Part 1: Why Machine Learning in Systems?

• Making the case

  • Learned Operating Systems, Yiying Zhang and Yutong Huang, SIGOPS OSR 2019
  • On Foundation Models for Operating Systems, Divyanshu Saxena, Nihal Sharma, Donghyun Kim, Rohit Dwivedula, Jiayi Chen, Chenxi Yang, Sriram Ravula, Zichao Hu, Aditya Akella, Joydeep Biswas, Swarat Chaudhurim, Isil Dillig, Alex Dimakis, Daehyeok Kim, Chris Rossbach
  • Toward ML-Centric Cloud Platforms, Ricardo Bianchini, Marcus Fontoura, Eli Cortez, Anand Bonde, Alexandre Muzio, Ana-Maria Constantin, Thomas Moscibroda, Gabriel Magalhaes, Girish Bablani, Mark Russinovich, CACM 2020
  • On the Promise and Challenges of Foundation Models for Learning-based Cloud Systems Management, Haoran Qiu, Weichao Mao, Chen Wangm Hubertus Frankem Zbigniew T. Kalbarczykm Tamer Basarm Ravishankar K. Iyer
  • Architecture 2.0 Workshop: How Machine Learning Will Redefine Computer Architecture and Systems
  • Machine Learning for Databases, Guoliang Li, Xuanhe Zhou, and Lei Cao, AIMLSystems '21

• Self-Supervised Learning

  • Tutorial on Transformers and State-of-the-Art, TBA

---

Part 2: Use Cases of Learning in Systems

• Learned systems data structures

  • Indices

    • The Case for Learned Index Structures, Tim Kraska, Alex Beutel, Ed H. Chi, Jeffrey Dean, Neoklis Polyzotis. SIGMOD'18
    • ALEX: An Updatable Adaptive Learned Index, Jialin Ding, Umar Farooq Minhas, Jia Yu, Chi Wang, Jaeyoung Do, Yinan Li, Hantian Zhang, Badrish Chandramouli, Johannes Gehrke, Donald Kossmann, David Lomet, and Tim Kraska. SIGMOD'20 (Optional)

  • OS data structures

    • From WiscKey to Bourbon: A Learned Index for Log-Structured Merge Trees, Yifan Dai, Yien Xu, Aishwarya Ganesan, Ramnatthan Alagappan, Brian Kroth, Andrea Arpaci-Dusseau, and Remzi Arpaci-Dusseau. OSDI'20

• Learned algorithmic decisions

  • Scheduling

    • Learning scheduling algorithms for data processing clusters, Hongzi Mao, Malte Schwarzkopf, Shaileshh Bojja Venkatakrishnan, Zili Meng, and Mohammad Alizadeh. SIGCOMM'19

  • Resource allocation

    • LinnOS: Predictability on Unpredictable Flash Storage with a Light Neural Network, Mingzhe Hao, Levent Toksoz, Nanqinqin Li, Edward Edberg Halim, Henry Hoffmann, and Haryadi S. Gunawi. OSDI'20

  • Routing and flow problems

    • DOTE: Rethinking (Predictive) WAN Traffic Engineering, Yarin Perry, Felipe Vieira Frujeri, Chaim Hoch, Srikanth Kandula, Ishai Menache, Michael Schapira, and Aviv Tamar. USENIX NSDI 2023
    • Teal: Learning-Accelerated Optimization of WAN Traffic Engineering, Zhiying Xu, Francis Y. Yan, Rachee Singh, Justin T. Chiu, Alexander M. Rush, and Minlan Yu. SIGCOMM 2023. (Optional)

  • Prefetching

    • Learning Memory Access Patterns, Milad Hashemi, Kevin Swersky, Jamie Smith, Grant Ayers, Heiner Litz, Jichuan Chang, Christos Kozyrakis, Parthasarathy Ranganathan. ICML 2018

  • Caching

    • HALP: Heuristic Aided Learned Preference Eviction Policy for YouTube Content Delivery Network, Zhenyu Song, Kevin Chen, Nikhil Sarda, Deniz Altinbüken, Eugene Brevdo, Jimmy Coleman, Xiao Ju, Pawel Jurczyk, Richard Schooler, and Ramki Gummadi. NSDI 2023

• Learning configurations

  • Cloud and big data

    • SelfTune: Learning-based Cluster Managers, Ajaykrishna Karthikeyan, Nagarajan Natarajan, Gagan Somashekar, Lei Zhao, Ranjita Bhagwan, Rodrigo Fonseca, Tatiana Racheva, and Yogesh Bansal. NSDI 2023
    • CherryPick: Adaptively Unearthing the Best Cloud Configurations for Big Data Analytics, Omid Alipourfard, Hongqiang Harry Liu, Jianshu Chen, Shivaram Venkataraman, Minlan Yu, and Ming Zhang. NSDI'17 (Optional)

  • CDN Caches

    • Darwin: Flexible Learning-based CDN Caching, Jiayi Chen, Nihal Sharma, Tarannum Khan, Shu Liu, Brian Chang, Aditya Akella, Sanjay Shakkottai, and Ramesh K. Sitaraman. SIGCOMM'23
    • Configanator: A Data-driven Approach to Improving CDN Performance, Usama Naseer and Theophilus A. Benson. NSDI'22. (Optional)

• Learned controllers

  • Congestion control

    • Classic Meets Modern: a Pragmatic Learning-Based Congestion Control for the Internet, Soheil Abbasloo, Chen-Yu Yen, H. Jonathan Chao. SIGCOMM'20
    • Computers Can Learn from the Heuristic Designs and Master Internet Congestion Control, Chen-Yu Yen, Soheil Abbasloo, and H. Jonathan Chao. SIGCOMM'23. (Optional)

  • Microservice controllers

    • FIRM: An Intelligent Fine-grained Resource Management Framework for SLO-Oriented Microservices, Haoran Qiu, Subho S. Banerjee, Saurabh Jha, Zbigniew T. Kalbarczyk, Ravishankar K. Iyer. OSDI'20.
    • Sinan: ML-based and QoS-aware resource management for cloud microservices , Yanqi Zhang, Weizhe Hua, Zhuangzhuang Zhou, G. Edward Suh, Christina Delimitrou, ASPLOS'21. (Optional)

• Learning to manage

  • NetVigil: Robust and Low-Cost Anomaly Detection for East-West Data Center Security , Kevin Hsieh, Mike Wong, Santiago Segarra, Sathiya Kumaran Mani, Trevor Eberl, Anatoliy Panasyuk, Ravi Netravali, Ranveer Chandra, and Srikanth Kandula, NSDI'24.
  • Murphy: Performance Diagnosis of Distributed Cloud Applications , Vipul Harsh, Wenxuan Zhou, Sachin Ashok, Radhika Niranjan Mysore, P. Brighten Godfrey, Sujata Banerjee, SIGCOMM'23.

• Learning to mimic

  • Trace generation

    • Practical GAN-based synthetic IP header trace generation using NetShare, Yucheng Yin, Zinan Lin, Minhao Jin, Giulia Fanti, Vyas Sekar. SIGCOMM'22
    • Generating Complex, Realistic Cloud Workloads using Recurrent Neural Networks, Shane Bergsma, Timothy Zeyl, Arik Senderovich, J. Christopher Beck. SOSP'21

  • Simulation

    • MimicNet: fast performance estimates for data center networks with machine learning, Qizhen Zhang, Kelvin K. W. Ng, Charles Kazer, Shen Yan, João Sedoc, Vincent Liu. SIGCOMM'21
    • CausalSim: A Causal Framework for Unbiased Trace-Driven Simulation, Abdullah Alomar, Pouya Hamadanian, Arash Nasr-Esfahany, Anish Agarwal, Mohammad Alizadeh, Devavrat Shah. NSDI'23

---

Part 3: Why Does Today's Use of ML in Systems Fall Short?

• System support for learning in systems

  • Towards a Machine Learning-Assisted Kernel with LAKE, Henrique Fingler, Isha Tarte, Hangchen Yu, Ariel Szekely, Bodun Hu, Aditya Akella, Christopher J. Rossbach.
  • LiteFlow: towards high-performance adaptive neural networks for kernel datapath, Junxue Zhang, Chaoliang Zeng, Hong Zhang, Shuihai Hu, Kai Chen. SIGCOMM'22

• Learning and guarantees

  • Verifying learning systems

    • Verifying learning-augmented systems, Tomer Eliyahu, Yafim Kazak, Guy Katz, Michael Schapira. SIGCOMM '21. (Optional)

  • Integrating with training

    • Building Verified Neural Networks for Computer Systems with Ouroboros, Tianhao Wei, Zhihao Jia, Changliu Liu, Cheng Tan, MLSys'23
    • Safe Neurosymbolic Learning with Differentiable Symbolic Execution, Chenxi Yang and Swarat Chaudhuri, ICLR 2022

• Learning composable decisions

  • Towards Verified Self-Driving Infrastructure, Bingzhe Liu, Ali Kheradmand, Matthew Caesar, P. Brighten Godfrey. HotNets'20

---