Alex Open Research Wiki

Tag: training-dynamics

5 items with this tag.

  • May 29, 2026

    Training Dynamics

    • training-dynamics
    • optimization
    • sharpness
    • sgd
    • compression
    • continual-learning
    • block-wise-training
  • May 28, 2026

    DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation

    • block-wise-training
    • diffusion
    • memory-efficient-training
    • training-dynamics
    • recurrent-depth
    • llm-post-training
    • private-adaptation
  • May 24, 2026

    Learning to Forget: Continual Learning with Adaptive Weight Decay

    • continual-learning
    • adaptive-weight-decay
    • forgetting
    • meta-learning
    • training-dynamics
  • May 24, 2026

    Learning is Forgetting: LLM Training As Lossy Compression

    • training-dynamics
    • lossy-compression
    • information-bottleneck
    • llm-interpretability
    • representation-learning
  • May 24, 2026

    SGD at the Edge of Stability: The Stochastic Sharpness Gap

    • training-dynamics
    • sgd
    • edge-of-stability
    • sharpness

Created with Quartz v4.5.2 © 2026