8 papers
Power-MSE trade-off of Factorized Low-rank Approximated Computation Scheme with Memristors
Binyu Lu, Matthias Frey, Stark Draper +1
Memristor crossbars enable analog vector-matrix multiplication (VMM) which is promising for machine learning applications. Scaling matrix entries to lower memristor conductance lev…
Capacity regimes for Boolean function computation via channels
Jingge Zhu, Matthias Frey
Consider a point-to-point communication system in which the transmitter holds a binary message of length and transmits a corresponding codeword of length . The receiver's go…
Universal Denoising without Channel Knowledge
Matthias Frey, Jonathan H. Manton, Jingge Zhu
Inspired by a classical algorithm for online prediction, we propose a novel denoising scheme which is universal for families of probability distributions both in terms of the sourc…
On Unified and Sharpened CMI Bounds for Generalization Errors
Yang Lu, Matthias Frey, Margreta Kuijper +1
We present a new family of information-theoretic generalization bounds within the framework of conditional mutual information (CMI). Most of our results are established based on th…
Online Prediction of Stochastic Sequences with High Probability Regret Bounds
Matthias Frey, Jonathan H. Manton, Jingge Zhu
We revisit the classical problem of universal prediction of stochastic sequences with a finite time horizon known to the learner. The question we investigate is whether it is p…
Block-Sample MAC-Bayes Generalization Bounds
Matthias Frey, Jingge Zhu, Michael C. Gastpar
We present a family of novel block-sample MAC-Bayes bounds (mean approximately correct). While PAC-Bayes bounds (probably approximately correct) typically give bounds for the gener…
Beyond Identification: Computing Boolean Functions via Channels
Jingge Zhu, Matthias Frey
Consider a point-to-point communication system in which the transmitter holds a binary message of length and transmits a corresponding codeword of length . The receiver's go…
Low-Rank-Based Approximate Computation with Memristors
Binyu Lu, Matthias Frey, Stark Draper +1
Memristor crossbars enable vector-matrix multiplication (VMM), and are promising for low-power applications. However, it can be difficult to write the memristor conductance values…