Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning最新文献_第8页

Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources 可证明的基于扰动数据源的高效离线强化学习

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-06-14 DOI: 10.48550/arXiv.2306.08364

Chengshuai Shi, Wei Xiong, Cong Shen, Jing Yang

{"title":"Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources","authors":"Chengshuai Shi, Wei Xiong, Cong Shen, Jing Yang","doi":"10.48550/arXiv.2306.08364","DOIUrl":"https://doi.org/10.48550/arXiv.2306.08364","url":null,"abstract":"Existing theoretical studies on offline reinforcement learning (RL) mostly consider a dataset sampled directly from the target task. In practice, however, data often come from several heterogeneous but related sources. Motivated by this gap, this work aims at rigorously understanding offline RL with multiple datasets that are collected from randomly perturbed versions of the target task instead of from itself. An information-theoretic lower bound is derived, which reveals a necessary requirement on the number of involved sources in addition to that on the number of data samples. Then, a novel HetPEVI algorithm is proposed, which simultaneously considers the sample uncertainties from a finite number of data samples per data source and the source uncertainties due to a finite number of available data sources. Theoretical analyses demonstrate that HetPEVI can solve the target task as long as the data sources collectively provide a good data coverage. Moreover, HetPEVI is demonstrated to be optimal up to a polynomial factor of the horizon length. Finally, the study is extended to offline Markov games and offline robust RL, which demonstrates the generality of the proposed designs and theoretical analyses.","PeriodicalId":74529,"journal":{"name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","volume":"180 1","pages":"31353-31388"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74915081","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

SRATTA : Sample Re-ATTribution Attack of Secure Aggregation in Federated Learning 联邦学习中安全聚合的样本重归因攻击

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-06-13 DOI: 10.48550/arXiv.2306.07644

Tanguy Marchand, Regis Loeb, Ulysse Marteau-Ferey, Jean Ogier du Terrail, Arthur Pignet

引用次数: 0

Robustly Learning a Single Neuron via Sharpness 通过锐度稳健地学习单个神经元

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-06-13 DOI: 10.48550/arXiv.2306.07892

Puqian Wang, Nikos Zarifis, Ilias Diakonikolas, Jelena Diakonikolas

引用次数: 3

Von Mises Mixture Distributions for Molecular Conformation Generation 分子构象生成的Von Mises混合分布

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-06-13 DOI: 10.48550/arXiv.2306.07472

K. Swanson, J. Williams, Eric Jonas

{"title":"Von Mises Mixture Distributions for Molecular Conformation Generation","authors":"K. Swanson, J. Williams, Eric Jonas","doi":"10.48550/arXiv.2306.07472","DOIUrl":"https://doi.org/10.48550/arXiv.2306.07472","url":null,"abstract":"Molecules are frequently represented as graphs, but the underlying 3D molecular geometry (the locations of the atoms) ultimately determines most molecular properties. However, most molecules are not static and at room temperature adopt a wide variety of geometries or $textit{conformations}$. The resulting distribution on geometries $p(x)$ is known as the Boltzmann distribution, and many molecular properties are expectations computed under this distribution. Generating accurate samples from the Boltzmann distribution is therefore essential for computing these expectations accurately. Traditional sampling-based methods are computationally expensive, and most recent machine learning-based methods have focused on identifying $textit{modes}$ in this distribution rather than generating true $textit{samples}$. Generating such samples requires capturing conformational variability, and it has been widely recognized that the majority of conformational variability in molecules arises from rotatable bonds. In this work, we present VonMisesNet, a new graph neural network that captures conformational variability via a variational approximation of rotatable bond torsion angles as a mixture of von Mises distributions. We demonstrate that VonMisesNet can generate conformations for arbitrary molecules in a way that is both physically accurate with respect to the Boltzmann distribution and orders of magnitude faster than existing sampling methods.","PeriodicalId":74529,"journal":{"name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","volume":"13 1","pages":"33319-33342"},"PeriodicalIF":0.0,"publicationDate":"2023-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82740690","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: 2

User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems 物理动力系统扩散模型中用户自定义事件采样和不确定性量化

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-06-13 DOI: 10.48550/arXiv.2306.07526

Marc Finzi, Anudhyan Boral, A. Wilson, Fei Sha, Leonardo Zepeda-N'unez

{"title":"User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems","authors":"Marc Finzi, Anudhyan Boral, A. Wilson, Fei Sha, Leonardo Zepeda-N'unez","doi":"10.48550/arXiv.2306.07526","DOIUrl":"https://doi.org/10.48550/arXiv.2306.07526","url":null,"abstract":"Diffusion models are a class of probabilistic generative models that have been widely used as a prior for image processing tasks like text conditional generation and inpainting. We demonstrate that these models can be adapted to make predictions and provide uncertainty quantification for chaotic dynamical systems. In these applications, diffusion models can implicitly represent knowledge about outliers and extreme events; however, querying that knowledge through conditional sampling or measuring probabilities is surprisingly difficult. Existing methods for conditional sampling at inference time seek mainly to enforce the constraints, which is insufficient to match the statistics of the distribution or compute the probability of the chosen events. To achieve these ends, optimally one would use the conditional score function, but its computation is typically intractable. In this work, we develop a probabilistic approximation scheme for the conditional score function which provably converges to the true distribution as the noise level decreases. With this scheme we are able to sample conditionally on nonlinear userdefined events at inference time, and matches data statistics even when sampling from the tails of the distribution.","PeriodicalId":74529,"journal":{"name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","volume":"48 1","pages":"10136-10152"},"PeriodicalIF":0.0,"publicationDate":"2023-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80029760","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: 3

A Distribution Optimization Framework for Confidence Bounds of Risk Measures 风险测度置信限的分布优化框架

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-06-12 DOI: 10.48550/arXiv.2306.07059

Hao Liang, Zhimin Luo

{"title":"A Distribution Optimization Framework for Confidence Bounds of Risk Measures","authors":"Hao Liang, Zhimin Luo","doi":"10.48550/arXiv.2306.07059","DOIUrl":"https://doi.org/10.48550/arXiv.2306.07059","url":null,"abstract":"We present a distribution optimization framework that significantly improves confidence bounds for various risk measures compared to previous methods. Our framework encompasses popular risk measures such as the entropic risk measure, conditional value at risk (CVaR), spectral risk measure, distortion risk measure, equivalent certainty, and rank-dependent expected utility, which are well established in risk-sensitive decision-making literature. To achieve this, we introduce two estimation schemes based on concentration bounds derived from the empirical distribution, specifically using either the Wasserstein distance or the supremum distance. Unlike traditional approaches that add or subtract a confidence radius from the empirical risk measures, our proposed schemes evaluate a specific transformation of the empirical distribution based on the distance. Consequently, our confidence bounds consistently yield tighter results compared to previous methods. We further verify the efficacy of the proposed framework by providing tighter problem-dependent regret bound for the CVaR bandit.","PeriodicalId":74529,"journal":{"name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","volume":"1 1","pages":"20677-20705"},"PeriodicalIF":0.0,"publicationDate":"2023-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90784281","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

Efficient Approximations of Complete Interatomic Potentials for Crystal Property Prediction 晶体性质预测中完全原子间势的有效逼近

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-06-12 DOI: 10.48550/arXiv.2306.10045

Yu-Ching Lin, Keqiang Yan, Youzhi Luo, Yi Liu, Xiaoning Qian, Shuiwang Ji

{"title":"Efficient Approximations of Complete Interatomic Potentials for Crystal Property Prediction","authors":"Yu-Ching Lin, Keqiang Yan, Youzhi Luo, Yi Liu, Xiaoning Qian, Shuiwang Ji","doi":"10.48550/arXiv.2306.10045","DOIUrl":"https://doi.org/10.48550/arXiv.2306.10045","url":null,"abstract":"We study property prediction for crystal materials. A crystal structure consists of a minimal unit cell that is repeated infinitely in 3D space. How to accurately represent such repetitive structures in machine learning models remains unresolved. Current methods construct graphs by establishing edges only between nearby nodes, thereby failing to faithfully capture infinite repeating patterns and distant interatomic interactions. In this work, we propose several innovations to overcome these limitations. First, we propose to model physics-principled interatomic potentials directly instead of only using distances as in many existing methods. These potentials include the Coulomb potential, London dispersion potential, and Pauli repulsion potential. Second, we model the complete set of potentials among all atoms, instead of only between nearby atoms as in existing methods. This is enabled by our approximations of infinite potential summations with provable error bounds. We further develop efficient algorithms to compute the approximations. Finally, we propose to incorporate our computations of complete interatomic potentials into message passing neural networks for representation learning. We perform experiments on the JARVIS and Materials Project benchmarks for evaluation. Results show that the use of interatomic potentials and complete interatomic potentials leads to consistent performance improvements with reasonable computational costs. Our code is publicly available as part of the AIRS library (https://github.com/divelab/AIRS/tree/main/OpenMat/PotNet).","PeriodicalId":74529,"journal":{"name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","volume":"42 1","pages":"21260-21287"},"PeriodicalIF":0.0,"publicationDate":"2023-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88190590","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: 6

Can Forward Gradient Match Backpropagation? 前向梯度能匹配反向传播吗?

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-06-12 DOI: 10.48550/arXiv.2306.06968

Louis Fournier, Stephane Rivaud, Eugene Belilovsky, Michael Eickenberg, Edouard Oyallon

引用次数: 0

Diffusion Models for Black-Box Optimization 黑盒优化的扩散模型

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-06-12 DOI: 10.48550/arXiv.2306.07180

S. Krishnamoorthy, Satvik Mashkaria, Aditya Grover

{"title":"Diffusion Models for Black-Box Optimization","authors":"S. Krishnamoorthy, Satvik Mashkaria, Aditya Grover","doi":"10.48550/arXiv.2306.07180","DOIUrl":"https://doi.org/10.48550/arXiv.2306.07180","url":null,"abstract":"The goal of offline black-box optimization (BBO) is to optimize an expensive black-box function using a fixed dataset of function evaluations. Prior works consider forward approaches that learn surrogates to the black-box function and inverse approaches that directly map function values to corresponding points in the input domain of the black-box function. These approaches are limited by the quality of the offline dataset and the difficulty in learning one-to-many mappings in high dimensions, respectively. We propose Denoising Diffusion Optimization Models (DDOM), a new inverse approach for offline black-box optimization based on diffusion models. Given an offline dataset, DDOM learns a conditional generative model over the domain of the black-box function conditioned on the function values. We investigate several design choices in DDOM, such as re-weighting the dataset to focus on high function values and the use of classifier-free guidance at test-time to enable generalization to function values that can even exceed the dataset maxima. Empirically, we conduct experiments on the Design-Bench benchmark and show that DDOM achieves results competitive with state-of-the-art baselines.","PeriodicalId":74529,"journal":{"name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","volume":"68 1","pages":"17842-17857"},"PeriodicalIF":0.0,"publicationDate":"2023-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81314038","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: 7

Online Prototype Alignment for Few-shot Policy Transfer 在线原型对准少射策略转移

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-06-12 DOI: 10.48550/arXiv.2306.07307

Qi Yi, Rui Zhang, Shaohui Peng, Jiaming Guo, Yunkai Gao, Kaizhao Yuan, Rui Chen, Siming Lan, Xingui Hu, Zidong Du, Xishan Zhang, Qi Guo, Yunji Chen

{"title":"Online Prototype Alignment for Few-shot Policy Transfer","authors":"Qi Yi, Rui Zhang, Shaohui Peng, Jiaming Guo, Yunkai Gao, Kaizhao Yuan, Rui Chen, Siming Lan, Xingui Hu, Zidong Du, Xishan Zhang, Qi Guo, Yunji Chen","doi":"10.48550/arXiv.2306.07307","DOIUrl":"https://doi.org/10.48550/arXiv.2306.07307","url":null,"abstract":"Domain adaptation in reinforcement learning (RL) mainly deals with the changes of observation when transferring the policy to a new environment. Many traditional approaches of domain adaptation in RL manage to learn a mapping function between the source and target domain in explicit or implicit ways. However, they typically require access to abundant data from the target domain. Besides, they often rely on visual clues to learn the mapping function and may fail when the source domain looks quite different from the target domain. To address these problems, we propose a novel framework Online Prototype Alignment (OPA) to learn the mapping function based on the functional similarity of elements and is able to achieve the few-shot policy transfer within only several episodes. The key insight of OPA is to introduce an exploration mechanism that can interact with the unseen elements of the target domain in an efficient and purposeful manner, and then connect them with the seen elements in the source domain according to their functionalities (instead of visual clues). Experimental results show that when the target domain looks visually different from the source domain, OPA can achieve better transfer performance even with much fewer samples from the target domain, outperforming prior methods.","PeriodicalId":74529,"journal":{"name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","volume":"467 1","pages":"39968-39983"},"PeriodicalIF":0.0,"publicationDate":"2023-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79893497","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: 1