<?xml version="1.0" encoding="UTF-8"?><urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"><url><loc>https://mbrenndoerfer.com/writing/weight-decay-decoupled-adamw-regularization-l2/weight-decay</loc><lastmod>2026-01-27T23:29:13.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/weight-decay-decoupled-adamw-regularization-l2/the-weight-decay-penalty</loc><lastmod>2026-01-27T23:29:13.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/weight-decay-decoupled-adamw-regularization-l2/a-worked-example-weight-decay-step-by-step</loc><lastmod>2026-01-27T23:29:13.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/weight-decay-decoupled-adamw-regularization-l2/decoupled-weight-decay-and-adamw</loc><lastmod>2026-01-27T23:29:13.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/weight-decay-decoupled-adamw-regularization-l2/which-parameters-should-receive-weight-decay</loc><lastmod>2026-01-27T23:29:13.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/weight-decay-decoupled-adamw-regularization-l2/choosing-the-weight-decay-coefficient</loc><lastmod>2026-01-27T23:29:13.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/weight-decay-decoupled-adamw-regularization-l2/code-implementation</loc><lastmod>2026-01-27T23:29:13.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/weight-decay-decoupled-adamw-regularization-l2/weight-decay-in-transformer-training</loc><lastmod>2026-01-27T23:29:13.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/weight-decay-decoupled-adamw-regularization-l2/limitations-and-practical-considerations</loc><lastmod>2026-01-27T23:29:13.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/weight-decay-decoupled-adamw-regularization-l2/summary</loc><lastmod>2026-01-27T23:29:13.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/weight-decay-decoupled-adamw-regularization-l2/quiz</loc><lastmod>2026-01-27T23:29:13.000Z</lastmod></url></urlset>