Doshi, Darshil
- Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks
2024/06/04 by Tianyu He, Darshil Doshi, He, Tianyu +5 · 8 citations
Mathematics · #Cognitive and developmental aspects of mathematical skills #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Computer and information sciences #FOS: Physical sciences #High Energy Physics - Theory (hep-th) #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- To grok or not to grok: Disentangling generalization and memorization on corrupted algorithmic datasets
2023/10/19 by Darshil Doshi, Doshi, Darshil, Aritra Das +5 · 5 citations
Computer Science · #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification
- Grokking Modular Polynomials
2024/06/05 by Darshil Doshi, Tianyu He, Doshi, Darshil +5 · 3 citations
Mathematics · #Mathematics and Applications