← Back to blog timeline

The Geometry of MoE Compression (Part E)

Expanding on Phase-Collapse: β transfer in FFNs, formal Softmax soundness, and recovering dense performance from quantized layers.

  1. The β-lift and FFN Transfer: MoE Compression Part E

    Why β transfer in FFNs matters for quantization and the formal 'structure bonus' theorems in MoE compression.

  2. Formalizing the Softmax and Hessian: Lean 4 Soundness Proofs

    A deep dive into the Lean 4 proofs for Softmax soundness and the BetaLocalHessian skeleton in the lean-mining project.

  3. Dense Activation-Fit Recovery: Healing Quantized Layers

    How to recover dense performance from quantized layers using activation-fit artifacts and the recovery scripts in lean-mining.