检索结果-内蒙古大学图书馆

Finite-time analysis of globally nonstationary multi-armed bandits

学校读者我要写书评

暂无评论

The Journal of Machine Learning Research

The Journal of Machine Learning Research 2024年第1期25卷 5481-5536页

作者： Junpei Komiyama Edouard Fouché Junya Honda Stern School of Business New York University Institute for Program Structures and Data Organization Karlsruhe Institute of Technology Germany Department of Systems Science Graduate School of Informatics Kyoto University Japan Center for Advanced Intelligence Project RIKEN Japan

We consider nonstationary multi-armed bandit problems where the model parameters of the arms change over time. We introduce the adaptive resetting bandit (ADR-bandit), a bandit algorithm class that leverages adaptive windowing techniques from literature on data streams. We first provide new guarantees on the quality of estimators resulting from adaptive windowing techniques, which are of independent interest. Furthermore, we conduct a finite-time analysis of ADR-bandit in two typical environments: an abrupt environment where changes occur instantaneously and a gradual environment where changes occur progressively. We demonstrate that ADR-bandit has nearly optimal performance when abrupt or gradual changes occur in a coordinated manner that we call global changes. We demonstrate that forced exploration is unnecessary when we assume such global changes. Unlike the existing nonstationary bandit algorithms, ADR-bandit has optimal performance in stationary environments as well as nonstationary environments with global changes. Our experiments show that the proposed algorithms outperform the existing approaches in synthetic and real-world environments.

关键词： multi-armed bandits adaptive windows nonstationary bandits changepoint detection sequential learning

Decentralized Federated Graph Learning with Lightweight Zero Trust Architecture for Next-Generation Networking Security

学校读者我要写书评

暂无评论

IEEE Journal on Selected Areas in Communications 2025年第6期43卷 1908-1922页

作者： Zhou, Xiaokang Liang, Wei Wang, Kevin I-Kai Yada, Katsutoshi Yang, Laurence T. Ma, Jianhua Jin, Qun Kansai University Faculty of Business Data Science Osaka565-0823 Japan RIKEN Center for Advanced Intelligence Project RIKEN Tokyo103-0027 Japan Hunan University of Technology and Business School of Computer Science Changsha410205 China Xiangjiang Laboratory Changsha410205 China The University of Auckland Department of Electrical Computer and Software Engineering Auckland1010 New Zealand St. Francis Xavier University Department of Computer Science AntigonishNSB2G 2W5 Canada Hosei University Faculty of Computer and Information Sciences Chiyoda-ku102-8160 Japan Waseda University Faculty of Human Sciences Tokorozawa359-1192 Japan

The rapid development and usage of digital technologies in modern intelligent systems and applications bring critical challenges on data security and privacy. It is essential to allow cross-organizational data sharing to achieve smart service provisioning, while preventing unauthorized access and data leak to ensure end users' efficient and secure collaborations. Federated Learning (FL) offers a promising pathway to enable innovative collaboration across multiple organizations. However, more stringent security policies are needed to ensure authenticity of participating entities, safeguard data during communication, and prevent malicious activities. In this paper, we propose a Decentralized Federated Graph Learning (FGL) with Lightweight Zero Trust Architecture (ZTA) model, named DFGL-LZTA, to provide context-aware security with dynamic defense policy update, while maintaining computational and communication efficiency in resource-constrained environments, for highly distributed and heterogeneous systems in next-generation networking. Specifically, with a re-designed lightweight ZTA, which leverages adaptive privacy preservation and reputation-based aggregation together to tackle multi-level security threats (e.g., data-level, model-level, and identity-level attacks), a Proximal Policy Optimization (PPO) based Deep Reinforcement Learning (DRL) agent is introduced to enable the real-time and adaptive security policy update and optimization based on contextual features. A hierarchical Graph Attention Network (GAT) mechanism is then improved and applied to facilitate the dynamic subgraph learning in local training with a layer-wise architecture, while a so-called sparse global aggregation scheme is developed to balance the communication efficiency and model robustness in a P2P manner. Experiments and evaluations conducted based on two open-source datasets and one synthetic dataset demonstrate the usefulness of our proposed model in terms of training performance, computa

关键词： Federated learning

Functionally Specialized Spectral Organization of the Resting Human Cortex

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Bai, Wenjun Yamashita, Okito Yoshimoto, Junichiro Kyoto Japan Center for Advanced Intelligence Project RIKEN Tokyo Japan Department of Biomedical Data Science School of Medicine Fujita Health University Japan International Center for Brain Science Fujita Health University Aichi Japan

Ample studies across various neuroimaging modalities have suggested that the human cortex at rest is hierarchically organized along the spectral and functional axes. However, the relationship between the spectral and functional organizations of the human cortex remains largely unexplored. Here, we reveal the confluence of functional and spectral cortical organizations by examining the functional specialization in spectral gradients of the cortex. These spectral gradients, derived from functional magnetic resonance imaging data at rest using our temporal de-correlation method to enhance spectral resolution, demonstrate regional frequency biases. The grading of spectral gradients across the cortex – aligns with many existing brain maps – is found to be highly functionally specialized through discovered frequency-specific resting-state functional networks, functionally distinctive spectral profiles, and an intrinsic coordinate system that is functionally specialized. By demonstrating the functionally specialized spec- tral gradients of the cortex, we shed light on the close relation between functional and spectral organizations of the resting human cortex. © 2024, The Authors. All rights reserved.

关键词： Spectrum analysis

Multi-agent statistical discriminative sub-trajectory mining and an application to NBA basketball

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bunker, Rory Duy, Vo Nguyen Le Tabei, Yasuo Takeuchi, Ichiro Fujii, Keisuke Graduate School of Informatics Nagoya University Japan Data-Driven Biomedical Science Team RIKEN Center for Advanced Intelligence Project Japan RIKEN Center for Advanced Intelligence Project Japan Graduate School of Engineering Mechanical Systems Engineering Nagoya University Japan PRESTO Japan Science and Technology Agency Japan

Improvements in tracking technology through optical and computer vision systems have enabled a greater understanding of the movement-based behaviour of multiple agents, including in team sports. In this study, a Multi-Agent Statistically Discriminative Sub-Trajectory Mining (MA-Stat-DSM) method is proposed that takes a set of binary-labelled agent trajectory matrices as input and incorporates Hausdorff distance to identify sub-matrices that statistically significantly discriminate between the two groups of labelled trajectory matrices. Utilizing 2015/16 SportVU NBA tracking data, agent trajectory matrices representing attacks consisting of the trajectories of five agents (the ball, shooter, last passer, shooter defender, and last passer defender), were truncated to correspond to the time interval following the receipt of the ball by the last passer, and labelled as effective or ineffective based on a definition of attack effectiveness that we devise in the current study. After identifying appropriate parameters for MA-Stat-DSM by iteratively applying it to all matches involving the two top- and two bottom-placed teams from the 2015/16 NBA season, the method was then applied to selected matches and could identify and visualize the portions of plays, e.g., involving passing, on-, and/or off-the-ball movements, which were most relevant in rendering attacks effective or ineffective. © 2023, CC BY.

关键词： Geographic information systems

DIRECT DISTRIBUTIONAL OPTIMIZATION FOR PROVABLE ALIGNMENT OF DIFFUSION MODELS

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Kawata, Ryotaro Oko, Kazusato Nitanda, Atsushi Suzuki, Taiji Department of Mathematical Informatics University of Tokyo Japan Center for Advanced Intelligence Project RIKEN Japan Department of ECCS UC Berkeley United States Singapore College of Computing and Data Science Nanyang Technological University Singapore

We introduce a novel alignment method for diffusion models from distribution optimization perspectives while providing rigorous convergence guarantees. We first formulate the problem as a generic regularized loss minimization over probability distributions and directly optimize the distribution using the Dual Averaging method. Next, we enable sampling from the learned distribution by approximating its score function via Doob’s h-transform technique. The proposed framework is supported by rigorous convergence guarantees and an end-to-end bound on the sampling error, which imply that when the original distribution’s score is known accurately, the complexity of sampling from shifted distributions is independent of isoperimetric conditions. This framework is broadly applicable to general distribution optimization problems, including alignment tasks in Reinforcement Learning with Human Feedback (RLHF), Direct Preference Optimization (DPO), and Kahneman-Tversky Optimization (KTO). We empirically validate its performance on synthetic and image datasets using the DPO objective. © 2025, CC BY.

关键词： Probability distributions

Towards multi-dimensional explanation alignment for medical classification 24

学校读者我要写书评

暂无评论

Towards multi-dimensional explanation alignment for medical ...

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Lijie Hu Songning Lai Wenshuo Chen Hongru Xiao Hongbin Lin Lu Yu Jingfeng Zhang Di Wang Provable Responsible AI and Data Analytics (PRADA) Lab and King Abdullah University of Science and Technology Provable Responsible AI and Data Analytics (PRADA) Lab and King Abdullah University of Science and Technology and HKUST(GZ) Tongji University HKUST(GZ) Ant Group The University of Auckland and RIKEN Center for Advanced Intelligence Project (AIP)

ISBN: (纸本)9798331314385

The lack of interpretability in the field of medical image analysis has significant ethical and legal implications. Existing interpretable methods in this domain encounter several challenges, including dependency on specific models, difficulties in understanding and visualization, as well as issues related to efficiency. To address these limitations, we propose a novel framework called Med-MICN (Medical Multidimensional Interpretable Concept Network). Med-MICN provides interpretability alignment for various angles, including neural symbolic reasoning, concept semantics, and saliency maps, which are superior to current interpretable methods. Its advantages include high prediction accuracy, interpretability across multiple dimensions, and automation through an end-to-end concept labeling process that reduces the need for extensive human training effort when working with new datasets. To demonstrate the effectiveness and interpretability of Med-MICN, we apply it to four benchmark datasets and compare it with baselines. The results clearly demonstrate the superior performance and interpretability of our Med-MICN.

关键词：

Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bu, Dake Huang, Wei Han, Andi Nitanda, Atsushi Suzuki, Taiji Zhang, Qingfu Wong, Hau-San Department of Computer Science City University of Hong Kong Hong Kong Center for Advanced Intelligence Project RIKEN Japan Singapore College of Computing and Data Science Nanyang Technological University Singapore Department of Mathematical Informatics The University of Tokyo Japan

Transformer-based large language models (LLMs) have displayed remarkable creative prowess and emergence capabilities. Existing empirical studies have revealed a strong connection between these LLMs' impressive emergence abilities and their in-context learning (ICL) capacity, allowing them to solve new tasks using only task-specific prompts without further fine-tuning. On the other hand, existing empirical and theoretical studies also show that there is a linear regularity of the multi-concept encoded semantic representation behind transformer-based LLMs. However, existing theoretical work fail to build up an understanding of the connection between this regularity and the innovative power of ICL. Additionally, prior work often focuses on simplified, unrealistic scenarios involving linear transformers or unrealistic loss functions, and they achieve only linear or sub-linear convergence rates. In contrast, this work provides a fine-grained mathematical analysis to show how transformers leverage the multi-concept semantics of words to enable powerful ICL and excellent out-of-distribution ICL abilities, offering insights into how transformers innovate solutions for certain unseen tasks encoded with multiple cross-concept semantics. Inspired by empirical studies on the linear latent geometry of LLMs, the analysis is based on a concept-based low-noise sparse coding prompt model. Leveraging advanced techniques, this work showcases the exponential 0-1 loss convergence over the highly non-convex training dynamics, which pioneeringly incorporates the challenges of softmax self-attention, ReLU-activated MLPs, and cross-entropy loss. Empirical simulations corroborate the theoretical findings. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

Integrating Large Language Models in Causal Discovery: A Statistical Causal Approach

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Takayama, Masayuki Okuda, Tadahisa Pham, Thong Ikenoue, Tatsuyoshi Fukuma, Shingo Shimizu, Shohei Sannai, Akiyoshi Data Science and AI Innovation Research Promotion Center Shiga University Japan Department of Health Data Science Tokyo Medical University Graduate School of Medicine Human Health Sciences Kyoto University Japan Faculty of Data Science Shiga University Graduate School of Medicine Human Health Sciences Kyoto University Center for Advanced Intelligence Project RIKEN Japan Faculty of Data Science Shiga University Graduate School of Medicine Human Health Sciences Kyoto University Japan Graduate School of Medicine Human Health Sciences Kyoto University Department of Epidemiology Infectious Disease Control and Prevention Hiroshima University Graduate school of Biomedical and Health Sciences Japan Faculty of Data Science Shiga University Graduate School of Medicine Human Health Sciences Kyoto University Institute for the Advanced Study of Human Biology Kyoto University Center for Advanced Intelligence Project RIKEN Japan Department of Physics Kyoto University Data Science and AI Innovation Research Promotion Center Shiga University Graduate School of Engineering The University of Tokyo Center for Advanced Intelligence Project RIKEN Research Development Center for Large Language Models National Institute of Informatics Japan

In practical statistical causal discovery (SCD), embedding domain expert knowledge as constraints into the algorithm is significant for creating consistent meaningful causal models, despite the challenges in systematic acquisition of the background knowledge. To overcome these challenges, this paper proposes a novel methodology for causal inference, in which SCD methods and knowledge based causal inference (KBCI) with a large language model (LLM) are synthesized through "statistical causal prompting (SCP)" for LLMs and prior knowledge augmentation for SCD. Experiments have revealed that GPT-4 can cause the output of the LLM-KBCI and the SCD result with prior knowledge from LLM-KBCI to approach the ground truth, and that the SCD result can be further improved, if GPT-4 undergoes SCP. Furthermore, by using an unpublished real-world dataset, we have demonstrated that the background knowledge provided by the LLM can improve SCD on this dataset, even if this dataset has never been included in the training data of the LLM. The proposed approach can thus address challenges such as dataset biases and limitations, illustrating the potential of LLMs to improve data-driven causal inference across diverse scientific domains. © 2024, CC BY.

关键词： Computational linguistics

Bayesian Causal Synthesis for Meta-Inference on Heterogeneous Treatment Effects

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Sugasawa, Shonosuke Takanashi, Kōsaku McAlinn, Kenichiro Airoldi, Edoardo M. Faculty of Economics Keio University Japan RIKEN Center for Advanced Intelligence Project Japan Department of Statistics Operations and Data Science Fox School of Business Temple University United States

The estimation of heterogeneous treatment effects in the potential outcome setting is biased when there exists model misspecification or unobserved confounding. As these biases are unobservable, what model to use when remains a critical open question. In this paper, we propose a novel Bayesian methodology to mitigate misspecification and improve estimation via a synthesis of multiple causal estimates, which we call Bayesian causal synthesis. Our development is built upon identifying a synthesis function that correctly specifies the heterogeneous treatment effect under no unobserved confounding, and achieves the irreducible bias under unobserved confounding. We show that our proposed method results in consistent estimates of the heterogeneous treatment effect;either with no bias or with irreducible bias. We provide a computational algorithm for fast posterior sampling. Several benchmark simulations and an empirical study highlight the efficacy of the proposed approach compared to existing methodologies, providing improved point and density estimation of the heterogeneous treatment effect, even under unobserved confounding. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning