3 papers
cs.CC2026
Graded Projection Recursion (GPR): Corrections, Obstructions, and Conservative Approximate Matrix Multiplication
Jeffrey Uhlmann
Earlier versions proposed Graded Projection Recursion (GPR) as a deterministic packed-recursion framework for model-honest near-quadratic dense matrix multiplication. This revised…
cs.LG2026
Unit-Consistent (UC) Adjoint for GSD and Backprop in Deep Learning Applications
Jeffrey Uhlmann
Deep neural networks constructed from linear maps and positively homogeneous nonlinearities (e.g., ReLU) possess a fundamental gauge symmetry: the network function is invariant to…
cs.LG2025
The Fourth State: Signed-Zero Ternary for Stable LLM Quantization (and More)
Jeffrey Uhlmann
Quantization is usually regarded as a means to trade quality of performance for reduced compute requirements, i.e., as a suboptimal approximation. However, if examined in terms of…