Search Results for author:
Found 5 papers, 1 papers with code
Global Convergence of SGD For Logistic Loss on Two Layer Neural Nets
In this note, we demonstrate a first-of-its-kind provable convergence of SGD to the global minima of appropriately regularized logistic empirical risk of depth $2$ nets -- for arbitrary data and with any number of gates with adequately smooth and bounded activations like sigmoid and tanh.
Global Convergence of SGD On Two Layer Neural Nets
In this note we demonstrate provable convergence of SGD to the global minima of appropriately regularized $\ell_2-$empirical risk of depth $2$ nets -- for arbitrary data and with any number of gates, if they are using adequately smooth and bounded activations like sigmoid and tanh.
Towards Size-Independent Generalization Bounds for Deep Operator Nets
In recent times machine learning methods have made significant advances in becoming a useful tool for analyzing physical systems.
Investigating the Role of Overparameterization While Solving the Pendulum with DeepONets
DeepONets [1] are one of the most prominent ideas in this theme which entails an optimization over a space of inner-products of neural nets.
On Adversarial Robustness: A Neural Architecture Search perspective
We show that NAS, which is popular for achieving SoTA accuracy, can provide adversarial accuracy as a free add-on without any form of adversarial training.
