International Conference on Machine Learning最新文献

LinSATNet: The Positive Linear Satisfiability Neural Networks LinSATNet：正线性可满足性神经网络

International Conference on Machine Learning Pub Date : 2024-07-18 DOI: 10.5555/3618408.3619931

Runzhong Wang, Yunhao Zhang, Ziao Guo, Tianyi Chen, Xiaokang Yang, Junchi Yan

引用次数: 5

Stochastic Gradient Succeeds for Bandits 随机梯度成功解决强盗问题

International Conference on Machine Learning Pub Date : 2024-02-27 DOI: 10.48550/arXiv.2402.17235

Jincheng Mei, Zixin Zhong, Bo Dai, Alekh Agarwal, Csaba Szepesvari, D. Schuurmans

{"title":"Stochastic Gradient Succeeds for Bandits","authors":"Jincheng Mei, Zixin Zhong, Bo Dai, Alekh Agarwal, Csaba Szepesvari, D. Schuurmans","doi":"10.48550/arXiv.2402.17235","DOIUrl":"https://doi.org/10.48550/arXiv.2402.17235","url":null,"abstract":"We show that the emph{stochastic gradient} bandit algorithm converges to a emph{globally optimal} policy at an $O(1/t)$ rate, even with a emph{constant} step size. Remarkably, global convergence of the stochastic gradient bandit algorithm has not been previously established, even though it is an old algorithm known to be applicable to bandits. The new result is achieved by establishing two novel technical findings: first, the noise of the stochastic updates in the gradient bandit algorithm satisfies a strong ``growth condition'' property, where the variance diminishes whenever progress becomes small, implying that additional noise control via diminishing step sizes is unnecessary; second, a form of ``weak exploration'' is automatically achieved through the stochastic gradient updates, since they prevent the action probabilities from decaying faster than $O(1/t)$, thus ensuring that every action is sampled infinitely often with probability $1$. These two findings can be used to show that the stochastic gradient update is already ``sufficient'' for bandits in the sense that exploration versus exploitation is automatically balanced in a manner that ensures almost sure convergence to a global optimum. These novel theoretical findings are further verified by experimental results.","PeriodicalId":516931,"journal":{"name":"International Conference on Machine Learning","volume":"81 5","pages":"24325-24360"},"PeriodicalIF":0.0,"publicationDate":"2024-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140427055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep Continuous Networks 深度连续网络

International Conference on Machine Learning Pub Date : 2024-02-02 DOI: 10.48550/arXiv.2402.01557

Nergis Tomen, S. Pintea, J. V. Gemert

{"title":"Deep Continuous Networks","authors":"Nergis Tomen, S. Pintea, J. V. Gemert","doi":"10.48550/arXiv.2402.01557","DOIUrl":"https://doi.org/10.48550/arXiv.2402.01557","url":null,"abstract":"CNNs and computational models of biological vision share some fundamental principles, which opened new avenues of research. However, fruitful cross-field research is hampered by conventional CNN architectures being based on spatially and depthwise discrete representations, which cannot accommodate certain aspects of biological complexity such as continuously varying receptive field sizes and dynamics of neuronal responses. Here we propose deep continuous networks (DCNs), which combine spatially continuous filters, with the continuous depth framework of neural ODEs. This allows us to learn the spatial support of the filters during training, as well as model the continuous evolution of feature maps, linking DCNs closely to biological models. We show that DCNs are versatile and highly applicable to standard image classification and reconstruction problems, where they improve parameter and data efficiency, and allow for meta-parametrization. We illustrate the biological plausibility of the scale distributions learned by DCNs and explore their performance in a neuroscientifically inspired pattern completion task. Finally, we investigate an efficient implementation of DCNs by changing input contrast.","PeriodicalId":516931,"journal":{"name":"International Conference on Machine Learning","volume":"56 3","pages":"10324-10335"},"PeriodicalIF":0.0,"publicationDate":"2024-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139897066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 11

Deep Continuous Networks 深度连续网络

International Conference on Machine Learning Pub Date : 2024-02-02 DOI: 10.48550/arXiv.2402.01557

Nergis Tomen, S. Pintea, J. V. Gemert

{"title":"Deep Continuous Networks","authors":"Nergis Tomen, S. Pintea, J. V. Gemert","doi":"10.48550/arXiv.2402.01557","DOIUrl":"https://doi.org/10.48550/arXiv.2402.01557","url":null,"abstract":"CNNs and computational models of biological vision share some fundamental principles, which opened new avenues of research. However, fruitful cross-field research is hampered by conventional CNN architectures being based on spatially and depthwise discrete representations, which cannot accommodate certain aspects of biological complexity such as continuously varying receptive field sizes and dynamics of neuronal responses. Here we propose deep continuous networks (DCNs), which combine spatially continuous filters, with the continuous depth framework of neural ODEs. This allows us to learn the spatial support of the filters during training, as well as model the continuous evolution of feature maps, linking DCNs closely to biological models. We show that DCNs are versatile and highly applicable to standard image classification and reconstruction problems, where they improve parameter and data efficiency, and allow for meta-parametrization. We illustrate the biological plausibility of the scale distributions learned by DCNs and explore their performance in a neuroscientifically inspired pattern completion task. Finally, we investigate an efficient implementation of DCNs by changing input contrast.","PeriodicalId":516931,"journal":{"name":"International Conference on Machine Learning","volume":"65 5","pages":"10324-10335"},"PeriodicalIF":0.0,"publicationDate":"2024-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139893647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 11

Properties of the Mallows Model Depending on the Number of Alternatives: A Warning for an Experimentalist 马洛斯模型的特性取决于备选方案的数量：给实验者的警告

International Conference on Machine Learning Pub Date : 2024-01-25 DOI: 10.48550/arXiv.2401.14562

Niclas Boehmer, Piotr Faliszewski, Sonja Kraiczy

引用次数: 1