Pulkit Gopalani

According to our database, Pulkit Gopalani authored at least 7 papers between 2021 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers.

Pulkit Gopalani, Wei Hu

CoRR, June, 2025

2024

Towards Size-Independent Generalization Bounds for Deep Operator Nets.

Pulkit Gopalani, Sayar Karmakar, Dibyakanti Kumar, Anirbit Mukherjee

Trans. Mach. Learn. Res., 2024

Global Convergence of SGD For Logistic Loss on Two Layer Neural Nets.

Pulkit Gopalani, Samyak Jha, Anirbit Mukherjee

Trans. Mach. Learn. Res., 2024

Abrupt Learning in Transformers: A Case Study on Matrix Completion.

Pulkit Gopalani, Ekdeep Singh Lubana, Wei Hu

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

2022

Global Convergence of SGD On Two Layer Neural Nets.

Pulkit Gopalani, Anirbit Mukherjee

CoRR, 2022

Capacity Bounds for the DeepONet Method of Solving Differential Equations.

Pulkit Gopalani, Sayar Karmakar, Anirbit Mukherjee

CoRR, 2022

2021

On Adversarial Robustness: A Neural Architecture Search perspective.

Chaitanya Devaguptapu, Devansh Agarwal, Gaurav Mittal, Pulkit Gopalani, Vineeth N. Balasubramanian

Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, 2021