task. To overcome manual annotation costs, we employ abductive augmentation reasoning (AAR) to automatically generate training data by modifying the pseudo labels from FLLM's own outputs. Experiments show our data-centric FLLM with AAR substantially outperforms baseline financial LLMs designed for raw text, achieving state-of-the-art on financial analysis and interpretation tasks. We also open source a new benchmark for financial analysis and interpretation. Our methodology provides a promising path to unlock LLMs' potential for complex real-world domains.

cs.CL↗

arXiv2023

Calico Salmon Migration Algorithm: A novel meta-heuristic optimization algorithm

A novel population-based optimization method is proposed in this paper, the Calico Salmon Migration Algorithm (CSMA), which is inspired by the natural behavior of calico salmon during their migration for mating. The CSMA optimization process comprises four stages: selecting the search space by swimming into the river, expanding the search space from the river into the ocean, performing precise search during the migrating process, and breeding new subspecies by the remaining calico salmon population. To evaluate the effectiveness of the new optimizer, we conducted a series of experiments using different optimization problems and compared the results with various optimization algorithms in the literature. The numerical experimental results for benchmark functions demonstrate that the proposed CSMA outperforms other competing optimization algorithms in terms of convergence speed, accuracy, and stability. Furthermore, the Friedman ranking test shows that the CSMA is ranked first among similar algorithms.

math.OC↗

arXiv2023

Dynamic Subgoal-based Exploration via Bayesian Optimization

Reinforcement learning in sparse-reward navigation environments with expensive and limited interactions is challenging and poses a need for effective exploration. Motivated by complex navigation tasks that require real-world training (when cheap simulators are not available), we consider an agent that faces an unknown distribution of environments and must decide on an exploration strategy. It may leverage a series of training environments to improve its policy before it is evaluated in a test environment drawn from the same environment distribution. Most existing approaches focus on fixed exploration strategies, while the few that view exploration as a meta-optimization problem tend to ignore the need for cost-efficient exploration. We propose a cost-aware Bayesian optimization approach that efficiently searches over a class of dynamic subgoal-based exploration strategies. The algorithm adjusts a variety of levers -- the locations of the subgoals, the length of each episode, and the number of replications per trial -- in order to overcome the challenges of sparse rewards, expensive interactions, and noise. An experimental evaluation demonstrates that the new approach outperforms existing baselines across a number of problem domains. We also provide a theoretical foundation and prove that the method asymptotically identifies a near-optimal subgoal design.

math.OC↗

arXiv2023

qecGPT: decoding Quantum Error-correcting Codes with Generative Pre-trained Transformers

We propose a general framework for decoding quantum error-correcting codes with generative modeling. The model utilizes autoregressive neural networks, specifically Transformers, to learn the joint probability of logical operators and syndromes. This training is in an unsupervised way, without the need for labeled training data, and is thus referred to as pre-training. After the pre-training, the model can efficiently compute the likelihood of logical operators for any given syndrome, using maximum likelihood decoding. It can directly generate the most-likely logical operators with computational complexity $\mathcal O(2k)$ in the number of logical qubits $k$, which is significantly better than the conventional maximum likelihood decoding algorithms that require $\mathcal O(4^k)$ computation. Based on the pre-trained model, we further propose refinement to achieve more accurately the likelihood of logical operators for a given syndrome by directly sampling the stabilizer operators. We perform numerical experiments on stabilizer codes with small code distances, using both depolarizing error models and error models with correlated noise. The results show that our approach provides significantly better decoding accuracy than the minimum weight perfect matching and belief-propagation-based algorithms. Our framework is general and can be applied to any error model and quantum codes with different topologies such as surface codes and quantum LDPC codes. Furthermore, it leverages the parallelization capabilities of GPUs, enabling simultaneous decoding of a large number of syndromes. Our approach sheds light on the efficient and accurate decoding of quantum error-correcting codes using generative artificial intelligence and modern computational power.

quant-ph↗

arXiv2023

Tensor Network Message Passing

When studying interacting systems, computing their statistical properties is a fundamental problem in various fields such as physics, applied mathematics, and machine learning. However, this task can be quite challenging due to the exponential growth of the state space as the system size increases. Many standard methods have significant weaknesses. For instance, message-passing algorithms can be inaccurate and even fail to converge due to short loops. At the same time, tensor network methods can have exponential computational complexity in large graphs due to long loops. This work proposes a new method called ``tensor network message passing.'' This approach allows us to compute local observables like marginal probabilities and correlations by combining the strengths of tensor networks in contracting small sub-graphs with many short loops and the strengths of message-passing methods in globally sparse graphs, thus addressing the crucial weaknesses of both approaches. Our algorithm is exact for systems that are globally tree-like and locally dense-connected when the dense local graphs have limited treewidth. We have conducted numerical experiments on synthetic and real-world graphs to compute magnetizations of Ising models and spin glasses, to demonstrate the superiority of our approach over standard belief propagation and the recently proposed loopy message-passing algorithm. In addition, we discuss the potential applications of our method in inference problems in networks, combinatorial optimization problems, and decoding problems in quantum error correction.

cond-mat.stat-mech↗

arXiv2023

Prediction of single well production rate in water-flooding oil fields driven by the fusion of static, temporal and spatial information

It is very difficult to forecast the production rate of oil wells as the output of a single well is sensitive to various uncertain factors, which implicitly or explicitly show the influence of the static, temporal and spatial properties on the oil well production. In this study, a novel machine learning model is constructed to fuse the static geological information, dynamic well production history, and spatial information of the adjacent water injection wells. There are 3 basic modules in this stacking model, which are regarded as the encoders to extract the features from different types of data. One is Multi-Layer Perceptron, which is to analyze the static geological properties of the reservoir that might influence the well production rate. The other two are both LSTMs, which have the input in the form of two matrices rather than vectors, standing for the temporal and the spatial information of the target well. The difference of the two modules is that in the spatial information processing module we take into consideration the time delay of water flooding response, from the injection well to the target well. In addition, we use Symbolic Transfer Entropy to prove the superiorities of the stacking model from the perspective of Causality Discovery. It is proved theoretically and practically that the presented model can make full use of the model structure to integrate the characteristics of the data and the experts' knowledge into the process of machine learning, greatly improving the accuracy and generalization ability of prediction.

cs.LG↗

arXiv2022

Inverse Multiobjective Optimization Through Online Learning

We study the problem of learning the objective functions or constraints of a multiobjective decision making model, based on a set of sequentially arrived decisions. In particular, these decisions might not be exact and possibly carry measurement noise or are generated with the bounded rationality of decision makers. In this paper, we propose a general online learning framework to deal with this learning problem using inverse multiobjective optimization. More precisely, we develop two online learning algorithms with implicit update rules which can handle noisy data. Numerical results show that both algorithms can learn the parameters with great accuracy and are robust to noise.

cs.LG↗

arXiv2022

Eigen mode selection in human subject game experiment

Eigen mode selection ought to be a practical issue in some real game systems, as it is a practical issue in the dynamics behaviour of a building, bridge, or molecular, because of the mathematical similarity in theory. However, its reality and accuracy have not been known in real games. We design a 5-strategy game which, in the replicator dynamics theory, is predicted to exist two eigen modes. Further, in behaviour game theory, the game is predicted that the mode selection should depends on the game parameter. We conduct human subject game experiments by controlling the parameter. The data confirm that, the predictions on the mode existence as well as the mode selection are significantly supported. This finding suggests that, like the equilibrium selection concept in classical game theory, eigen mode selection is an issue in game dynamics theory.

econ.TH↗

arXiv2022

Dynamic Structure in Four-strategy Game: Theory and Experiment

Game dynamics theory, as a field of science, the consistency of theory and experiment is essential. In the past 10 years, important progress has been made in the merging of the theory and experiment in this field, in which dynamics cycle is the presentation. However, the merging works have not got rid of the constraints of Euclidean two-dimensional cycle so far. This paper uses a classic four-strategy game to study the dynamic structure (non-Euclidean superplane cycle). The consistency is in significant between the three ways: (1) the analytical results from evolutionary dynamics equations, (2) agent-based simulation results from learning models and (3) laboratory results from human subjects game experiments. The consistency suggests that, game dynamic structure could be quantitatively predictable, observable and controllable in general.

econ.TH↗

arXiv2021

Structured Actor-Critic for Managing Public Health Points-of-Dispensing

Public health organizations face the problem of dispensing treatments (i.e., vaccines, antibiotics, and others) to groups of affected populations through "points-of-dispensing" (PODs) during emergency situations, typically in the presence of complexities like demand stochasticity, heterogenous utilities (e.g., for vaccine distribution, certain segments of the population may need to be prioritized), and limited storage. We formulate a hierarchical Markov decision process (MDP) model with two levels of decisions (and decision-makers): the upper-level decisions come from an inventory planner that "controls" a lower-level dynamic problem, which optimizes dispensing decisions that take into consideration the heterogeneous utility functions of the random set of PODs. We then derive structural properties of the MDP model and propose an approximate dynamic programming (ADP) algorithm that leverages structure in both the policy and the value space (state-dependent basestocks and concavity, respectively). The algorithm can be considered an actor-critic method; to our knowledge, this paper is the first to jointly exploit policy and value structure within an actor-critic framework. We prove that the policy and value function approximations each converge to their optimal counterparts with probability one and provide a comprehensive numerical analysis showing improved empirical convergence rates when compared to other ADP techniques. Finally, we show how an aggregation-based version of our algorithm can be applied in a realistic case study for the problem of dispensing naloxone (an overdose reversal drug) via first responders amidst the ongoing opioid crisis.

math.OC↗

arXiv2021

One Backward from Ten Forward, Subsampling for Large-Scale Deep Learning

Deep learning models in large-scale machine learning systems are often continuously trained with enormous data from production environments. The sheer volume of streaming training data poses a significant challenge to real-time training subsystems and ad-hoc sampling is the standard practice. Our key insight is that these deployed ML systems continuously perform forward passes on data instances during inference, but ad-hoc sampling does not take advantage of this substantial computational effort. Therefore, we propose to record a constant amount of information per instance from these forward passes. The extra information measurably improves the selection of which data instances should participate in forward and backward passes. A novel optimization framework is proposed to analyze this problem and we provide an efficient approximation algorithm under the framework of Mini-batch gradient descent as a practical solution. We also demonstrate the effectiveness of our framework and algorithm on several large-scale classification and regression tasks, when compared with competitive baselines widely used in industry.

cs.LG↗

arXiv2017

Using experimental game theory to transit human values to ethical AI

Knowing the reflection of game theory and ethics, we develop a mathematical representation to bridge the gap between the concepts in moral philosophy (e.g., Kantian and Utilitarian) and AI ethics industry technology standard (e.g., IEEE P7000 standard series for Ethical AI). As an application, we demonstrate how human value can be obtained from the experimental game theory (e.g., trust game experiment) so as to build an ethical AI. Moreover, an approach to test the ethics (rightness or wrongness) of a given AI algorithm by using an iterated Prisoner's Dilemma Game experiment is discussed as an example. Compared with existing mathematical frameworks and testing method on AI ethics technology, the advantages of the proposed approach are analyzed.

cs.AI↗