arXiv Machine Learning By Victor Felipe Domingues Do Amaral (GeePs), Pierre Demaj (GeePs), Erwan Libessart (GeePs), Laurent Folliot (GeePs), Anthony Kolar (GeePs), Philippe B\'enab\`es (GeePs)

QScheduler: Adaptive Gradient Sampling for Zeroth-Order On-Device Training on INT8 NPUs

Read the original on arXiv Machine Learning →

arXiv:2607. 18802v1 Announce Type: new Abstract: Zeroth-Order (ZO) optimization enables On-Device Learning (ODL) on NPU-equipped microcontrollers by estimating gradients through forward passes alone, bypassing the need for backpropagation primitives and reducing memory requirements.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
Jun 9

Adaptive directional gradients for parameterised quantum circuits

arXiv:2606. 09734v1 Announce Type: cross Abstract: Training parameterised quantum circuits (PQCs) on quantum hardware is bottlenecked by the measurement cost of gradient estimation, which under the parameter-shift rule scales linearly in the number of trainable parameters and dominates the total shot budget of training at scale.

By Brian Coyle, Snehal Raj, Virag Umathe, El Amine Cherrat, Elham Kashefi
arXiv Machine Learning
Aug 4

AOS: Adaptive Optimizer Switching via Training-State Signals for Faster Convergence and Better Generalization

arXiv:2608. 01997v1 Announce Type: new Abstract: Single-optimizer training is a poor fit for the distinct phases of deep network optimization: adaptive methods handle noisy early gradients well but overshoot flat minima, while SGD with momentum generalizes better in the late phase but converges slowly early on.

By Alok Kumar Pandey, Umang Chaturvedi, Aatish Rana, Gopi Krishna Nedanuri