Nikhil Ghosh

1. LoRA+: Efficient Low Rank Adaptation of Large Models
   2024/02/19 by Soufiane Hayou, Hayou, Soufiane, Nikhil Ghosh +4 · 3 voices · 66 citations
   Computer Science · #Domain Adaptation and Few-Shot Learning #Speech Recognition and Synthesis
2. There Will Be a Scientific Theory of Deep Learning
   2026/04/23 by Jamie Simon, Daniel Kunin, Alexander Atanasov +11 · 31 voices · 1 citation
   #stat.ML #cs.LG
3. Alternating Updates for Efficient Transformers
   2023/01/30 by Cenk Baykal, Dylan Cutler, Baykal, Cenk +9 · 4 citations
   Computer Science · #Topic Modeling #Advanced Neural Network Applications #Advanced Graph Neural Networks
4. More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory
   2023/11/24 by James B. Simon, Dhruva Karkada, Simon, James B. +5 · 3 citations
   Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Machine Learning and Data Classification
5. Landmark Ordinal Embedding
   2019/10/27 by Nikhil Ghosh, Yuxin Chen, Ghosh, Nikhil +3 · 1 citation
   Computer Science · Mathematics · #Data Mining Algorithms and Applications #FOS: Computer and information sciences #Imbalanced Data Classification Techniques #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Statistical Methods and Inference
6. The Effect of SGD Batch Size on Autoencoder Learning: Sparsity, Sharpness, and Feature Learning
   2023/08/06 by Nikhil Ghosh, Spencer Frei, Ghosh, Nikhil +5 · 1 citation
   Computer Science · Physics and Astronomy · #Stochastic Gradient Optimization Techniques #Model Reduction and Neural Networks #Machine Learning and ELM
7. Deconstructing Distributions: A Pointwise Framework of Learning
   2022/02/20 by Gal Kaplun, Nikhil Ghosh, Kaplun, Gal +7 · 1 citation
   Computer Science · #Machine Learning and Data Classification #Explainable Artificial Intelligence (XAI) #Adversarial Robustness in Machine Learning
8. PoLoRA: A Preconditioned Orthogonalized LoRA Optimizer
   2026/07/20 by Nikhil Ghosh, Tetiana Parshakova, Robert M. Gower
   #cs.LG #cs.CL #math.OC