2002/01/14 by Igor Rivin, Rivin, Igor
Computer Science · #Algorithms and Data Compression #Discrete Mathematics (cs.DM) #FOS: Computer and information sciences #Face and Expression Recognition #I2.6 #Machine Learning (cs.LG) #Machine Learning and Algorithms #cs.DM #cs.LG
paper · pdf · doi:10.48550/arxiv.cs/0201009
Supercedes a part of cs.LG/0107033
arxiv created 2002/01/14 · openalex publication_date 2002/01/14 · arxiv updated 2009/11/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We analyze completely the convergence speed of the batch learning algorithm, and compare its speed to that of the memoryless learning algorithm and of learning with memory. We show that the batch learning algorithm is never worse than the memoryless learning algorithm (at least asymptotically). Its performance vis-a-vis learning with full memory is less clearcut, and depends on certain probabilistic assumptions.