Shah, Harshay

1. The Pitfalls of Simplicity Bias in Neural Networks
   2020/06/13 by Harshay Shah, Kaustav Tamuly, Shah, Harshay +7 · 24 citations
   Computer Science · #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
2. ContextCite: Attributing Model Generation to Context
   2024/09/01 by Cohen-Wang, Benjamin, Shah, Harshay, Georgiev, Kristian +1 · 19 citations
   #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)
3. Decomposing and Editing Predictions by Modeling Model Computation
   2024/04/17 by Shah, Harshay, Ilyas, Andrew, Madry, Aleksander · 4 citations
   #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
4. Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models
   2025/01/21 by Samira Abnar, Harshay Shah, Abnar, Samira +9 · 7 citations
   Computer Science · #Topic Modeling #Bayesian Methods and Mixture Models #Machine Learning and Algorithms
5. Do Input Gradients Highlight Discriminative Features?
   2021/02/25 by Harshay Shah, Shah, Harshay, Prateek Jain +3 · 2 citations
   Computer Science · #Explainable Artificial Intelligence (XAI) #Adversarial Robustness in Machine Learning #Machine Learning and Data Classification
6. Growing Attributed Networks through Local Processes
   2017/12/29 by Shah, Harshay, Kumar, Suhansanu, Sundaram, Hari · 1 citation
   #FOS: Computer and information sciences #Social and Information Networks (cs.SI)