A seminar by Dr Zhenyu Liao from the University of California, Berkeley
Title: Performance-complexity trade-off in large dimensional spectral clustering
Abstract: The big data revolution comes along with the challenging need to parse, mine, compress a large amount of large dimensional data. Many modern machine learning algorithms (including state-of-the-art deep neural networks) are designed to work with compressed, quantized, or even binarized data so that they can run on low-power IoT devices.
In this talk, we will focus on the theoretical analysis of spectral clustering method that aims to find possible clusters from a given data matrix in an unsupervised manner, by exploring the informative eigenstructure (e.g., the dominant eigenvector) of the data matrix. Random matrix analysis reveals the surprising fact that very little change occurs in the informative eigenstructure even under drastic sparsification and/or quantization, and consequently, that very little downstream performance loss occurs with very aggressively uniformed and non-uniformed, sparsified and/or quantized spectral clustering. The present study is based on a spiked model analysis of nonlinear random matrices and may be of independent research interest. We expect that our analysis opens the door to improved analysis of computationally efficient methods for large dimensional machine learning and neural network models more generally.
Reference:
* Zarrouk, T., Couillet, R., Chatelain, F., & Le Bihan, N. (2020). Performance-complexity trade-off in large dimensional statistics. In 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing (MLSP) (pp. 1-6). IEEE.
* Liao, Z., Couillet, R., & Mahoney, M. W. (2020). Sparse quantized spectral clustering. The Ninth International Conference on Learning Representations (ICLR 2021).
For further details, please contact RSFAS Enquiry.
All information collected by the University is governed by the ANU Privacy Policy.