324 citations · 1.4k across the 135 of their papers we have counts for
156 papers
Scale Sensitivity in Low-Bit Post-Training Quantization: Curvature of the Quantization Error Landscape
Jonas von Berg, Massimiliano Datres, Carlo Kneißl +1
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 deg…
Polyhedral Geometry of Time-to-First-Spike Neural Networks
Manjot Singh, Guido Montúfar, Gitta Kutyniok
We study the expressivity of spiking neural networks, which provide a natural framework for asynchronous, event-driven computation complementary to conventional feedforward neural…
Functional Degeneracy in Neural Networks: Measurement and Pruning
Maria Matveev, Pascal Esser, Ayush Bharadwaj +2
A central question in modern machine learning is how much a trained model can be compressed without changing its behavior, to reduce the memory, compute and energy required to depl…
Towards an Expressivity-Normalized Energy-Demand Comparison of ANNs and SNNs
Miriam Kranzlmüller, Pascal Esser, Gitta Kutyniok
Spiking neural networks (SNNs) are often regarded as energy-efficient alternatives to artificial neural networks (ANNs), yet their advantage depends critically on both network arch…
Sparse-Aware Neural Networks for Nonlinear Functionals: Mitigating the Exponential Dependence on Dimension
Jianfei Li, Shuo Huang, Han Feng +2
Deep neural networks have emerged as powerful tools for learning operators defined over infinite-dimensional function spaces. However, existing theories frequently encounter diffic…
Adaptive-CaRe: Adaptive Causal Regularization for Robust Outcome Prediction
Nithya Bhasker, Fiona R. Kolbinger, Susu Hu +2
Accurate prediction of outcomes is crucial for clinical decision-making and personalized patient care. Supervised machine learning algorithms, which are commonly used for outcome p…