{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T21:10:52Z","timestamp":1780089052005,"version":"3.54.0"},"reference-count":67,"publisher":"Association for Computing Machinery (ACM)","issue":"2","funder":[{"name":"Ontario Research Fund \u2013 Research Excellence program","award":["ORF-RE012-051"],"award-info":[{"award-number":["ORF-RE012-051"]}]},{"name":"European Union\u2019s Horizon Europe research and innovation programme","award":["101139048"],"award-info":[{"award-number":["101139048"]}]},{"name":"Rogers Communications Chair in Network Automation","award":["-"],"award-info":[{"award-number":["-"]}]},{"name":"Canada Research Chair in Network Intelligence","award":["-"],"award-info":[{"award-number":["-"]}]},{"name":"NSERC Alliance","award":["-"],"award-info":[{"award-number":["-"]}]},{"DOI":"10.13039\/501100004489","name":"Mitacs","doi-asserted-by":"crossref","award":["-"],"award-info":[{"award-number":["-"]}],"id":[{"id":"10.13039\/501100004489","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001804","name":"Canada Research Chair","doi-asserted-by":"crossref","award":["CRC-2023-00035"],"award-info":[{"award-number":["CRC-2023-00035"]}],"id":[{"id":"10.13039\/501100001804","id-type":"DOI","asserted-by":"crossref"}]},{"name":"NSERC Discovery grant","award":["RGPIN-2023-03775"],"award-info":[{"award-number":["RGPIN-2023-03775"]}]},{"name":"DFG grant CLAYRE","award":["565652476"],"award-info":[{"award-number":["565652476"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Meas. Anal. Comput. Syst."],"published-print":{"date-parts":[[2026,5,29]]},"abstract":"<jats:p>\n                    Deep reinforcement learning (DRL) has shown remarkable performance on complex control problems in systems and networking, including adaptive video streaming, wireless resource management, and congestion control. For safe deployment, however, it is critical to reason about how agents behave across the range of system states they may encounter in practice. Existing verification-based approaches in this domain primarily focus on\n                    <jats:italic toggle=\"yes\">point properties<\/jats:italic>\n                    -- properties defined around fixed input states -- which offer limited coverage and require substantial manual effort to identify relevant input-output pairs for analysis.\n                  <\/jats:p>\n                  <jats:p>\n                    In this paper, we study\n                    <jats:italic toggle=\"yes\">symbolic properties<\/jats:italic>\n                    -- properties that specify expected behaviors over ranges of input states -- for DRL agents in systems and networking. We present a generic formulation for symbolic properties, with monotonicity and robustness as concrete examples, and show how they can be analyzed using existing DNN verification engines. Our approach encodes symbolic properties as comparisons between related executions of the same policy and decomposes them into practically tractable sub-properties. These techniques serve as practical enablers for applying existing verification tools to symbolic analysis.\n                  <\/jats:p>\n                  <jats:p>Using our framework, diffRL, we conduct an extensive empirical study across three representative DRL-based control systems -- adaptive video streaming, wireless resource allocation, and congestion control -- covering both discrete and continuous action spaces. Through these case studies, we analyze symbolic properties over broad input ranges, examine how property satisfaction evolves during training, study the impact of model size on verifiability, and compare multiple verification backends. Our results show that symbolic properties provide substantially broader coverage than point properties and can uncover non-obvious, operationally meaningful counterexamples, while also revealing practical solver trade-offs and limitations.<\/jats:p>","DOI":"10.1145\/3805627","type":"journal-article","created":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T20:34:18Z","timestamp":1780086858000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Analyzing Symbolic Properties for DRL Agents in Systems and Networking"],"prefix":"10.1145","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6657-0677","authenticated-orcid":false,"given":"Mohammad","family":"Zangooei","sequence":"first","affiliation":[{"name":"University of Waterloo, Waterloo, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5439-9131","authenticated-orcid":false,"given":"Jannis","family":"Weil","sequence":"additional","affiliation":[{"name":"Leibniz University Hannover, Hannover, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9385-7729","authenticated-orcid":false,"given":"Amr","family":"Rizk","sequence":"additional","affiliation":[{"name":"Leibniz University Hannover, Hannover, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5594-1110","authenticated-orcid":false,"given":"Mina Tahmasbi","family":"Arashloo","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7936-6862","authenticated-orcid":false,"given":"Raouf","family":"Boutaba","sequence":"additional","affiliation":[{"name":"Computer Science, University of Waterloo, Waterloo, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,5,29]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"https:\/\/github.com\/NeuralNetworkVerification\/Marabou","year":"2024","unstructured":"v2.0.0. Marabou. https:\/\/github.com\/NeuralNetworkVerification\/Marabou. Accessed: September, 2024."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405892"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/3691825.3691878"},{"key":"e_1_2_1_4_1","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Arashloo Mina Tahmasbi","year":"2023","unstructured":"Mina Tahmasbi Arashloo, Ryan Beckett, and Rachit Agarwal. 2023. Formal methods for network performance analysis. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 645--661."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472912"},{"key":"e_1_2_1_6_1","volume-title":"Counterexample-Guided Repair of Reinforcement Learning Systems Using Safety Critics. arXiv preprint arXiv:2405.15430","author":"Boetius David","year":"2024","unstructured":"David Boetius and Stefan Leue. 2024. Counterexample-Guided Repair of Reinforcement Learning Systems Using Safety Critics. arXiv preprint arXiv:2405.15430 (2024)."},{"key":"e_1_2_1_7_1","unstructured":"Shaileshh Bojja Venkatakrishnan Shreyan Gupta Hongzi Mao Mohammad Alizadeh et al. 2019. Learning Generalizable Device Placement Algorithms for Distributed Machine Learning. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_2_1_8_1","volume-title":"The fourth international verification of neural networks competition (VNN-COMP 2023): Summary and results. arXiv preprint arXiv:2312.16760","author":"Brix Christopher","year":"2023","unstructured":"Christopher Brix, Stanley Bak, Changliu Liu, and Taylor T Johnson. 2023. The fourth international verification of neural networks competition (VNN-COMP 2023): Summary and results. arXiv preprint arXiv:2312.16760 (2023)."},{"key":"e_1_2_1_9_1","first-page":"1","article-title":"Branch and bound for piecewise linear neural network verification","volume":"21","author":"Bunel Rudy","year":"2020","unstructured":"Rudy Bunel, Jingyue Lu, Ilker Turkaslan, Philip HS Torr, Pushmeet Kohli, and M Pawan Kumar. 2020. Branch and bound for piecewise linear neural network verification. Journal of Machine Learning Research 21, 42 (2020), 1--39.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_1_10_1","volume-title":"Property-Driven Evaluation of RL-Controllers in Self-Driving Datacenters. In Workshop on Challenges in Deploying and Monitoring Machine Learning Systems, NeurIPS Virtual Workshop.","author":"Chakravarthy Arnav","year":"2022","unstructured":"Arnav Chakravarthy, Nina Narodytska, Asmitha Rathis, Marius Vilcu, Mahmood Sharif, and Gagandeep Singh. 2022. Property-Driven Evaluation of RL-Controllers in Self-Driving Datacenters. In Workshop on Challenges in Deploying and Monitoring Machine Learning Systems, NeurIPS Virtual Workshop."},{"key":"e_1_2_1_11_1","volume-title":"Proceedings of the 2018 conference of the ACM special interest group on data communication. 191--205","author":"Chen Li","year":"2018","unstructured":"Li Chen, Justinas Lingys, Kai Chen, and Feng Liu. 2018. Auto: Scaling deep reinforcement learning for datacenterscale automatic traffic optimization. In Proceedings of the 2018 conference of the ACM special interest group on data communication. 191--205."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11339"},{"key":"e_1_2_1_13_1","volume-title":"IEEE INFOCOM 2023-IEEE Conference on Computer Communications. IEEE, 1--10","author":"Dery Micha","year":"2023","unstructured":"Micha Dery, Orr Krupnik, and Isaac Keslassy. 2023. QueuePilot: Reviving Small Buffers With a Learned AQM Policy. In IEEE INFOCOM 2023-IEEE Conference on Computer Communications. IEEE, 1--10."},{"key":"e_1_2_1_14_1","volume-title":"Proceedings of the 2019 Workshop on Network Meets AI, #38; ML. 29--36","author":"Dethise Arnaud","year":"2019","unstructured":"Arnaud Dethise, Marco Canini, and Srikanth Kandula. 2019. Cracking open the black box: What observations can tell us about reinforcement learning agents. In Proceedings of the 2019 Workshop on Network Meets AI, #38; ML. 29--36."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488898"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472936"},{"key":"e_1_2_1_17_1","volume-title":"Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems. 1606--1614","author":"Gangopadhyay Briti","year":"2023","unstructured":"Briti Gangopadhyay, Pallab Dasgupta, and Soumyajit Dey. 2023. Counterexample-Guided Policy Refinement in Multi-Agent Reinforcement Learning. In Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems. 1606--1614."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3365609.3365862"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672231"},{"key":"e_1_2_1_20_1","unstructured":"Gurobi Optimization LLC. 2024. Gurobi Optimizer Reference Manual. https:\/\/www.gurobi.com"},{"key":"e_1_2_1_21_1","volume-title":"Proceedings of Machine Learning and Systems 5","author":"Hu Yi","year":"2023","unstructured":"Yi Hu, Chaoran Zhang, Edward Andert, Harshul Singh, Aviral Shrivastava, James Laudon, Yanqi Zhou, Bob Iannucci, and Carlee Joe-Wong. 2023. GiPH: Generalizable Placement Learning for Adaptive Heterogeneous Computing. Proceedings of Machine Learning and Systems 5 (2023)."},{"key":"e_1_2_1_22_1","volume-title":"2023 IEEE\/ACM 31st International Symposium on Quality of Service (IWQoS). IEEE, 01--10","author":"Huang Yangfan","year":"2023","unstructured":"Yangfan Huang, Yuling Lin, Haizhou Du, Yijian Chen, Haohao Song, Linghe Kong, Qiao Xiang, Qiang Li, Franck Le, and Jiwu Shu. 2023. Toward a Unified Framework for Verifying and Interpreting Learning-Based Networking Systems. In 2023 IEEE\/ACM 31st International Symposium on Quality of Service (IWQoS). IEEE, 01--10."},{"key":"e_1_2_1_23_1","unstructured":"IBM Corporation. 2019. IBM ILOG CPLEX Optimization Studio. IBM."},{"key":"e_1_2_1_24_1","volume-title":"International Conference on Machine Learning. PMLR, 3050--3059","author":"Jay Nathan","year":"2019","unstructured":"Nathan Jay, Noga Rotman, Brighten Godfrey, Michael Schapira, and Aviv Tamar. 2019. A deep reinforcement learning perspective on internet congestion control. In International Conference on Machine Learning. PMLR, 3050--3059."},{"key":"e_1_2_1_25_1","volume-title":"IEEE INFOCOM 2023-IEEE Conference on Computer Communications. IEEE, 1--10","author":"Jia Lianchen","year":"2023","unstructured":"Lianchen Jia, Chao Zhou, Tianchi Huang, Chaoyang Li, and Lifeng Sun. 2023. RDladder: Resolution-Duration Ladder for VBR-encoded Videos via Imitation Learning. In IEEE INFOCOM 2023-IEEE Conference on Computer Communications. IEEE, 1--10."},{"key":"e_1_2_1_26_1","volume-title":"Meet the Challenge of Industrial Adaptive Streaming via Offline Reinforcement Learning. In IEEE INFOCOM 2024-IEEE Conference on Computer Communications. IEEE, 2169--2178","author":"Jia Lianchen","year":"2024","unstructured":"Lianchen Jia, Chao Zhou, Tianchi Huang, Chaoyang Li, and Lifeng Sun. 2024. Dancing with Shackles, Meet the Challenge of Industrial Adaptive Streaming via Offline Reinforcement Learning. In IEEE INFOCOM 2024-IEEE Conference on Computer Communications. IEEE, 2169--2178."},{"key":"e_1_2_1_27_1","volume-title":"AutoSpec: Automated Generation of Neural Network Specifications. arXiv preprint arXiv:2409.10897","author":"Jin Shuowei","year":"2024","unstructured":"Shuowei Jin, Francis Y Yan, Cheng Tan, Anuj Kalia, Xenofon Foukas, and Z Morley Mao. 2024. AutoSpec: Automated Generation of Neural Network Specifications. arXiv preprint arXiv:2409.10897 (2024)."},{"key":"e_1_2_1_28_1","volume-title":"18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)","author":"Jog Suraj","year":"2021","unstructured":"Suraj Jog, Zikun Liu, Antonio Franques, Vimuth Fernando, Sergi Abadal, Josep Torrellas, and Haitham Hassanieh. 2021. One protocol to rule them all: Wireless Network-on-Chip using deep reinforcement learning. In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21). 973--989."},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63387-9_5"},{"key":"e_1_2_1_30_1","volume-title":"EdgeRIC: Empowering Real-time Intelligent Optimization and Control in NextG Cellular Networks. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Ko Woo-Hyun","year":"2024","unstructured":"Woo-Hyun Ko, Ushasi Ghosh, Ujwal Dinesha, Raini Wu, Srinivas Shakkottai, and Dinesh Bharadia. 2024. EdgeRIC: Empowering Real-time Intelligent Optimization and Control in NextG Cellular Networks. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). USENIX Association, Santa Clara, CA, 1315--1330. https: \/\/www.usenix.org\/conference\/nsdi24\/presentation\/ko"},{"key":"e_1_2_1_31_1","first-page":"80270","article-title":"Provably bounding neural network preimages","volume":"36","author":"Kotha Suhas","year":"2023","unstructured":"Suhas Kotha, Christopher Brix, J Zico Kolter, Krishnamurthy Dvijotham, and Huan Zhang. 2023. Provably bounding neural network preimages. Advances in Neural Information Processing Systems 36 (2023), 80270--80290.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_32_1","volume-title":"Kivi: Verification for Cluster Management. In 2024 USENIX Annual Technical Conference (USENIX ATC 24)","author":"Liu Bingzhe","unstructured":"Bingzhe Liu, Gangmuk Lim, Ryan Beckett, and P. Brighten Godfrey. 2024. Kivi: Verification for Cluster Management. In 2024 USENIX Annual Technical Conference (USENIX ATC 24). USENIX Association, Santa Clara, CA, 509--527. https:\/\/www.usenix.org\/conference\/atc24\/presentation\/liu-bingzhe"},{"key":"e_1_2_1_33_1","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Liu Zikun","year":"2023","unstructured":"Zikun Liu, Changming Xu, Yuqing Xie, Emerson Sie, Fan Yang, Kevin Karwaski, Gagandeep Singh, Zhao Lucis Li, Yu Zhou, Deepak Vasisht, et al. 2023. Exploring practical vulnerabilities of machine learning-based wireless systems. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 1801--1817."},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519593"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342080"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405859"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/3692070.3693543"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.3390\/make4010013"},{"key":"e_1_2_1_41_1","volume-title":"The third international verification of neural networks competition (VNN-COMP 2022): Summary and results. arXiv preprint arXiv:2212.10376","author":"M\u00fcller Mark Niklas","year":"2022","unstructured":"Mark Niklas M\u00fcller, Christopher Brix, Stanley Bak, Changliu Liu, and Taylor T Johnson. 2022. The third international verification of neural networks competition (VNN-COMP 2022): Summary and results. arXiv preprint arXiv:2212.10376 (2022)."},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672253"},{"key":"e_1_2_1_43_1","volume-title":"Proceedings of the 22nd ACM Workshop on Hot Topics in Networks. 213--219","author":"Pazhooheshy Parsa","year":"2023","unstructured":"Parsa Pazhooheshy, Soheil Abbasloo, and Yashar Ganjali. 2023. Harnessing ML For Network Protocol Assessment: A Congestion Control Use Case. In Proceedings of the 22nd ACM Workshop on Hot Topics in Networks. 213--219."},{"key":"e_1_2_1_44_1","volume-title":"14th USENIX symposium on operating systems design and implementation (OSDI 20)","author":"Qiu Haoran","year":"2020","unstructured":"Haoran Qiu, Subho S Banerjee, Saurabh Jha, Zbigniew T Kalbarczyk, and Ravishankar K Iyer. 2020. FIRM: An intelligent fine-grained resource management framework for SLO-Oriented microservices. In 14th USENIX symposium on operating systems design and implementation (OSDI 20). 805--825."},{"key":"e_1_2_1_45_1","first-page":"524","article-title":"FLASH: Fast model adaptation in ML-centric cloud platforms","volume":"6","author":"Qiu Haoran","year":"2024","unstructured":"Haoran Qiu, Weichao Mao, Archit Patke, Shengkun Cui, Chen Wang, Hubertus Franke, Zbigniew T Kalbarczyk, Tamer Basar, and Ravishankar K Iyer. 2024. FLASH: Fast model adaptation in ML-centric cloud platforms. Proceedings of Machine Learning and Systems 6 (2024), 524--544.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_2_1_46_1","volume-title":"International Conference on Machine Learning. PMLR, 29338--29353","author":"Runje Davor","year":"2023","unstructured":"Davor Runje and Sharath M Shankaranarayana. 2023. Constrained monotonic neural networks. In International Conference on Machine Learning. PMLR, 29338--29353."},{"key":"e_1_2_1_47_1","volume-title":"International Conference on Machine Learning. PMLR, 8707--8718","author":"Shen Qianli","year":"2020","unstructured":"Qianli Shen, Yan Li, Haoming Jiang, Zhaoran Wang, and Tuo Zhao. 2020. Deep reinforcement learning with robust and smooth policy. In International Conference on Machine Learning. PMLR, 8707--8718."},{"key":"e_1_2_1_48_1","volume-title":"International Conference on Tools and Algorithms for the Construction and Analysis of Systems. Springer, 315--335","author":"Shi Zhouxing","year":"2025","unstructured":"Zhouxing Shi, Qirui Jin, Zico Kolter, Suman Jana, Cho-Jui Hsieh, and Huan Zhang. 2025. Neural network verification with branch-and-bound for general nonlinearities. In International Conference on Tools and Algorithms for the Construction and Analysis of Systems. Springer, 315--335."},{"key":"e_1_2_1_49_1","volume-title":"Anvil: Verifying Liveness of Cluster Management Controllers. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Sun Xudong","year":"2024","unstructured":"Xudong Sun, Wenjie Ma, Jiawei Tyler Gu, Zicheng Ma, Tej Chajed, Jon Howell, Andrea Lattuada, Oded Padon, Lalith Suresh, Adriana Szekeres, and Tianyin Xu. 2024. Anvil: Verifying Liveness of Cluster Management Controllers. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). USENIX Association, Santa Clara, CA, 649--666. https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/sun-xudong"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.5555\/3312046"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796967"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3512798.3512815"},{"key":"e_1_2_1_53_1","volume-title":"Evaluating Robustness of Neural Networks with Mixed Integer Programming. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=HyGIdiRqtm","author":"Tjeng Vincent","year":"2019","unstructured":"Vincent Tjeng, Kai Y. Xiao, and Russ Tedrake. 2019. Evaluating Robustness of Neural Networks with Mixed Integer Programming. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=HyGIdiRqtm"},{"key":"e_1_2_1_54_1","volume-title":"Lipschitz regularity of deep neural networks: analysis and efficient estimation. Advances in Neural Information Processing Systems 31","author":"Virmaux Aladin","year":"2018","unstructured":"Aladin Virmaux and Kevin Scaman. 2018. Lipschitz regularity of deep neural networks: analysis and efficient estimation. Advances in Neural Information Processing Systems 31 (2018)."},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796784"},{"key":"e_1_2_1_56_1","first-page":"29909","article-title":"Beta-crown: Efficient bound propagation with per-neuron split constraints for neural network robustness verification","volume":"34","author":"Wang Shiqi","year":"2021","unstructured":"Shiqi Wang, Huan Zhang, Kaidi Xu, Xue Lin, Suman Jana, Cho-Jui Hsieh, and J Zico Kolter. 2021. Beta-crown: Efficient bound propagation with per-neuron split constraints for neural network robustness verification. Advances in Neural Information Processing Systems 34 (2021), 29909--29921.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_57_1","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Wang Zibo","year":"2024","unstructured":"Zibo Wang, Pinghe Li, Chieh-Jan Mike Liang, Feng Wu, and Francis Y Yan. 2024. Autothrottle: A Practical Bi-Level Approach to Resource Management for SLO-Targeted Microservices. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). 149--165."},{"key":"e_1_2_1_58_1","volume-title":"Unconstrained monotonic neural networks. Advances in neural information processing systems 32","author":"Gilles Louppe AntoineWehenkel","year":"2019","unstructured":"AntoineWehenkel and Gilles Louppe. 2019. Unconstrained monotonic neural networks. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_2_1_59_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 6853--6878","author":"Wei Dennis","year":"2023","unstructured":"Dennis Wei, Haoze Wu, Min Wu, Pin-Yu Chen, Clark Barrett, and Eitan Farchi. 2023. Convex bounds on the softmax function with applications to robustness verification. In International Conference on Artificial Intelligence and Statistics. PMLR, 6853--6878."},{"key":"e_1_2_1_60_1","volume-title":"Proceedings of the ACM on Programming Languages 6, OOPSLA2","author":"Wu Haoze","year":"2022","unstructured":"Haoze Wu, Clark Barrett, Mahmood Sharif, Nina Narodytska, and Gagandeep Singh. 2022. Scalable verification of GNN-based job schedulers. Proceedings of the ACM on Programming Languages 6, OOPSLA2 (2022), 1036--1065."},{"key":"e_1_2_1_61_1","volume-title":"International Conference on Computer Aided Verification. Springer, 249--264","author":"Wu Haoze","year":"2024","unstructured":"Haoze Wu, Omri Isac, Aleksandar Zeljic, Teruhiro Tagomori, Matthew Daggitt, Wen Kokke, Idan Refaeli, Guy Amir, Kyle Julian, Shahaf Bassan, et al. 2024. Marabou 2.0: a versatile formal analyzer of neural networks. In International Conference on Computer Aided Verification. Springer, 249--264."},{"key":"e_1_2_1_62_1","first-page":"1129","article-title":"Automatic perturbation analysis for scalable certified robustness and beyond","volume":"33","author":"Xu Kaidi","year":"2020","unstructured":"Kaidi Xu, Zhouxing Shi, Huan Zhang, Yihan Wang, Kai-Wei Chang, Minlie Huang, Bhavya Kailkhura, Xue Lin, and Cho-Jui Hsieh. 2020. Automatic perturbation analysis for scalable certified robustness and beyond. Advances in Neural Information Processing Systems 33 (2020), 1129--1141.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_63_1","unstructured":"Kaidi Xu Huan Zhang Shiqi Wang Yihan Wang Suman Jana Xue Lin and Cho-Jui Hsieh. 2021. Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifiers. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=nVZtXBI6LNn"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604857"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472927"},{"key":"e_1_2_1_66_1","volume-title":"Flexible RAN Slicing in Open RAN With Constrained Multi-Agent Reinforcement Learning","author":"Zangooei Mohammad","year":"2023","unstructured":"Mohammad Zangooei, Morteza Golkarifard, Mohamed Rouili, Niloy Saha, and Raouf Boutaba. 2023. Flexible RAN Slicing in Open RAN With Constrained Multi-Agent Reinforcement Learning. IEEE Journal on Selected Areas in Communications (2023)."},{"key":"e_1_2_1_67_1","volume-title":"Efficient neural network robustness certification with general activation functions. Advances in neural information processing systems 31","author":"Zhang Huan","year":"2018","unstructured":"Huan Zhang, Tsui-Wei Weng, Pin-Yu Chen, Cho-Jui Hsieh, and Luca Daniel. 2018. Efficient neural network robustness certification with general activation functions. Advances in neural information processing systems 31 (2018)."}],"container-title":["Proceedings of the ACM on Measurement and Analysis of Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3805627","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T20:37:27Z","timestamp":1780087047000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805627"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,29]]},"references-count":67,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,5,29]]}},"alternative-id":["10.1145\/3805627"],"URL":"https:\/\/doi.org\/10.1145\/3805627","relation":{},"ISSN":["2476-1249"],"issn-type":[{"value":"2476-1249","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,29]]},"assertion":[{"value":"2026-05-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}