10:45官方账号arXiv cs.LG@Aritra Das, Vincent Froese, Moritz Grillo, Debayan Gupta, Christoph Hertrich, Tharrshann Jayan Logarajah, Georg Loho, Mihir More, Moritz Stargalla精选This paper studies the $L_p$-Lipschitz constant computation for two-layer input-convex neural networks (ICNNs), showing that maximizing the $L_p$-norm over a zonotope is W[1]-hard. The results resolve an open problem from COLT'25 and prioritize clear mathematical exposition. Research process, including LLM usage, is described.论文Lipschitz ConstantsInput Convex Neural NetworksZonotopes推荐理由：这篇论文详细解析了ICNNs的$L_p$-Lipschitz常数计算问题，揭示了在Zonotope上最大化$L_p$范数的困难性，对COLT'25的一个未解决问题进行了解答。阅读它，你能了解复杂的数学证明和LLM在研究中的应用。原文稍后读已读值得跟进有用关注 Lipschitz Constants
官方账号arXiv cs.LG@Aritra Das, Vincent Froese, Moritz Grillo, Debayan Gupta, Christoph Hertrich, Tharrshann Jayan Logarajah, Georg Loho, Mihir More, Moritz Stargalla