Search Results for author:
Found 8 papers, 0 papers with code
Benign Overfitting in Deep Neural Networks under Lazy Training
This paper focuses on over-parameterized deep neural networks (DNNs) with ReLU activation functions and proves that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification while obtaining (nearly) zero-training error under the lazy training regime.
Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study
Neural tangent kernel (NTK) is a powerful tool to analyze training dynamics of neural networks and their generalization bounds.
Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)
In particular, when initialized with LeCun initialization, depth helps robustness with the lazy training regime.
Generalization Properties of NAS under Activation and Skip Connection Search
To this end, we derive the lower (and upper) bounds of the minimum eigenvalue of the Neural Tangent Kernel (NTK) under the (in)finite-width regime using a certain search space including mixed activation functions, fully connected, and residual neural networks.
Controlling the Complexity and Lipschitz Constant improves polynomial nets
While the class of Polynomial Nets demonstrates comparable performance to neural networks (NN), it currently has neither theoretical generalization characterization nor robustness guarantees.
Fully general-relativistic simulations of isolated and binary strange quark stars
The hypothesis that strange quark matter is the true ground state of matter has been investigated for almost four decades, but only a few works have explored the dynamics of binary systems of quark stars.
High Energy Astrophysical Phenomena General Relativity and Quantum Cosmology
Tidal deformability and gravitational-wave phase evolution of magnetised compact-star binaries
Hence, the measurement of these corrections has the potential of providing important information on the equation of state of nuclear matter.
High Energy Astrophysical Phenomena General Relativity and Quantum Cosmology
PSDNet and DPDNet: Efficient channel expansion, Depthwise-Pointwise-Depthwise Inverted Bottleneck Block
To design more efficient lightweight concolutional neural netwok, Depthwise-Pointwise-Depthwise inverted bottleneck block (DPD block) is proposed and DPDNet is designed by stacking DPD block.
