Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Transformers as Generic Deep Neural Networks: Exact Compilation, the Cost of Removing Activation-Activation Products, and Multi-Agent Attention Clustering
Sergey Salishev, Zeev Volkovich, Oleg Granichin
Transformers are deployed as a special model class. Neural processing units (NPU) add dedicated operators for attention and normalization, and quantization relies on Transformer-sp…
cs.LG2026
Local Stability and Gaussian Smoothing of Quantized Neural Networks
Sergey Salishev, Anton Makarov, Oleg Granichin
We study Gaussian averaging as a smooth surrogate for quantized neural models. Under bounded local oscillation, we derive a local dimension-dependent bound on |f-g|, linking Gaussi…
cs.LG2025
GDNSQ: Gradual Differentiable Noise Scale Quantization for Low-bit Neural Networks
Sergey Salishev, Ian Akhremchik
Quantized neural networks can be viewed as a chain of noisy channels, where rounding in each layer reduces capacity as bit-width shrinks; the floating-point (FP) checkpoint sets th…