DeepAI AI Chat
Log In Sign Up

On One-Bit Quantization

02/10/2022
by   Sourbh Bhadane, et al.
cornell university
0

We consider the one-bit quantizer that minimizes the mean squared error for a source living in a real Hilbert space. The optimal quantizer is a projection followed by a thresholding operation, and we provide methods for identifying the optimal direction along which to project. As an application of our methods, we characterize the optimal one-bit quantizer for a continuous-time random process that exhibits low-dimensional structure. We numerically show that this optimal quantizer is found by a neural-network-based compressor trained via stochastic gradient descent.

READ FULL TEXT
11/10/2020

Neural Networks Optimally Compress the Sawbridge

Neural-network-based compressors have proven to be remarkably effective ...
11/17/2016

Stochastic Gradient Descent in Continuous Time

Stochastic gradient descent in continuous time (SGDCT) provides a comput...
11/09/2018

Information Theoretic Bounds Based Channel Quantization Design for Emerging Memories

Channel output quantization plays a vital role in high-speed emerging me...
06/24/2020

When Do Neural Networks Outperform Kernel Methods?

For a certain scaling of the initialization of stochastic gradient desce...