检索结果-内蒙古大学图书馆

Quantum architecture search with meta-learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： He, Zhimin Chen, Chuangtao Li, Lvzhou Zheng, Shenggen Situ, Haozhen School of Electronic and Information Engineering Foshan University Foshan528000 China School of Mechatronic Engineering and Automation Foshan University Foshan528000 China Institute of Quantum Computing and Computer Science Theory School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510006 China Peng Cheng Laboratory Shenzhen518055 China College of Mathematics and Informatics South China Agricultural University Guangzhou510642 China

Variational quantum algorithms (VQAs) have been successfully applied to quantum approximate optimization algorithms, variational quantum compiling and quantum machine learning models. The performances of VQAs largely depend on the architecture of parameterized quantum circuits (PQCs). Quantum architecture search (QAS) aims to automate the design of PQCs in different VQAs with classical optimization algorithms. However, current QAS algorithms do not use prior experiences and search the quantum architecture from scratch for each new task, which is inefficient and time consuming. In this paper, we propose a meta quantum architecture search (MetaQAS) algorithm, which learns good initialization heuristics of the architecture (i.e., meta-architecture), along with the meta-parameters of quantum gates from a number of training tasks such that they can adapt to new tasks with a small number of gradient updates, which leads to fast learning on new tasks. The proposed MetaQAS can be used with arbitrary gradient-based QAS algorithms. Simulation results of variational quantum compiling on three- and four-qubit circuits show that the architectures optimized by MetaQAS converge much faster than a state-of-the-art gradient-based QAS algorithm, namely DQAS. MetaQAS also achieves a better solution than DQAS after fine-tuning of gate parameters. Copyright © 2021, The Authors. All rights reserved.

关键词： learning algorithms

Fine-grained few shot learning with foreground object transformation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Chaofei Song, Shiji Yang, Qisen Li, Xiang Huang, Gao Department of Automation Tsinghua University Beijing China

Traditional fine-grained image classification generally requires abundant labeled samples to deal with the low inter-class variance but high intra-class variance problem. However, in many scenarios we may have limited samples for some novel sub-categories, leading to the fine-grained few shot learning (FG-FSL) setting. To address this challenging task, we propose a novel method named foreground object transformation (FOT), which is composed of a foreground object extractor and a posture transformation generator. The former aims to remove image background, which tends to increase the difficulty of fine-grained image classification as it amplifies the intra-class variance while reduces inter-class variance. The latter transforms the posture of the foreground object to generate additional samples for the novel sub-category. As a data augmentation method, FOT can be conveniently applied to any existing few shot learning algorithm and greatly improve its performance on FG-FSL tasks. In particular, in combination with FOT, simple fine-tuning baseline methods can be competitive with the state-of-the-art methods both in inductive setting and transductive setting. Moreover, FOT can further boost the performances of latest excellent methods and bring them up to the new state-of-the-art. In addition, we also show the effectiveness of FOT on general FSL tasks. © 2021, CC BY.

关键词： learning algorithms

Bayesian meta-learning for few-shot policy adaptation across robotic platforms

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ghadirzadeh, Ali Chen, Xi Poklukar, Petra Finn, Chelsea Björkman, Mårten Kragic, Danica Stanford University United States KTH Royal Institute of Technology Sweden

Reinforcement learning methods can achieve significant performance but require a large amount of training data collected on the same robotic platform. A policy trained with expensive data is rendered useless after making even a minor change to the robot hardware. In this paper, we address the challenging problem of adapting a policy, trained to perform a task, to a novel robotic hardware platform given only few demonstrations of robot motion trajectories on the target robot. We formulate it as a few-shot meta-learning problem where the goal is to find a meta-model that captures the common structure shared across different robotic platforms such that data-efficient adaptation can be performed. We achieve such adaptation by introducing a learning framework consisting of a probabilistic gradient-based meta-learning algorithm that models the uncertainty arising from the few-shot setting with a low-dimensional latent variable. We experimentally evaluate our framework on a simulated reaching and a real-robot picking task using 400 simulated robots generated by varying the physical parameters of an existing set of robotic platforms. Our results show that the proposed method can successfully adapt a trained policy to different robotic platforms with novel physical parameters and the superiority of our meta-learning algorithm compared to state-of-the-art methods for the introduced few-shot policy adaptation problem. Copyright © 2021, The Authors. All rights reserved.

关键词： learning algorithms

Provable Adaptivity of Adam under Non-uniform Smoothness

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Bohan Zhang, Yushun Zhang, Huishuai Meng, Qi Sun, Ruoyu Ma, Zhi-Ming Liu, Tie-Yan Luo, Zhi-Quan Chen, Wei University of Science and Technology of China Microsoft Research Asia Beijing China The Chinese University of Hong Kong Shenzhen Guangdoug Shenzhen China Peking University Beijing China Chinese Academy of Mathematics and Systems Science Beijing China Microsoft Beijing China Institute of Computing Technology Chinese Academy of Sciences Beijing China

Adam is widely adopted in practical applications due to its fast convergence. However, its theoretical analysis is still far from satisfactory. Existing convergence analyses for Adam rely on the bounded smoothness assumption, referred to as the L-smooth condition. Unfortunately, this assumption does not hold for many deep learning tasks. Moreover, we believe that this assumption obscures the true benefit of Adam, as the algorithm can adapt its update magnitude according to local smoothness. This important feature of Adam becomes irrelevant when assuming globally bounded smoothness. This paper studies the convergence of randomly reshuffled Adam (RR Adam) with diminishing learning rate, which is the major version of Adam adopted in deep learning tasks. We present the first convergence analysis of RR Adam without the bounded smoothness assumption. We demonstrate that RR Adam can maintain its convergence properties when smoothness is linearly bounded by the gradient norm, referred to as the (L0, L1)-smooth condition. We further compare Adam to SGD when both methods use diminishing learning rate. We refine the existing lower bound of SGD and show that SGD can be slower than Adam. To our knowledge, this is the first time that Adam and SGD are rigorously compared in the same setting and the advantage of Adam is revealed. © 2022, CC BY.

关键词： learning algorithms

Multiple-Play Stochastic Bandits with Shareable Finite-Capacity Arms

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Xuchuang Xie, Hong Lui, John C. S. Department of Computer Science & Engineering The Chinese University of Hong Kong Hong Kong College of Computer Science Chongqing University China

We generalize the multiple-play multi-armed bandits (MP-MAB) problem with a shareable arm setting, in which several plays can share the same arm. Furthermore, each shareable arm has a finite reward capacity and a "per-load" reward distribution, both of which are unknown to the learner. The reward from a shareable arm is load-dependent, which is the "per-load" reward multiplying either the number of plays pulling the arm, or its reward capacity when the number of plays exceeds the capacity limit. When the "per-load" reward follows a Gaussian distribution, we prove a sample complexity lower bound of learning the capacity from load-dependent rewards and also a regret lower bound of this new MP-MAB problem. We devise a capacity estimator whose sample complexity upper bound matches the lower bound in terms of reward means and capacities. We also propose an online learning algorithm to address the problem and prove its regret upper bound. This regret upper bound's first term is the same as regret lower bound's, and its second and third terms also evidently correspond to lower bound's. Extensive experiments validate our algorithm's performance and also its gain in 5G & 4G base station selection. Copyright © 2022, The Authors. All rights reserved.

关键词： learning algorithms

Robust Attack Graph Generation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Mouwen, Dennis Verwer, Sicco Nadeem, Azqa Delft University of Technology Netherlands

We present a method to learn automaton models that are more robust to input modifications. It iteratively aligns sequences to a learned model, modifies the sequences to their aligned versions, and re-learns the model. Automaton learning algorithms are typically very good at modeling the frequent behavior of a software system. Our solution can be used to also learn the behavior present in infrequent sequences, as these will be aligned to the frequent ones represented by the model. We apply our method to the SAGE tool for modeling attacker behavior from intrusion alerts. In experiments, we demonstrate that our algorithm learns models that can handle noise such as added and removed symbols from sequences. Furthermore, it learns more concise models that fit better to the training data. © 2022, CC BY.

关键词： learning algorithms

Analysis of Intelligent Approaches for Discovery and Management of Knowledge: A Review

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Ahamad, Rayees Mishra, Kamta Nath Department of Computer Science and Engineering India Birla Institute of Technology Mesra India

There are many conventional methods used in the process of Knowledge Discovery & Management (KDM). But, the use of intelligent approaches in this process can further improve the efficiency in the sense of time and accuracy. Intelligent techniques especially soft computing approaches have the ability to learn in any environment with the help of logic, reasoning, and other computing abilities. Intelligent techniques may be categorized as learning algorithms , Logic & Rule-Based algorithms , Nature-inspired algorithms, and hybrid approaches . The main aim of existing intelligent techniques is to solve the day-to-day problems of our rural and smart digital societies. © 2022, The Authors. All rights reserved.

关键词： learning algorithms

Information-theoretic Characterizations of Generalization Error for the Gibbs Algorithm

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Aminian, Gholamali Bu, Yuheng Toni, Laura Rodrigues, Miguel R.D. Wornell, Gregory W. The Alan Turing Institute London United Kingdom The Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02139 United States The Electronic and Electrical Engineering Department University College London United Kingdom

Various approaches have been developed to upper bound the generalization error of a supervised learning algorithm. However, existing bounds are often loose and even vacuous when evaluated in practice. As a result, they may fail to characterize the exact generalization ability of a learning algorithm. Our main contributions are exact characterizations of the expected generalization error of the well-known Gibbs algorithm (a.k.a. Gibbs posterior) using different information measures, in particular, the symmetrized KL information between the input training samples and the output hypothesis. Our result can be applied to tighten existing expected generalization error and PAC-Bayesian bounds. Our information-theoretic approach is versatile, as it also characterizes the generalization error of the Gibbs algorithm with a data-dependent regularizer and that of the Gibbs algorithm in the asymptotic regime, where it converges to the standard empirical risk minimization algorithm. Of particular relevance, our results highlight the role the symmetrized KL information plays in controlling the generalization error of the Gibbs algorithm. Copyright © 2022, The Authors. All rights reserved.

关键词： learning algorithms

BEYOND LABELS: VISUAL REPRESENTATIONS FOR BONE MARROW CELL MORPHOLOGY RECOGNITION

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Fazeli, Shayan Sarrafzadeh, Majid Samiei, Alireza Lee, Thomas D. Department of Computer Science University of California Los Angeles Los AngelesCA90095 United States Department of Pathology and Laboratory Medicine David Geffen School of Medicine University of California Los Angeles Los AngelesCA90095 United States

Analyzing and inspecting bone marrow cell cytomorphology is a critical but highly complex and time-consuming component of hematopathology diagnosis. Recent advancements in artificial intelligence have paved the way for the application of deep learning algorithms to complex medical tasks. Nevertheless, there are many challenges in applying effective learning algorithms to medical image analysis, such as the lack of sufficient and reliably annotated training datasets and the highly class-imbalanced nature of most medical data. Here, we improve on the state-of-the-art methodologies of bone marrow cell recognition by deviating from sole reliance on labeled data and leveraging self-supervision in training our learning models. We investigate our approach’s effectiveness in identifying bone marrow cell types. Our experiments demonstrate significant performance improvements in conducting different bone marrow cell recognition tasks compared to the current state-of-the-art methodologies. Our codes and toolkits are available at https://***/shayanfazeli/marrovision. © 2022, CC BY-NC-SA.

关键词： learning algorithms