Mukherjee, Anirbit

6 publications

TMLR 2025 Regularized Gradient Clipping Provably Trains Wide and Deep Neural Networks Matteo Tucat, Anirbit Mukherjee, Mingfei Sun, Procheta Sen, Omar Rivasplata

TMLR 2024 Global Convergence of SGD for Logistic Loss on Two Layer Neural Nets Pulkit Gopalani, Samyak Jha, Anirbit Mukherjee

TMLR 2024 Size Lowerbounds for Deep Operator Networks Anirbit Mukherjee, Amartya Roy

TMLR 2024 Towards Size-Independent Generalization Bounds for Deep Operator Nets Pulkit Gopalani, Sayar Karmakar, Dibyakanti Kumar, Anirbit Mukherjee

NeurIPSW 2021 Investigating the Role of Overparameterization While Solving the Pendulum with DeepONets Pulkit Gopalani, Anirbit Mukherjee

ICLR 2018 Understanding Deep Neural Networks with Rectified Linear Units Raman Arora, Amitabh Basu, Poorya Mianjy, Anirbit Mukherjee