no code implementations • 17 Sep 2023 • Pulkit Gopalani, Samyak Jha, Anirbit Mukherjee
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.
no code implementations • 20 Oct 2022 • Pulkit Gopalani, Anirbit Mukherjee
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.
no code implementations • 23 May 2022 • Pulkit Gopalani, Sayar Karmakar, Dibyakanti Kumar, Anirbit Mukherjee
In recent times machine learning methods have made significant advances in becoming a useful tool for analyzing physical systems.
no code implementations • NeurIPS Workshop DLDE 2021 • Pulkit Gopalani, Anirbit Mukherjee
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.
1 code implementation • 16 Jul 2020 • Chaitanya Devaguptapu, Devansh Agarwal, Gaurav Mittal, Pulkit Gopalani, Vineeth N Balasubramanian
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.