Alexander M. Powell

activity

20062026

most citedUncertainty principles for orthonormal sequences

41 citations · 71 across the 8 of their papers we have counts for

collaborators

Showing 2020Show all

3 papers · 1 filter

cs.LG2020

Stochastic Markov Gradient Descent and Training Low-Bit Neural Networks

Jonathan Ashbrock, Alexander M. Powell

The massive size of modern neural networks has motivated substantial recent interest in neural network quantization. We introduce Stochastic Markov Gradient Descent (SMGD), a discr…

cs.IT2020★ 6 cited

High order low-bit Sigma-Delta quantization for fusion frames

Zhen Gao, Felix Krahmer, Alexander M. Powell

We construct high order low-bit Sigma-Delta $(ΣΔ)$ quantizers for the vector-valued setting of fusion frames. We prove that these $ΣΔ$ quantizers can be stably implemented to quant…

math.FA2020

A Schauder basis for $L_{2}$ consisting of non-negative functions

Daniel Freeman, Alexander M. Powell, Mitchell A. Taylor

We prove that $L_{2} (R)$ contains a Schauder basis of non-negative functions. Similarly, $L_{p} (R)$ contains a Schauder basic sequence of non-negative functions such…

Stochastic Markov Gradient Descent and Training Low-Bit Neural Networks

High order low-bit Sigma-Delta quantization for fusion frames

A Schauder basis for L2​ consisting of non-negative functions

A Schauder basis for $L_{2}$ consisting of non-negative functions