Signal Processing for Big Data
Program
Part 1: Signal Processing and Sparsity
Definition of signals, signal properties, discrete representations, Fourier transforms, filtering, sampling theory, applications to audio signals and images.
Basics of convex optimization: Convex sets, convex functions, convex optimization problems.
Sparse representations, compressive sensing, application to image recovery.
Matrix completion, application to recommendation systems.
Sparse plus low-rank models, Application to traffic prediction over networks.
Tensor factorization and completion.
Part 2: Graph Signal Processing
Algebraic graph theory, graph properties, connectivity, degree centrality, eigenvector centrality, PageRank, betweeness, modularity
Graph partitioning
Graph filtering, sampling, prediction of graph processes
Independence graphs: Markov networks, Bayes networks, Gaussian Markov Random Fields, inference of graph topology from data. Application to brain functional connectivity inference.
Graph convolutional neural networks. Application to Geometric Deep Learning.
Part 3: Distributed Optimization and Machine Learning
Duality theory: Lagrange dual problem, Slater's constraint qualifications, KKT conditions.
Optimization algorithms: Primal methods (steepest descent, gradient projection, Newton method, proximal gradient), primal-dual methods (dual ascent, method of multipliers, ADMM).
Distributed convex machine learning: Computing architectures (parallel, federated, etc.). Splitting across examples and/or features; Application to distributed regression and classification.
Distributed non-convex machine learning: Parallel SGD and the SCA framework. Application to Neural Network training and matrix/tensor completion.
Textbooks and resources:
[1] Slides and codes
[2] S. Boyd and L. Vandenberghe, Convex Optimization, Cambridge University Press, 2004;
[3] S. Foucart and R. Holger, A mathematical introduction to compressive sensing, Basel: Birkhäuser, 2013.
[4] S. Boyd et al., Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers, Foundations and Trends in Machine Learning, 3(1):1–122, 2011.
[5] CVX software for convex optimization.
[6] E.J. Candès et al., Exact matrix completion via convex optimization, Foundations of Computational mathematics, 9(6), 717-772, 2009.
[7] Cai, J. F., Candès, E. J., & Shen, Z., A singular value thresholding algorithm for matrix completion, SIAM Journal on Optimization, 20(4), 1956-1982.
[8] P. Di Lorenzo, S. Barbarossa, and P. Banelli, Sampling and Recovery of Graph Signals, Cooperative and Graph Signal Processing, P. Djuric and C. Richard Eds., Elsevier, 2018.
[9] Vetterli, Martin, Jelena Kovačević, and Vivek K. Goyal. Foundations of signal processing. Cambridge University Press, 2014.
[10] M.E.J. Newman, Networks: An Introduction, Oxford, UK: Oxford University Press.