#adamw
Adamw: 2 AI articles covering adamw news, analysis, and research
Articles
Don't Just "Throw Adam at It": Misunderstanding Adam Will Cost Youβ10
Don't blindly use default AdamW parameters. Tuning beta values, especially in reinforcement learning, can be the crucial fix when nothing else
The Active Ingredient in Muon's Grokkingβ8
Ablation study reveals Muon's grokking speedup comes from orthogonalization, not spectral constraints. Newton-Schulz iteration reduces spectral norm by
