In offline reinforcement learning, a policy is learned using a static dataset in the absence of costly feedback from the environment. In contrast to the online setting, only using static datasets poses additional challenges, such as policies generating out-of-distribution samples. Model-based offline reinforcement learning methods try to overcome these by learning a model of the underlying dynamics of the environment and using it to guide policy search. It is beneficial but, with limited datasets, errors in the model and the issue of value overestimation among out-of-distribution states can worsen performance. Current model-based methods apply some notion of conservatism to the Bellman update, often implemented using uncertainty estimation derived from model ensembles. In this paper, we propose Constrained Latent Action Policies (C-LAP) which learns a generative model of the joint distribution of observations and actions. We cast policy learning as a constrained objective to always stay within the support of the latent action distribution, and use the generative capabilities of the model to impose an implicit constraint on the generated actions. Thereby eliminating the need to use additional uncertainty penalties on the Bellman update and significantly decreasing the number of gradient steps required to learn a policy. We empirically evaluate C-LAP on the D4RL and V-D4RL benchmark, and show that C-LAP is competitive to state-of-the-art methods, especially outperforming on datasets with visual observations.
相關內容
This study explores the application of the rate-splitting multiple access (RSMA) technique, vital for interference mitigation in modern communication systems. It investigates the use of precoding methods in RSMA, especially in complex multiple-antenna interference channels, employing deep reinforcement learning. The aim is to optimize precoders and power allocation for common and private data streams involving multiple decision-makers. A multi-agent deep deterministic policy gradient (MADDPG) framework is employed to address this complexity, where decentralized agents collectively learn to optimize actions in a continuous policy space. We also explore the challenges posed by imperfect channel side information at the transmitter. Additionally, decoding order estimation is addressed to determine the optimal decoding sequence for common and private data sequences. Simulation results demonstrate the effectiveness of the proposed RSMA method based on MADDPG, achieving the upper bound in single-antenna scenarios and closely approaching theoretical limits in multi-antenna scenarios. Comparative analysis shows superiority over other techniques such as MADDPG without rate-splitting, maximal ratio transmission (MRT), zero-forcing (ZF), and leakage-based precoding methods. These findings highlight the potential of deep reinforcement learning-driven RSMA in reducing interference and enhancing system performance in communication systems.
Neural combinatorial optimization (NCO) has gained significant attention due to the potential of deep learning to efficiently solve combinatorial optimization problems. NCO has been widely applied to job shop scheduling problems (JSPs) with the current focus predominantly on deterministic problems. In this paper, we propose a novel attention-based scenario processing module (SPM) to extend NCO methods for solving stochastic JSPs. Our approach explicitly incorporates stochastic information by an attention mechanism that captures the embedding of sampled scenarios (i.e., an approximation of stochasticity). Fed with the embedding, the base neural network is intervened by the attended scenarios, which accordingly learns an effective policy under stochasticity. We also propose a training paradigm that works harmoniously with either the expected makespan or Value-at-Risk objective. Results demonstrate that our approach outperforms existing learning and non-learning methods for the flexible JSP problem with stochastic processing times on a variety of instances. In addition, our approach holds significant generalizability to varied numbers of scenarios and disparate distributions.
High-quality datasets are critical for training machine learning models, as inconsistencies in feature generation can hinder the accuracy and reliability of threat detection. For this reason, ensuring the quality of the data in network intrusion detection datasets is important. A key component of this is using reliable tools to generate the flows and features present in the datasets. This paper investigates the impact of flow exporters on the performance and reliability of machine learning models for intrusion detection. Using HERA, a tool designed to export flows and extract features, the raw network packets of two widely used datasets, UNSW-NB15 and CIC-IDS2017, were processed from PCAP files to generate new versions of these datasets. These were compared to the original ones in terms of their influence on the performance of several models, including Random Forest, XGBoost, LightGBM, and Explainable Boosting Machine. The results obtained were significant. Models trained on the HERA version of the datasets consistently outperformed those trained on the original dataset, showing improvements in accuracy and indicating a better generalisation. This highlighted the importance of flow generation in the model's ability to differentiate between benign and malicious traffic.
Safe reinforcement learning (RL) is a popular and versatile paradigm to learn reward-maximizing policies with safety guarantees. Previous works tend to express the safety constraints in an expectation form due to the ease of implementation, but this turns out to be ineffective in maintaining safety constraints with high probability. To this end, we move to the quantile-constrained RL that enables a higher level of safety without any expectation-form approximations. We directly estimate the quantile gradients through sampling and provide the theoretical proofs of convergence. Then a tilted update strategy for quantile gradients is implemented to compensate the asymmetric distributional density, with a direct benefit of return performance. Experiments demonstrate that the proposed model fully meets safety requirements (quantile constraints) while outperforming the state-of-the-art benchmarks with higher return.
Utilising quantum computing technology to enhance artificial intelligence systems is expected to improve training and inference times, increase robustness against noise and adversarial attacks, and reduce the number of parameters without compromising accuracy. However, moving beyond proof-of-concept or simulations to develop practical applications of these systems while ensuring high software quality faces significant challenges due to the limitations of quantum hardware and the underdeveloped knowledge base in software engineering for such systems. In this work, we have conducted a systematic mapping study to identify the challenges and solutions associated with the software architecture of quantum-enhanced artificial intelligence systems. The results of the systematic mapping study reveal several architectural patterns that describe how quantum components can be integrated into inference engines, as well as middleware patterns that facilitate communication between classical and quantum components. Each pattern realises a trade-off between various software quality attributes, such as efficiency, scalability, trainability, simplicity, portability, and deployability. The outcomes of this work have been compiled into a catalogue of architectural patterns.
This study examines the effectiveness of traditional machine learning classifiers versus deep learning models for detecting the imagined speech using electroencephalogram data. Specifically, we evaluated conventional machine learning techniques such as CSP-SVM and LDA-SVM classifiers alongside deep learning architectures such as EEGNet, ShallowConvNet, and DeepConvNet. Machine learning classifiers exhibited significantly lower precision and recall, indicating limited feature extraction capabilities and poor generalization between imagined speech and idle states. In contrast, deep learning models, particularly EEGNet, achieved the highest accuracy of 0.7080 and an F1 score of 0.6718, demonstrating their enhanced ability in automatic feature extraction and representation learning, essential for capturing complex neurophysiological patterns. These findings highlight the limitations of conventional machine learning approaches in brain-computer interface (BCI) applications and advocate for adopting deep learning methodologies to achieve more precise and reliable classification of detecting imagined speech. This foundational research contributes to the development of imagined speech-based BCI systems.
Quadratic programming (QP) forms a crucial foundation in optimization, encompassing a broad spectrum of domains and serving as the basis for more advanced algorithms. Consequently, as the scale and complexity of modern applications continue to grow, the development of efficient and reliable QP algorithms is becoming increasingly vital. In this context, this paper introduces a novel deep learning-aided distributed optimization architecture designed for tackling large-scale QP problems. First, we combine the state-of-the-art Operator Splitting QP (OSQP) method with a consensus approach to derive DistributedQP, a new method tailored for network-structured problems, with convergence guarantees to optimality. Subsequently, we unfold this optimizer into a deep learning framework, leading to DeepDistributedQP, which leverages learned policies to accelerate reaching to desired accuracy within a restricted amount of iterations. Our approach is also theoretically grounded through Probably Approximately Correct (PAC)-Bayes theory, providing generalization bounds on the expected optimality gap for unseen problems. The proposed framework, as well as its centralized version DeepQP, significantly outperform their standard optimization counterparts on a variety of tasks such as randomly generated problems, optimal control, linear regression, transportation networks and others. Notably, DeepDistributedQP demonstrates strong generalization by training on small problems and scaling to solve much larger ones (up to 50K variables and 150K constraints) using the same policy. Moreover, it achieves orders-of-magnitude improvements in wall-clock time compared to OSQP. The certifiable performance guarantees of our approach are also demonstrated, ensuring higher-quality solutions over traditional optimizers.
Federated learning (FL) has been proposed to protect data privacy and virtually assemble the isolated data silos by cooperatively training models among organizations without breaching privacy and security. However, FL faces heterogeneity from various aspects, including data space, statistical, and system heterogeneity. For example, collaborative organizations without conflict of interest often come from different areas and have heterogeneous data from different feature spaces. Participants may also want to train heterogeneous personalized local models due to non-IID and imbalanced data distribution and various resource-constrained devices. Therefore, heterogeneous FL is proposed to address the problem of heterogeneity in FL. In this survey, we comprehensively investigate the domain of heterogeneous FL in terms of data space, statistical, system, and model heterogeneity. We first give an overview of FL, including its definition and categorization. Then, We propose a precise taxonomy of heterogeneous FL settings for each type of heterogeneity according to the problem setting and learning objective. We also investigate the transfer learning methodologies to tackle the heterogeneity in FL. We further present the applications of heterogeneous FL. Finally, we highlight the challenges and opportunities and envision promising future research directions toward new framework design and trustworthy approaches.
Recent contrastive representation learning methods rely on estimating mutual information (MI) between multiple views of an underlying context. E.g., we can derive multiple views of a given image by applying data augmentation, or we can split a sequence into views comprising the past and future of some step in the sequence. Contrastive lower bounds on MI are easy to optimize, but have a strong underestimation bias when estimating large amounts of MI. We propose decomposing the full MI estimation problem into a sum of smaller estimation problems by splitting one of the views into progressively more informed subviews and by applying the chain rule on MI between the decomposed views. This expression contains a sum of unconditional and conditional MI terms, each measuring modest chunks of the total MI, which facilitates approximation via contrastive bounds. To maximize the sum, we formulate a contrastive lower bound on the conditional MI which can be approximated efficiently. We refer to our general approach as Decomposed Estimation of Mutual Information (DEMI). We show that DEMI can capture a larger amount of MI than standard non-decomposed contrastive bounds in a synthetic setting, and learns better representations in a vision domain and for dialogue generation.
Deep learning has yielded state-of-the-art performance on many natural language processing tasks including named entity recognition (NER). However, this typically requires large amounts of labeled data. In this work, we demonstrate that the amount of labeled training data can be drastically reduced when deep learning is combined with active learning. While active learning is sample-efficient, it can be computationally expensive since it requires iterative retraining. To speed this up, we introduce a lightweight architecture for NER, viz., the CNN-CNN-LSTM model consisting of convolutional character and word encoders and a long short term memory (LSTM) tag decoder. The model achieves nearly state-of-the-art performance on standard datasets for the task while being computationally much more efficient than best performing models. We carry out incremental active learning, during the training process, and are able to nearly match state-of-the-art performance with just 25\% of the original training data.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191