3 papers
cs.CL2026
Algorithmic Stability in Infinite Dimensions: Characterizing Unconditional Convergence in Banach Spaces
Przemysław Spyra
The distinction between conditional, unconditional, and absolute convergence in infinite-dimensional spaces has fundamental implications for computational algorithms. While these c…
cs.LG2025
Energy-Efficient Deep Learning Without Backpropagation: A Rigorous Hardware-Validated Benchmarking Study of Forward-Only Algorithms
Przemysław Spyra, Witold Dzwinel
Backpropagation (BP) powers modern deep learning, but it must hold every activation in memory until a global backward sweep consumes it, and that sweep locks each layer until the o…
cs.LG2025
Beyond Backpropagation: Exploring Innovative Algorithms for Energy-Efficient Deep Neural Network Training
Przemysław Spyra
The rising computational and energy demands of deep neural networks (DNNs), driven largely by backpropagation (BP), challenge sustainable AI development. This paper rigorously inve…