同步公众号(arXiv每日论文速递),欢迎关注,感谢支持哦~
cs.LG 方向,今日共计72篇
【1】 Deep Network classification by Scattering and Homotopy dictionary learning
标题:基于散射和同伦字典学习的深层网络分类
作者: John Zarka, Louis Thiry
链接:https://arxiv.org/abs/1910.03561
【2】 Differentially private anonymized histograms
标题:差分私有匿名直方图
作者: Ananda Theertha Suresh
链接:https://arxiv.org/abs/1910.03553
【3】 TorchBeast: A PyTorch Platform for Distributed RL
标题:TorchBeast:一种面向分布式RL的PyTorch平台
作者: Heinrich Küttler, Nantas Nardelli
链接:https://arxiv.org/abs/1910.03552
【4】 Beyond Vector Spaces: Compact Data Representationas Differentiable Weighted Graphs
标题:超越向量空间:紧凑数据表示为可微分加权图
作者: Denis Mazur, Vage Egiazarian
链接:https://arxiv.org/abs/1910.03524
【5】 Self-Paced Multi-Label Learning with Diversity
标题:具有多样性的自定步长多标签学习
作者: Seyed Amjad Seyedi, S.Siamak Ghodsi
链接:https://arxiv.org/abs/1910.03497
【6】 Learning event representations in image sequences by dynamic graph embedding
标题:通过动态图嵌入学习图像序列中的事件表示
作者: Mariella Dimiccoli, Herwig Wendt
链接:https://arxiv.org/abs/1910.03483
【7】 Inferring Dynamical Systems with Long-Range Dependencies through Line Attractor Regularization
标题:用线吸引子正则化推断具有长程依赖的动力系统
作者: Dominik Schmidt, Georgia Koppe
链接:https://arxiv.org/abs/1910.03471
【8】 Directional Adversarial Training for Cost Sensitive Deep Learning Classification Applications
标题:针对成本敏感的深度学习分类应用的定向对抗训练
作者: Matteo Terzi, Gian Antonio Susto
链接:https://arxiv.org/abs/1910.03468
【9】 Can We Distinguish Machine Learning from Human Learning?
标题:我们能区分机器学习和人类学习吗?
作者: Vicki Bier, Paul B. Kantor
链接:https://arxiv.org/abs/1910.03466
【10】 Automatic Construction of Multi-layer Perceptron Network from Streaming Examples
标题:从流实例自动构建多层感知器网络
作者: Mahardhika Pratama, Choiru Za'in
备注:This paper has been accepted for publication in CIKM 2019
链接:https://arxiv.org/abs/1910.03437
【11】 Improved Regret Bounds for Projection-free Bandit Convex Optimization
标题:无投影Bandit凸优化的改进遗憾界
作者: Dan Garber, Ben Kretzu
链接:https://arxiv.org/abs/1910.03374
【12】 Deep Value Model Predictive Control
标题:深值模型预测控制
作者: Farbod Farshidian, David Hoeller
备注:Accepted for publication in the Conference on Robotic Learning (CoRL) 2019, Osaka. 10 pages (+5 supplementary)
链接:https://arxiv.org/abs/1910.03358
【13】 A Machine Learning Model for Long-Term Power Generation Forecasting at Bidding Zone Level
标题:竞价区级长期发电量预测的机器学习模型
作者: Michela Moschella, Mauro Tucci
备注:Paper presented at IEEE PES ISGT 2019 Conference (29 Sept - 2 Oct, Bucharest, Romania)
链接:https://arxiv.org/abs/1910.03276
【14】 Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates
标题:对等损失函数:在不知道噪声率的情况下从噪声标签中学习
作者: Yang Liu, Hongyi Guo
链接:https://arxiv.org/abs/1910.03231
【15】 NGBoost: Natural Gradient Boosting for Probabilistic Prediction
标题:NGBoost:用于概率预测的自然梯度增强
作者: Tony Duan, Anand Avati
链接:https://arxiv.org/abs/1910.03225
【16】 Random forest model identifies serve strength as a key predictor of tennis match outcome
标题:随机森林模型将发球强度确定为网球比赛结果的关键预测因子
作者: Zijian Gao, Amanda Kowalczyk
链接:https://arxiv.org/abs/1910.03203
【17】 Differentiable Sparsification for Deep Neural Networks
标题:深度神经网络的可微分离化
作者: Yognjin Lee
链接:https://arxiv.org/abs/1910.03201
【18】 Accelerating Federated Learning via Momentum Gradient Descent
标题:通过动量梯度下降加速联邦学习
作者: Wei Liu, Li Chen
备注:18 pages, 7 figures
链接:https://arxiv.org/abs/1910.03197
【19】 DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
标题:DeepONet:基于算子的普遍逼近定理学习非线性算子辨识微分方程
作者: Lu Lu, Pengzhan Jin
链接:https://arxiv.org/abs/1910.03193
【20】 Read, Highlight and Summarize: A Hierarchical Neural Semantic Encoder-based Approach
标题:阅读,强调和总结:一种基于分层神经语义编码器的方法
作者: Rajeev Bhatt Ambati, Saptarashmi Bandyopadhyay
备注:Submitted to ICLR 2020
链接:https://arxiv.org/abs/1910.03177
【21】 MIM: Mutual Information Machine
标题:MIM:互信息机器
作者: Micha Livne, Kevin Swersky
链接:https://arxiv.org/abs/1910.03175
【22】 Credible Sample Elicitation by Deep Learning, for Deep Learning
标题:深度学习的可信样本启发,用于深度学习
作者: Yang Liu, Zuyue Fu
链接:https://arxiv.org/abs/1910.03155
【23】 Generating valid Euclidean distance matrices
标题:生成有效的欧几里德距离矩阵
作者: Moritz Hoffmann, Frank Noé
链接:https://arxiv.org/abs/1910.03131
【24】 Evaluating Scalable Uncertainty Estimation Methods for DNN-Based Molecular Property Prediction
标题:基于DNN的分子性质预测中可扩展不确定度估计方法的评价
作者: Gabriele Scalia, Colin A. Grambow
链接:https://arxiv.org/abs/1910.03127
【25】 Energy-Aware Neural Architecture Optimization with Fast Splitting Steepest Descent
标题:快速分裂最陡下降的能量感知神经结构优化
作者: Dilin Wang, Meng Li
链接:https://arxiv.org/abs/1910.03103
【26】 Combining No-regret and Q-learning
标题:结合无悔和Q学习
作者: Ian A. Kash, Michael Sullins
链接:https://arxiv.org/abs/1910.03094
【27】 On the Interpretability and Evaluation of Graph Representation Learning
标题:论图形表征学习的可解释性与评价
作者: Antonia Gogoglou, C. Bayan Bruss
备注:NeurIPS 2019 Graph Representation Learning workshop
链接:https://arxiv.org/abs/1910.03081
【28】 Sequence embeddings help to identify fraudulent cases in healthcare insurance
标题:序列嵌入有助于识别医疗保险中的欺诈案例
作者: I. Fursov, A. Zaytsev
链接:https://arxiv.org/abs/1910.03072
【29】 Kernel-based Approach to Handle Mixed Data for Inferring Causal Graphs
标题:基于核的处理混合数据以推断因果图的方法
作者: Teny Handhayani, James Cussens
链接:https://arxiv.org/abs/1910.03055
【30】 Graph Few-shot Learning via Knowledge Transfer
标题:通过知识转移实现图形少发学习
作者: Huaxiu Yao, Chuxu Zhang
备注:Accepted by NeurIPS 2019 GRL workshop
链接:https://arxiv.org/abs/1910.03053
【31】 Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?
标题:对于样本有效的强化学习来说,良好的表示是否足够?
作者: Simon S. Du, Sham M. Kakade
链接:https://arxiv.org/abs/1910.03016
【32】 Stochastic Optimal Control as Approximate Input Inference
标题:近似输入推理的随机最优控制
作者: Joe Watson, Hany Abdulsamad
备注:Conference on Robot Learning (CoRL 2019)
链接:https://arxiv.org/abs/1910.03003
【33】 High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processes
标题:低秩高斯Copula过程的高维多变量预测
作者: David Salinas, Michael Bohlke-Schneider
链接:https://arxiv.org/abs/1910.03002
【34】 When Does Self-supervision Improve Few-shot Learning?
标题:自我监督何时能改善少发学习?
作者: Jong-Chyi Su, Subhransu Maji
备注:This is an updated version of "Boosting Supervision with Self-Supervision for Few-shot Learning" arXiv:1906.07079
链接:https://arxiv.org/abs/1910.03560
【35】 Towards Controllable and Personalized Review Generation
标题:走向可控和个性化的评论生成
作者: Pan Li, Alexander Tuzhilin
备注:Accepted to EMNLP 2019
链接:https://arxiv.org/abs/1910.03506
【36】 Investigating the Effectiveness of Word-Embedding Based Active Learning for Labelling Text Datasets
标题:基于单词嵌入的主动学习用于标注文本数据集的有效性研究
作者: Jinghui Lu, Maeve Henchion
链接:https://arxiv.org/abs/1910.03505
【37】 SentiCite: An Approach for Publication Sentiment Analysis
标题:SentiCite:一种出版物情感分析方法
作者: Dominique Mercier, Akansha Bhardwaj
链接:https://arxiv.org/abs/1910.03498
【38】 A Rademacher Complexity Based Method fo rControlling Power and Confidence Level in Adaptive Statistical Analysis
标题:一种基于Rademacher复杂度的自适应统计分析中控制力和置信水平的方法
作者: Lorenzo De Stefani, Eli Upfal
链接:https://arxiv.org/abs/1910.03493
【39】 Neural Language Priors
标题:神经语言优先
作者: Joseph Enguehard, Dan Busbridge
链接:https://arxiv.org/abs/1910.03492
【40】 Controlled Text Generation for Data Augmentation in Intelligent Artificial Agents
标题:智能人工代理中用于数据增强的受控文本生成
作者: Nikolaos Malandrakis, Minmin Shen
链接:https://arxiv.org/abs/1910.03487
【41】 Learning Parametric Constraints in High Dimensions from Demonstrations
标题:从演示中学习高维参数约束
作者: Glen Chou, Necmiye Ozay
备注:3rd Conference on Robot Learning (CoRL 2019)
链接:https://arxiv.org/abs/1910.03477
【42】 Classification As Decoder: Trading Flexibility For Control In Neural Dialogue
标题:分类为解码器:神经对话中控制的交易灵活性
作者: Sam Shleifer, Manish Chablani
链接:https://arxiv.org/abs/1910.03476
【43】 Fine-grained Sentiment Classification using BERT
标题:基于BERT的细粒度情感分类
作者: Manish Munikar, Sushil Shakya
链接:https://arxiv.org/abs/1910.03474
【44】 Lossy Image Compression with Recurrent Neural Networks: from Human Perceived Visual Quality to Classification Accuracy
标题:基于递归神经网络的有损图像压缩:从人类感知的视觉质量到分类精度
作者: Maurice Weber, Cedric Renggli
链接:https://arxiv.org/abs/1910.03472
【45】 Overcoming the Rare Word Problem for Low-Resource Language Pairs in Neural Machine Translation
标题:克服神经网络机器翻译中低资源语言对的稀有单词问题
作者: Thi-Vinh Ngo, Thanh-Le Ha
链接:https://arxiv.org/abs/1910.03467
【46】 TraffickCam: Explainable Image Matching For Sex Trafficking Investigations
标题:TraffickCam:用于性交易调查的可解释图像匹配
作者: Abby Stylianou, Richard Souvenir
备注:Presented at AAAI FSS-19: Artificial Intelligence in Government and Public Sector, Arlington, Virginia, USA
链接:https://arxiv.org/abs/1910.03455
【47】 Implicit Neural Solver for Time-dependent Linear PDEs with Convergence Guarantee
标题:具有收敛性保证的含时线性偏微分方程的隐式神经网络求解器
作者: Suprosanna Shit, Abinav Ravi
备注:Accepted in NeurIPS 2019 Workshop on Machine Learning with Guarantees
链接:https://arxiv.org/abs/1910.03452
【48】 Federated Learning of N-gram Language Models
标题:N-gram语言模型的联合学习
作者: Mingqing Chen, Ananda Theertha Suresh
链接:https://arxiv.org/abs/1910.03432
【49】 Toward Synergic Learning for Autonomous Manipulation of Deformable Tissues via Surgical Robots: An Approximate Q-Learning Approach
标题:通过手术机器人自主操纵可变形组织的协同学习:一种近似Q学习方法
作者: Sahba Aghajani Pedram, Peter Walker Ferguson
链接:https://arxiv.org/abs/1910.03398
【50】 When Specialization Helps: Using Pooled Contextualized Embeddings to Detect Chemical and Biomedical Entities in Spanish
标题:专业化认证有帮助时:使用池化上下文嵌入检测西班牙语中的化学和生物医学实体
作者: Manuel Stoeckel, Wahed Hemati
备注:EMNLP-IJCNLP 2019: International Workshop on BioNLP Open Shared Tasks 2019, 5, pages, 1 figure
链接:https://arxiv.org/abs/1910.03387
【51】 Universal Approximation Theorems
标题:普适逼近定理
作者: Anastasis Kratsios
链接:https://arxiv.org/abs/1910.03344
【52】 Improving Map Re-localization with Deep 'Movable' Objects Segmentation on 3D LiDAR Point Clouds
标题:在3DLiDAR点云上利用深度“可移动”对象分割改进地图重新定位
作者: Victor Vaquero, Kai Fischer
链接:https://arxiv.org/abs/1910.03336
【53】 Computational complexity in algebraic regression
标题:代数回归中的计算复杂性
作者: Oliver Gäfvert
链接:https://arxiv.org/abs/1910.03305
【54】 Aligning Multilingual Word Embeddings for Cross-Modal Retrieval Task
标题:跨模态检索任务的多语种单词嵌入对齐
作者: Alireza Mohammadshahi, Remi Lebret
链接:https://arxiv.org/abs/1910.03291
【55】 Motion Generation Considering Situation with Conditional Generative Adversarial Networks for Throwing Robots
标题:基于条件生成对抗网络的投掷机器人考虑情境的运动生成
作者: Kyo Kutsuzawa, Hitoshi Kusano
链接:https://arxiv.org/abs/1910.03253
【56】 Voice for the Voiceless: Active Sampling to Detect Comments Supporting the Rohingyas
标题:无声之声:主动取样以检测支持罗辛亚人的评论
作者: Shriphani Palakodety, Ashiqur R. KhudaBukhsh
链接:https://arxiv.org/abs/1910.03206
【57】 An Information-theoretic Approach to Unsupervised Feature Selection for High-Dimensional Data
标题:高维数据无监督特征选择的信息论方法
作者: Shao-Lun Huang, Xiangxiang Xu
链接:https://arxiv.org/abs/1910.03196
【58】 Lung nodule segmentation via level set machine learning
标题:基于水平集机器学习的肺结节分割
作者: Matthew C Hancock, Jerry F Magnan
链接:https://arxiv.org/abs/1910.03191
【59】 SesameBERT: Attention for Anywhere
标题:SesameBERT:随时随地的注意
作者: Ta-Chun Su, Hsiang-Chih Cheng
链接:https://arxiv.org/abs/1910.03176
【60】 xYOLO: A Model For Real-Time Object Detection In Humanoid Soccer On Low-End Hardware
标题:xYOLO:一种基于低端硬件的仿人足球实时目标检测模型
作者: Daniel Barry, Munir Shah
链接:https://arxiv.org/abs/1910.03159
【61】 On Polyhedral and Second-Order-Cone Decompositions of Semidefinite Optimization Problems
标题:关于半定优化问题的多面体和二阶锥分解
作者: Dimitris Bertsimas, Ryan Cory-Wright
链接:https://arxiv.org/abs/1910.03143
【62】 DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System
标题:DexPilot:基于视觉的灵巧机器人手臂系统遥操作
作者: Ankur Handa, Karl Van Wyk
链接:https://arxiv.org/abs/1910.03135
【63】 Generalization of machine-learned turbulent heat flux models applied to film cooling flows
标题:用于气膜冷却流动的机器学习湍流热流模型的推广
作者: Pedro M. Milani, Julia Ling
备注:Presented at ASME Turbo Expo 2019, accepted to the Journal of Turbomachinery
链接:https://arxiv.org/abs/1910.03097
【64】 INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Maps
标题:交互数据集:具有语义地图的交互式驾驶场景中的国际性、对抗性和合作性运动数据集
作者: Wei Zhan, Liting Sun
链接:https://arxiv.org/abs/1910.03088
【65】 Correlation of Auroral Dynamics and GNSS Scintillation with an Autoencoder
标题:利用自动编码器进行极光动力学和GNSS闪烁的相关性
作者: Kara Lamb, Garima Malhotra
备注:Four first authors contributed equally; Paper accepted in Machine Learning for the Physical Sciences workshop of NeurIPS 2019; Camera Ready Version to Follow
链接:https://arxiv.org/abs/1910.03085
【66】 CeliacNet: Celiac Disease Severity Diagnosis on Duodenal Histopathological Images Using Deep Residual Networks
标题:CeliacNet:使用深层残差网络的十二指肠组织病理学图像上的腹腔疾病严重程度诊断
作者: Rasoul Sali, Lubaina Ehsan
备注:accepted at IEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM 2019)
链接:https://arxiv.org/abs/1910.03084
【67】 Decentralized Multi-Agent Actor-Critic with Generative Inference
标题:具有生成性推理的分散式多智能体演员-批评者
作者: Kevin Corder, Manuel M. Vindiola
备注:8 pages. Accepted to Deep Reinforcement Learning Workshop at NeurIPS 2019
链接:https://arxiv.org/abs/1910.03058
【68】 Synthesizing Credit Card Transactions
标题:合成信用卡交易
作者: Erik R. Altman
链接:https://arxiv.org/abs/1910.03033
【69】 Bregman-divergence-guided Legendre exponential dispersion model with finite cumulants (K-LED)
标题:Bregman-发散引导的有限累积量Legendre指数色散模型(K-LED)
作者: Hyenkyun Woo
链接:https://arxiv.org/abs/1910.03025
【70】 Mental Task Classification Using Electroencephalogram Signal
标题:基于脑电信号的心理任务分类
作者: Zeyu Bai, Ruizhi Yang
链接:https://arxiv.org/abs/1910.03023
【71】 Flood Detection On Low Cost Orbital Hardware
标题:基于低成本轨道硬件的洪水检测
作者: Gonzalo Mateo-Garcia, Silviu Oprea
链接:https://arxiv.org/abs/1910.03019
【72】 Joint analysis of clinical risk factors and 4D cardiac motion for survival prediction using a hybrid deep learning network
标题:使用混合深度学习网络对临床危险因素和4D心脏运动进行生存预测的联合分析
作者: Shihao Jin, Nicolò Savioli
链接:https://arxiv.org/abs/1910.02951
机器翻译,仅供参考
网友评论