I enjoy exploring the following fields:
Machine learning
Natural language processing
I broadly identify with the machine learning (COLT, ICLR, ICML and NeurIPS) community. I am also interested in statistics and information theory. For a period in the past, I worked on systems and networking as well.
My research has been recognized in both academia and industry. Our project on data center networks and clock synchronization system has been on the front page of New York Times, and there are startups based on our work. In machine learning, my work on natural language processing was taught in Stanford's popular NLP course CS224n by Prof. Manning.
I am a reviewer for multiple conference (KDD, NeurIPS, ICLR, ICML, etc.).
Google Scholar Profile:
Yilong Geng, Shiyu Liu, Zi Yin, Ashish Naik, Balaji Prabhakar, Mendel Rosenblum and Amin Vahdat. "SIMON: A Simple and Scalable Method for Sensing, Inference and Measurement in Data Center Networks", 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI), Boston, MA, 2019.
Zi, Yin and Yuanyuan Shen. "On the Dimensionality of Word Embedding", Advances in Neural Information Processing Systems (NeurIPS), Montreal, 2018. (Oral presentation, top 0.6% of all submissions)
Zi, Yin, Vin Sachidananda and Balaji Prabhakar. "The Global Anchor Method for Quantifying Linguistic Shifts and Domain Adaptation", Advances in Neural Information Processing Systems (NeurIPS), Montreal, 2018.
Zi Yin. "Understand Functionality and Dimensionality of Vector Embeddings: the Distributional Hypothesis, the Pairwise Inner Product Loss and Its Bias-Variance Trade-off", arXiv Preprint, arXiv:1803.00502
Yilong Geng, Shiyu Liu, Zi Yin, Ashish Naik, Balaji Prabhakar, Mendel Rosenblum and Amin Vahdat. "Exploiting a natural network effect for scalable, fine-grained clock synchronization", 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI), Renton, WA, 2018.
Zi Yin, Keng-hao Chang, and Ruofei Zhang. "Deepprobe: Information directed sequence understanding and chatbot design via recurrent neural networks." Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (SIGKDD), Halifax, 2017.
Yilong Geng, Shiyu Liu, Feiran Wang, Zi Yin, Balaji Prabhakar and Mendel Rosenblum. "Self-programming networks: Architecture and algorithms", 55th Annual Allerton Conference on Communication, Control, and Computing (Allerton), Monticello, IL, 2017.
Zi Yin, Ying Li, Pietro Mazzoleni and Yuanyuan Shen. "Mining Effective Subsequences with Application in Marketing Attribution",2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW), Barcelona, 2016.