Nikhil Ghosh

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 17

Top Topics

Linear Predictors

Landmark Extraction

Top Venues

Publications

James B. Simon, Dhruva Karkada, Nikhil Ghosh, Mikhail Belkin
More is Better: when Infinite Overparameterization is Optimal and Overfitting is Obligatory. ICLR (2024)
Soufiane Hayou, Nikhil Ghosh, Bin Yu
LoRA+: Efficient Low Rank Adaptation of Large Models. CoRR (2024)
Soufiane Hayou, Nikhil Ghosh, Bin Yu
The Impact of Initialization on LoRA Finetuning Dynamics. CoRR (2024)
James B. Simon, Dhruva Karkada, Nikhil Ghosh, Mikhail Belkin
More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory. CoRR (2023)
Cenk Baykal, Dylan J. Cutler, Nishanth Dikkala, Nikhil Ghosh, Rina Panigrahy, Xin Wang
The Power of External Memory in Increasing Predictive Model Capacity. CoRR (2023)
Cenk Baykal, Dylan J. Cutler, Nishanth Dikkala, Nikhil Ghosh, Rina Panigrahy, Xin Wang
Alternating Updates for Efficient Transformers. NeurIPS (2023)
Cenk Baykal, Dylan Cutler, Nishanth Dikkala, Nikhil Ghosh, Rina Panigrahy, Xin Wang
Alternating Updates for Efficient Transformers. CoRR (2023)
Nikhil Ghosh, Mikhail Belkin
A Universal Trade-off Between the Model Size, Test Loss, and Training Loss of Linear Predictors. SIAM J. Math. Data Sci. 5 (4) (2023)
Nishanth Dikkala, Nikhil Ghosh, Raghu Meka, Rina Panigrahy, Nikhil Vyas, Xin Wang
On the Benefits of Learning to Route in Mixture-of-Experts Models. EMNLP (2023)
Gal Kaplun, Nikhil Ghosh, Saurabh Garg, Boaz Barak, Preetum Nakkiran
Deconstructing Distributions: A Pointwise Framework of Learning. ICLR (2023)
Nikhil Ghosh, Spencer Frei, Wooseok Ha, Bin Yu
The Effect of SGD Batch Size on Autoencoder Learning: Sparsity, Sharpness, and Feature Learning. CoRR (2023)
Nikhil Ghosh, Song Mei, Bin Yu
The Three Stages of Learning Dynamics in High-dimensional Kernel Methods. ICLR (2022)
Gal Kaplun, Nikhil Ghosh, Saurabh Garg, Boaz Barak, Preetum Nakkiran
Deconstructing Distributions: A Pointwise Framework of Learning. CoRR (2022)
Nikhil Ghosh, Mikhail Belkin
A Universal Trade-off Between the Model Size, Test Loss, and Training Loss of Linear Predictors. CoRR (2022)
Nikhil Ghosh, Song Mei, Bin Yu
The Three Stages of Learning Dynamics in High-Dimensional Kernel Methods. CoRR (2021)
Nikhil Ghosh, Yuxin Chen, Yisong Yue
Landmark Ordinal Embedding. CoRR (2019)
Nikhil Ghosh, Yuxin Chen, Yisong Yue
Landmark Ordinal Embedding. NeurIPS (2019)