Optimizing Neural Networks with Kronecker-factored Approximate Curvature · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1503.05671/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTOptimizing Neural Networks with Kronecker-factored Approximate Curvature — mentioned by proofofconcepthttps://news.ycombinator.com/item?id=20707612urn:hackerpapers:mention:1503.05671:20707612Thu, 15 Aug 2019 17:43:24 GMT<p>&gt;there is a follow up paper to the DL via Hessian-free optimization paper by James Martens that develops a variant of AD which calculates a special curvature quantity which is useful for efficient second order optimization Deep Learning via Hessian-free Optimization: http://www.cs.toronto.edu/~jmartens/docs/Deep_HessianFree.pd... Optimizing Neural Networks with Kronecker-factored Approximate Curvature: http://arxiv.org/abs/1503.05671 James Martens&#x27; list of publications with links to sample code for the above two papers, slides/condensed conference versions, etc…</p><p><a href="https://hackerpaper.kaipfister.de/p/1503.05671/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG