BrainStorming 樊艳波
Outline Several papers on icml15 & cvpr15 PALM Information Theory Learning.
Multi-view Sparse Co-clustering via Proximal Alternating Linearized Minimization(CVPR15) Single view rank-one approximation.
Multi-view co-clustering Objective Function. Optimization: PALM.
Proximal Alternating Linearized Minimization for Nonconvex and Nonsmooth Problems(Bolte, Mathematical Programming14) General nonconvex nonsmooth function Example:
Coordinate descent methods Gauss-Seidel iteration scheme: –Drawback: strict convexity assumption. Proximal regularization of the Gauss-Seidel scheme: –Existing problems: Hard to optimize each step exactly.
Proposed PALM method Idea: linear expansion
Proposed PALM method Algorithm.
An example: Sparse NMF Generate
Entropic Graph-based Posterior Regularization. MaxwellW Libbrecht(ICML15) Objective Function. R: regularization term over, Existing ways : L0, L1, L2...
Posterior Regularization Posterior regularization: –Nearby variables have simple posterior distributions. –More nature. Formulation.
Optimation & Simulations EM-like algorithm. has closed form.
Unsupervised Simultaneous Orthogonal Basis Clustering Feature Selection.(CVPR15) Regularized regression model: Proposed Model. B: latent cluster center. E: encoding matrix. each row of E has only one non-zero term.
Just for Insights
Optimal Graph Learning with Partial Tags and Multiple Features for Image and Video Annotation.(CVPR15) Extensions: out of sample annotation; noise label information.
Information-Theoretic Dictionary Learning for Image Classification(TPAMI14) Traditional Dictionary learning. ITL based Dictionary learning. –D^{0}: initialization by k-svd or others. –Dictionary compactness: –Dictionary discrimination: –Dictionary representation: Optimization: gauss process, kernel density estimates...