Nikhil Ghosh

According to our database, Nikhil Ghosh authored at least 18 papers between 2019 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2026

There Will Be a Scientific Theory of Deep Learning.

Jamie Simon, Daniel Kunin, Alexander B. Atanasov, Enric Boix-Adserà, Blake Bordelon, Jeremy Cohen, Nikhil Ghosh, Florentin Guth, Arthur Jacot, Mason Kamb, Dhruva Karkada, Eric J. Michaud, Berkan Ottlik, Joseph Turnbull

CoRR, April, 2026

Does a Global Perspective Help Prune Sparse MoEs Elegantly?

Zeliang Zhang, Nikhil Ghosh, Jiani Liu, Bin Yu, Xiaodong Liu

CoRR, April, 2026

2025

Understanding the Mechanisms of Fast Hyperparameter Transfer.

Nikhil Ghosh, Denny Wu, Alberto Bietti

CoRR, December, 2025

GSM-Agent: Understanding Agentic Reasoning Using Controllable Environments.

Hanlin Zhu, Tianyu Guo, Song Mei, Stuart Russell, Nikhil Ghosh, Alberto Bietti, Jiantao Jiao

CoRR, September, 2025

PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models.

Soufiane Hayou, Nikhil Ghosh, Bin Yu

CoRR, June, 2025

The Effect of SGD Batch Size on Autoencoder Learning: Sparsity, Sharpness, and Feature Learning.

Nikhil Ghosh, Spencer Frei, Wooseok Ha, Bin Yu

J. Mach. Learn. Res., 2025

2024

The Impact of Initialization on LoRA Finetuning Dynamics.

Soufiane Hayou, Nikhil Ghosh, Bin Yu

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

LoRA+: Efficient Low Rank Adaptation of Large Models.

Soufiane Hayou, Nikhil Ghosh, Bin Yu

Proceedings of the Forty-first International Conference on Machine Learning, 2024

More is Better: when Infinite Overparameterization is Optimal and Overfitting is Obligatory.

James B. Simon, Dhruva Karkada, Nikhil Ghosh, Mikhail Belkin

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

A Universal Trade-off Between the Model Size, Test Loss, and Training Loss of Linear Predictors.

Nikhil Ghosh, Mikhail Belkin

SIAM J. Math. Data Sci., December, 2023

More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory.

James B. Simon, Dhruva Karkada, Nikhil Ghosh, Mikhail Belkin

CoRR, 2023

The Power of External Memory in Increasing Predictive Model Capacity.

Cenk Baykal, Dylan J. Cutler, Nishanth Dikkala, Nikhil Ghosh, Rina Panigrahy, Xin Wang

CoRR, 2023

Alternating Updates for Efficient Transformers.

Cenk Baykal, Dylan J. Cutler, Nishanth Dikkala, Nikhil Ghosh, Rina Panigrahy, Xin Wang

CoRR, 2023

Alternating Updates for Efficient Transformers.

Cenk Baykal, Dylan J. Cutler, Nishanth Dikkala, Nikhil Ghosh, Rina Panigrahy, Xin Wang

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Deconstructing Distributions: A Pointwise Framework of Learning.

Gal Kaplun, Nikhil Ghosh, Saurabh Garg, Boaz Barak, Preetum Nakkiran

Proceedings of the Eleventh International Conference on Learning Representations, 2023

On the Benefits of Learning to Route in Mixture-of-Experts Models.

Nishanth Dikkala, Nikhil Ghosh, Raghu Meka, Rina Panigrahy, Nikhil Vyas, Xin Wang

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

2022

The Three Stages of Learning Dynamics in High-dimensional Kernel Methods.

Nikhil Ghosh, Song Mei, Bin Yu

Proceedings of the Tenth International Conference on Learning Representations, 2022

2019

Landmark Ordinal Embedding.

Nikhil Ghosh, Yuxin Chen, Yisong Yue

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019