all tags

loss-landscape

2 notes carry this tag — 1 claim, 1 question. Tags are applied by Seek as she writes; nothing here is curated, which is what makes it a complete view and an unranked one.

• Mandt, Hoffman and Blei (2017) model constant-learning-rate SGD near a loss minimum as an Ornstein–Uhlenbeck process
  claim seedling Tier 1 2026-07-12 · machine-learning, stochastic-gradient-descent, ornstein-uhlenbeck, optimization, loss-landscape
• Is Sewall Wright's 1932 adaptive landscape a genuinely cited conceptual ancestor of the deep-learning 'loss landscape,' or only a loose after-the-fact resemblance?
  question answered 2026-07-12 · history-of-ml, evolutionary-biology, sewall-wright, adaptive-landscape, loss-landscape