Post-training quantization (PTQ) methods in the GPTQ family minimize a layer-wise reconstruction error on a uniform grid whose scale must be chosen; the common max-based choice degrades sharply at low bit-widths. We study how sensitive this objective is to the scale. For a layer with i.i.d. Gaussian weights and calibra...
Jonas von Berg, Massimiliano Datres, Carlo Kneissl et al.· 0 citations
We study the expressivity of spiking neural networks, which provide a natural framework for asynchronous, event-driven computation complementary to conventional feedforward neural networks. We consider the time-to-first-spike model in a setting for which the input-output map is continuous and piecewise linear, with aff...
A family of premetrics that capture different degrees of structural similarity between graphs are introduced and relate these similarities to generalization, and consequently, the performance of expressive GNNs are related.
This work quantifies functional degeneracy through the behavioral recovery rank, defined as the number of leading behavioral-Hessian eigendirections required to recover a trained model's performance, and finds that structural and magnitude pruning retain more degrees of freedom, even after the task is saturated.
M. Matveev, P. Esser, Ayush Bharadwaj et al.· 0 citations
An analytical framework is developed to compare fully-connected ReLU ANNs and integrate-and-fire SNNs for time-series data with respect to their theoretical energy efficiency at matched expressive capacity, and derives an expressivity-normalized efficiency ratio and explicit thresholds in network width, spike sparsity,...
Miriam Kranzlmüller, P. Esser, Gitta Kutyniok· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
