Search Results for author:
Found 7 papers, 0 papers with code
Learning to Prune Instances of Steiner Tree Problem in Graphs
In this paper, we use this learning framework on the Steiner tree problem and show that even on this problem, the learning-to-prune framework results in computing near-optimal solutions at a fraction of the time required by commercial ILP solvers.
Variational Autoencoder with CCA for Audio-Visual Cross-Modal Retrieval
On the one hand, audio encoder and visual encoder separately encode audio data and visual data into two different latent spaces.
Simultaneous Imaging Achiral and Chiral Domains beyond Diffraction Limit by Structured-illumination Microscopy
Chiral SIM is suitable for imaging chiral domains at sub-wavelength resolution but loses the high spatial frequency of the achiral ones.
Image Reconstruction
Super-Resolution
Optics
Biological Physics
Sharp pointwise-in-time error estimate of L1 scheme for nonlinear subdiffusion equations
An essential feature of the subdiffusion equations with the $\alpha$-order time fractional derivative is the weak singularity at the initial time.
Numerical Analysis Numerical Analysis 65M06, 65M12, 65M15, 35R11 F.2.2
Plasmonic elliptical nanoholes for chiroptical analysis and enantioselective optical trapping
Under linearly polarized excitation, an elliptical nanohole in a thin gold film can generate a localized chiral optical field for chiroptical analysis and simultaneously serve as a near-field optical trap to capture dielectric and plasmonic nanospheres.
Optics Mesoscale and Nanoscale Physics Materials Science Applied Physics Chemical Physics
Frequency Principle in Deep Learning Beyond Gradient-descent-based Training
Frequency perspective recently makes progress in understanding deep learning.
A priori generalization error for two-layer ReLU neural network through minimum norm solution
We first estimate \emph{a priori} generalization error of finite-width two-layer ReLU NN with constraint of minimal norm solution, which is proved by \cite{zhang2019type} to be an equivalent solution of a linearized (w. r. t.
