MahNMFManhattanNon-negativeMatrixFactorization资源-CSDN文库

共8个文件

m：6个

mexw32：1个

mexw64：1个

5星 · 超过95%的资源需积分: 12 136 浏览量 2015-04-22 10:40:20 上传评论收藏 29KB RAR 举报

MahNMF Manhattan Non-negative Matrix Factorization code % Manhattan Non-negative Matrix Factorization. % ManhNMF: Matlab Code for Efficient Robust Manhattan NMF Solver % Reference % [1] N. Guan, D. Tao, Z. Luo, and J. Shawe-taylor, "MahNMF: Manhattan % Non-negative Matrix Factorization," arXiv:1207.3438v1, 2012. % [2] N. Guan, D. Tao, Z. Luo, and J. Shawe-taylor, "MahNMF: Manhattan % Non-negative Matrix Factorization," Submitted to Journal of Machine Learning Research, 2013. % The model is X \approx W^TH, where X, W, and H are defined as follows: % X (m x n): data matrix including n samples in m-dimensional space; % W (r x m): basis matrix including r bases in m-dimensional space; % H (r x n): coefficients matrix includeing n encodings in r-dimensional space. % Written by Naiyang Guan (ny.guan@gmail.com) % Copyright 2012-2014 by Naiyang Guan and Dacheng Tao % Modified at Jan. 28 2013 % <Inputs> % X : Input data matrix (m x n) % r : Target low-rank % % (Below are optional arguments: can be set by providing name-value pairs) % MAX_ITER : Maximum number of iterations. Default is 1,000. % MIN_ITER : Minimum number of iterations. Default is 10. % MAX_TIME : Maximum amount of time in seconds. Default is 100,000. % W_INIT : (m x r) initial value for W. % H_INIT : (r x n) initial value for H. % LAM_INIT : initial value of smoothness parameter. Default is 1. % MDL_TYPE : Model type (Default is 'PLAIN'), % 'PLAIN' - MahNMF (min{||X-W^T*H||_1,s.t.,W >= 0 and H >= 0}.), % 'BXC' - Box Constrained MahNMF (min{||X-W^T*H||_1,s.t.,1 >= W >= 0 and 1 >= H >= 0}.), % 'MNR' - Manifold Regularized MahNMF % (min{||X-W^T*H||_1+.5*beta*TR(H*Lp*H^T),s.t.,W >= 0 and H >= 0}.), % 'GSP' - Group Sparse MahNMF % (min{||X-W^T*H||_1+.5*beta*\sum_{g\in G}||W^[g]||_{1,p},s.t.,W >= 0 and H >= 0}.), % 'SYM' - Symmetric MahNMF (min{||X-H*H^T||_1,s.t., H >= 0}.). % ALG_TYPE : Algorithm type (Default is 'AGD'), % 'AGD' - Accelerated Gradient Descent, % 'RRI' - Rank-one Residue Iteration. % BETA : Tradeoff parameter over regularization term. Default is 1e-3. % SIM_MTX : Similarity matrix constructed by 'constructW'. % GPP_MTX : Group pattern for boundary of all groups. % TOL_INNR : Stopping tolerance of inner iterations. Default is 1e-2. % TOL_OUTR : Stopping tolerance of outer iterations. Default is 1e-3. % If you want to obtain a more accurate solution, decrease TOL_INNR or TOL_OUTR and increase MAX_ITER at the same time. % VB_OUTR : 0 (default) - No debugging information is collected. % 1 (debugging purpose) - History of computation is returned by 'HIS' variable. % 2 (debugging purpose) - History of computation is additionally printed on screen. % VB_INNR : 0 (default) - No debugging information is collected. % 1 (debugging purpose) - History of computation is returned by 'HIS' variable. % 2 (debugging purpose) - History of computation is additionally printed on screen. % <Outputs> % W : Obtained basis matrix (r x m). % H : Obtained coefficients matrix (r x n). % iter : Number of iterations. % elapse : CPU time in seconds. % HIS : (debugging purpose) History of computation, % niter - total iteration number spent for Nesterov's optimal % gradient method, % cpus - CPU seconds at iteration rounds, % objf - objective function values at iteration rounds, % dlta - stopping criteria of block coordinate descent. % % <Usage Examples> % >>X=rand(1000,500); % >>ManhNMF(X,10); % >>ManhNMF(X,20,'verbose',1); % >>ManhNMF(X,30,'verbose',2,'w_init',rand(r,m)); % >>ManhNMF(X,5,'verbose',2,'tol_outr',1e-5); % Note: other files 'GetStopCriterion.m', 'ApproxFunC.m', and 'wmedianf.mexw32' should be included under the same % directory as this code.

资源推荐

资源详情

资源评论

收起资源包目录

ManhNMF.rar （8个子文件）

ManhNMF

wmedianf.mexw64 27KB

RandPartDB.m 510B

Demo.m 2KB

ApproxFunC.m 247B

wmedianf.mexw32 20KB

ShowImage.m 1KB

ManhNMF.m 14KB

GetStopCriterion.m 525B

function [W,H,iter,elapse,HIS]=ManhNMF(X,r,varargin) % Manhattan Non-negative Matrix Factorization. % ManhNMF: Matlab Code for Efficient Robust Manhattan NMF Solver % Reference % [1] N. Guan, D. Tao, Z. Luo, and J. Shawe-taylor, "MahNMF: Manhattan % Non-negative Matrix Factorization," arXiv:1207.3438v1, 2012. % [2] N. Guan, D. Tao, Z. Luo, and J. Shawe-taylor, "MahNMF: Manhattan % Non-negative Matrix Factorization," Submitted to Journal of Machine Learning Research, 2013. % The model is X \approx W^TH, where X, W, and H are defined as follows: % X (m x n): data matrix including n samples in m-dimensional space; % W (r x m): basis matrix including r bases in m-dimensional space; % H (r x n): coefficients matrix includeing n encodings in r-dimensional space. % Written by Naiyang Guan (ny.guan@gmail.com) % Copyright 2012-2014 by Naiyang Guan and Dacheng Tao % Modified at Jan. 28 2013 % <Inputs> % X : Input data matrix (m x n) % r : Target low-rank % % (Below are optional arguments: can be set by providing name-value pairs) % MAX_ITER : Maximum number of iterations. Default is 1,000. % MIN_ITER : Minimum number of iterations. Default is 10. % MAX_TIME : Maximum amount of time in seconds. Default is 100,000. % W_INIT : (m x r) initial value for W. % H_INIT : (r x n) initial value for H. % LAM_INIT : initial value of smoothness parameter. Default is 1. % MDL_TYPE : Model type (Default is 'PLAIN'), % 'PLAIN' - MahNMF (min{||X-W^T*H||_1,s.t.,W >= 0 and H >= 0}.), % 'BXC' - Box Constrained MahNMF (min{||X-W^T*H||_1,s.t.,1 >= W >= 0 and 1 >= H >= 0}.), % 'MNR' - Manifold Regularized MahNMF % (min{||X-W^T*H||_1+.5*beta*TR(H*Lp*H^T),s.t.,W >= 0 and H >= 0}.), % 'GSP' - Group Sparse MahNMF % (min{||X-W^T*H||_1+.5*beta*\sum_{g\in G}||W^[g]||_{1,p},s.t.,W >= 0 and H >= 0}.), % 'SYM' - Symmetric MahNMF (min{||X-H*H^T||_1,s.t., H >= 0}.). % ALG_TYPE : Algorithm type (Default is 'AGD'), % 'AGD' - Accelerated Gradient Descent, % 'RRI' - Rank-one Residue Iteration. % BETA : Tradeoff parameter over regularization term. Default is 1e-3. % SIM_MTX : Similarity matrix constructed by 'constructW'. % GPP_MTX : Group pattern for boundary of all groups. % TOL_INNR : Stopping tolerance of inner iterations. Default is 1e-2. % TOL_OUTR : Stopping tolerance of outer iterations. Default is 1e-3. % If you want to obtain a more accurate solution, decrease TOL_INNR or TOL_OUTR and increase MAX_ITER at the same time. % VB_OUTR : 0 (default) - No debugging information is collected. % 1 (debugging purpose) - History of computation is returned by 'HIS' variable. % 2 (debugging purpose) - History of computation is additionally printed on screen. % VB_INNR : 0 (default) - No debugging information is collected. % 1 (debugging purpose) - History of computation is returned by 'HIS' variable. % 2 (debugging purpose) - History of computation is additionally printed on screen. % <Outputs> % W : Obtained basis matrix (r x m). % H : Obtained coefficients matrix (r x n). % iter : Number of iterations. % elapse : CPU time in seconds. % HIS : (debugging purpose) History of computation, % niter - total iteration number spent for Nesterov's optimal % gradient method, % cpus - CPU seconds at iteration rounds, % objf - objective function values at iteration rounds, % dlta - stopping criteria of block coordinate descent. % % <Usage Examples> % >>X=rand(1000,500); % >>ManhNMF(X,10); % >>ManhNMF(X,20,'verbose',1); % >>ManhNMF(X,30,'verbose',2,'w_init',rand(r,m)); % >>ManhNMF(X,5,'verbose',2,'tol_outr',1e-5); % Note: other files 'GetStopCriterion.m', 'ApproxFunC.m', and 'wmedianf.mexw32' should be included under the same % directory as this code. if ~exist('X','var'), error('please input the sample matrix.\n'); end if ~exist('r','var'), error('please input the low rank.\n'); end [m,n]=size(X); % Default setting MaxIter=1000; MinIter=10; MaxTime=10000; W0=rand(r,m); H0=rand(r,n); lambda0 = 1; mdl_type='PLAIN'; alg_type='AGD'; beta=1e-3; tol_outr=1e-3; tol_innr=1e-2; vb_outr=0; vb_innr=0; % Read optional parameters if (rem(length(varargin),2)==1) error('Optional parameters should always go by pairs'); else for i=1:2:(length(varargin)-1) switch upper(varargin{i}) case 'MAX_ITER', MaxIter=varargin{i+1}; case 'MIN_ITER', MinIter=varargin{i+1}; case 'MAX_TIME', MaxTime=varargin{i+1}; case 'W_INIT', W0=varargin{i+1}; case 'H_INIT', H0=varargin{i+1}; case 'LAM_INIT', lambda0=varargin{i+1}; case 'MDL_TYPE', mdl_type=upper(varargin{i+1}); case 'ALG_TYPE', alg_type=upper(varargin{i+1}); case 'BETA', beta=varargin{i+1}; case 'SIM_MTX', S=varargin{i+1}; case 'TOL_OUTR', tol_outr=varargin{i+1}; case 'TOL_INNR', tol_innr=varargin{i+1}; case 'VB_OUTR', vb_outr=varargin{i+1}; case 'VB_INNR', vb_innr=varargin{i+1}; otherwise error(['Unrecognized option: ',varargin{i}]); end end end ITER_MAX=1000; % maximum inner iteration number (Default) ITER_MIN=10; % minimum inner iteration number (Default) global STOP_RULE; STOP_RULE = 1; % '1' for Projected gradient norm (Default) % '2' for Normalized projected gradient norm % '3' for Normalized KKT residual % Initialization switch (alg_type), case 'AGD', W=W0; H=H0; case 'RRI', W=W0; H=H0; fprintf('NRRI: please make sure that the initial points contain small entries.\n'); otherwise, error('No such algorithm (%s).\n',alg_type); end switch (mdl_type), case 'PLAIN', case 'BXC', case 'MNR', if ~exist('S','var'), error('Similarity matrix must be collected for NeNMF-MR.\n'); end D=diag(sum(S)); Lp=D-S; if ~issparse(Lp), LpC=norm(Lp); % Lipschitz constant of MR term else LpC=norm(full(Lp)); end case 'GSP', case 'SYM', otherwise error('No such model (%s).\n',mdl_type); end % Historical information HIS.objf=0; % Historical objective values HIS.niter=0; % Historical iteration numbers HIS.cpus=0; % Historical CPU seconds switch (mdl_type), case 'PLAIN', E = X-W'*H; % Residue matrix HIS.objf(1)=sum(abs(E(:))); case 'BXC', E = X-W'*H; HIS.objf(1)=sum(abs(E(:))); case 'MNR', E = X-W'*H; HIS.objf(1)=sum(abs(E(:)))+.5*beta*sum(sum((H'*H).*Lp)); case 'GSP', E = X-W'*H; HIS.objf(1)=sum(abs(E(:))); case 'SYM', H = H'; % W=H' in this case E = X-H*H'; HIS.objf(1)=sum(abs(E(:))); otherwise, error('No such model (%s).\n',mdl_type); end if vb_outr==2, fprintf('\nManhNMF (%s) by %s starts,\tinitial objective value = %f.\n', mdl_type,alg_type,HIS.objf(1)); end % Iterative updating tolH=tol_innr; tolW=tolH; elapse=cputime; for iter=1:MaxIter, % Optimize H with W fixed if vb_outr==2, fprintf('\tOptimize H ...\n'); end switch (mdl_type), case 'PLAIN', switch (alg_type), case 'AGD', [H,E,iterH]=NLAD_AGD

评论收藏

内容反馈