Follow
Anirbit Mukherjee
Anirbit Mukherjee
Department of Computer Science, The University of Manchester
Verified email at manchester.ac.uk - Homepage
Title
Cited by
Cited by
Year
Understanding deep neural networks with rectified linear units
R Arora, A Basu, P Mianjy, A Mukherjee
The International Conference on Learning Representations (ICLR) 2018, 2016
8022016
Convergence guarantees for RMSProp and ADAM in non-convex optimization and their comparison to Nesterov acceleration on autoencoders
S De, A Mukherjee, E Ullah
arXiv preprint arXiv:1807.06766, 2018
164*2018
Sparse coding and autoencoders
A Rangamani, A Mukherjee, A Basu, A Arora, T Ganapathi, S Chin, ...
2018 IEEE International Symposium on Information Theory (ISIT), 36-40, 2018
29*2018
Lower bounds over Boolean inputs for deep neural networks with ReLU gates
A Mukherjee, A Basu
arXiv preprint arXiv:1711.03073, 2017
242017
Provable training of a ReLU gate with an iterative non-gradient algorithm
S Karmakar, A Mukherjee
Neural Networks, 2022
13*2022
Depth-2 neural networks under a data-poisoning attack
S Karmakar, A Mukherjee, T Papamarkou
Neurocomputing 532, 56-66, 2023
62023
Towards Size-Independent Generalization Bounds for Deep Operator Nets
P Gopalani, S Karmakar, D Kumar, A Mukherjee
arXiv preprint arXiv:2205.11359, 2022
6*2022
A Study of the Mathematics of Deep Learning
A Mukherjee
Johns Hopkins University, 2020
52020
Global Convergence of SGD On Two Layer Neural Nets
P Gopalani, A Mukherjee
arXiv preprint arXiv:2210.11452, 2022
22022
Investigating the Ability of PINNs to Solve Burgers’ PDE Near Finite-Time Blowup
D Kumar, A Mukherjee
Machine Learning: Science and Technology 5 (2), 025063, 2024
12024
Size Lowerbounds for Deep Operator Networks
A Mukherjee, A Roy
Transactions on Machine Learning Research, 2024
12024
Global Convergence of SGD For Logistic Loss on Two Layer Neural Nets
P Gopalani, S Jha, A Mukherjee
Transactions on Machine Learning Research, 2024
12024
Investigating the Role of Overparameterization While Solving the Pendulum with DeepONets
P Gopalani, A Mukherjee
The Symbiosis of Deep Learning and Differential Equations, 2021
12021
Improving PINNs By Algebraic Inclusion of Boundary and Initial Conditions
M Ren, Z Fang, K Li, A Mukherjee
arXiv preprint arXiv:2407.20741, 2024
2024
Regularized Gradient Clipping Provably Trains Wide and Deep Neural Networks
M Tucat, A Mukherjee
arXiv preprint arXiv:2404.08624, 2024
2024
LIPEx--Locally Interpretable Probabilistic Explanations--To Look Beyond The True Class
H Zhu, A Cangelosi, P Sen, A Mukherjee
arXiv preprint arXiv:2310.04856, 2023
2023
An Empirical Study of the Occurrence of Heavy-Tails in Training a ReLU Gate
S Karmakar, A Mukherjee
arXiv preprint arXiv:2204.12554, 2022
2022
Dynamics of Local Elasticity During Training of Neural Nets
S Dan, A Mukherjee, A Das, P Gampa
arXiv preprint arXiv:2111.01166, 2021
2021
Identifying stochastic oracles for fast convergence of RMSProp
AM Jiayao Zhang
Deep Math 2020, 2020
2020
Improving PAC-Bayes bounds on risk of neural nets using geometrical properties of training
A Mukherjee, D Roy, P Rastogi, J Yang
ICML 2019 Workshop, Understanding and Improving Generalization in Deep Learning, 2019
2019
The system can't perform the operation now. Try again later.
Articles 1–20