Hi All, I am a PhD student at National University of Singapore and have been doing research on streaming and real-time anomaly detection. Our algorithm MIDAS was recently published in AAAI 2020. It uses count min sketches. I think it should be useful to the community, hence sharing the code and the paper:
Github Repository: https://github.com/Stream-AD/MIDAS/ Paper: https://www.comp.nus.edu.sg/~sbhatia/assets/pdf/midas.pdf Let me know if you are interested to collaborate on anomaly detection using sketches. Also, can you please point me to a count sketch implementation if you are aware of one. Thanks, Siddharth
