AI RESEARCH

Compander-Aligned Query Geometry for Quantized Zeroth-Order Optimization

arXiv CS.LG

ArXi:2605.10673v1 Announce Type: new Low-bit forward evaluation is an attractive route to memory-efficient zeroth-order (ZO) adaptation: the optimizer needs only scalar losses, and the model can be queried near deployment precision. The obstacle is that a quantized ZO query is not a continuous finite difference followed by harmless storage rounding. The query chooses endpoints, the low-precision engine rounds them, and the loss difference is measured along the rounded chord.