Theoretical Guarantees for One-Shot Magnitude Pruning and Compute-Adaptive Early Exit
Read the original on arXiv Machine Learning →The paper investigates how to reduce computation in neural networks by combining one‑shot magnitude pruning in a static setting with early exit in an adaptive setting. In a simplified single‑neuron model it proves a concentration theorem for pruning and introduces a conditional perceptron whose excess error decreases as a power of the compute gap, with the exponent increasing as partial and full computations align. The authors extend these results to deep networks, showing how pruning distortions accumulate with depth and deriving a compute‑accuracy trade‑off for frozen‑backbone early exit under a Gaussian process framework, with numerical simulations supporting the theoretical scaling laws.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.