Undersampling　accelerates　signal　acquisition　at　the　expense　of　introducing　artifacts.　Removing　these　artifacts　is　a　fundamental　problem　in　signal　processing　and　this　task　is　also　called　signal　reconstruction.　Through　modeling　signals　as　the　superimposed　exponential　functions,　deep　learning　has　achieved　fast　and　high-fidelity　signal　reconstruction　by　training　a　mapping　from　the　undersampled　exponentials　to　the　fully　sampled　ones.　However,　the　mismatch,　such　as　undersampling　rates　(25　%　vs.　50　%),　anatomical　region　(knee　vs.　brain),　and　contrast　configurations　(PDw　vs.　T2w),　between　the　training　and　target　data　will　heavily　compromise　the　reconstruction.　To　overcome　this　limitation,　we　propose　Alternating　Deep　Low-Rank　(ADLR),　which　combines　deep　learning　solvers　and　classic　optimization　solvers.　Experimental　validation　on　the　reconstruction　of　synthetic　and　realworld　biomedical　magnetic　resonance　signals　demonstrates　that　ADLR　can　effectively　alleviate　the　mismatch　issue　and　achieve　lower　reconstruction　errors　than　state-of-the-art　methods.