Search Results for author:
Found 4 papers, 2 papers with code
Utilizing Expert Features for Contrastive Learning of Time-Series Representations
We therefore devise ExpCLR, a novel contrastive learning approach built on an objective that utilizes expert features to encourage both properties for the learned representation.
SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning
We validate SOSP-H by comparing it to our second method SOSP-I that uses a well-established Hessian approximation, and to numerous state-of-the-art methods.
Which Minimizer Does My Neural Network Converge To?
The loss surface of an overparameterized neural network (NN) possesses many global minima of zero training error.
Wide Neural Networks are Interpolating Kernel Methods: Impact of Initialization on Generalization
The recently developed link between strongly overparametrized neural networks (NNs) and kernel methods has opened a new way to understand puzzling features of NNs, such as their convergence and generalization behaviors.
