Home Knowledge Base Post-Training Neural Network

Post-Training Neural Network

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Post-Training Neural Network Pruning using Graph Curvature

arXiv:2601.16366v2 Announce Type: replace Abstract: This paper provides a fresh view of the neural network (NN) pruning problem through the lens of graph theory. To achieve effective pruning, we aim to identify the main NN data flows and the corresponding NN connections that are most and least important for the performance of the full model. Unlike the standard approach to NN data flow analysis, which is based on information theory, we employ the notion of graph curvature, specifically...

arXiv CS 9d ago

GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation

arXiv:2606.01412v1 Announce Type: new Abstract: Post-training quantization is widely used for compressing large neural networks, but aggressive low-bit quantization can significantly degrade model quality. A common remedy is to augment the quantized weights with a low-rank correction, leading to approximations of the form $W\approx Q+LR$. In this paper, we study this low-precision plus low-rank representation through the layer-wise reconstruction objective $\|XW-X(Q+LR)\|_F^2$, where $X$ is...

arXiv CS 8d ago

Understanding Quantization-Aware Training: Gradients at Quantized Weights Bias to the Low-Loss Basin

arXiv:2606.09012v1 Announce Type: new Abstract: Post-training quantization (PTQ) converts a trained full-precision model into low-bit weights without task-level retraining, while quantization-aware training (QAT) incorporates quantization into the training loop. Although PTQ is efficient and often accurate at moderate bitwidths, it can fail sharply at aggressive bitwidths; QAT is more expensive but can often recover the lost accuracy. We propose a unified geometric framework that explains...

arXiv CS 1d ago

Generalisation of training-induced recovery in occipital stroke: neurochemical and fMRI correlates

BACKGROUND: Damage to the early visual cortex after an occipital stroke typically results in the loss of conscious vision in the contralateral hemifield. Nonetheless, extensive perceptual training can restore visual motion discrimination in the blind-field. Here, we assessed, in a cohort study, whether improvements transferred to an untrained Gabor detection task and whether awareness within the blind field increased.

bioRxiv 9d ago