35 citations · 175 across the 34 of their papers we have counts for
44 papers
Do Neural Networks Compress Manifolds Optimally?
Sourbh Bhadane, Aaron B. Wagner, Johannes Ballé
Artificial Neural-Network-based (ANN-based) lossy compressors have recently obtained striking results on several sources. Their success may be ascribed to an ability to identify th…
Functional Covering of Point Processes
Nirmal V. Shende, Aaron B. Wagner
We introduce a new distortion measure for point processes called functional-covering distortion. It is inspired by intensity theory and is related to both the covering of point pro…
On One-Bit Quantization
Sourbh Bhadane, Aaron B. Wagner
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 thresholdin…
Efficiently Computable Converses for Finite-Blocklength Communication
Felipe Areces, Dan Song, Richard Wesel +1
This paper presents a method for computing a finite-blocklength converse for the rate of fixed-length codes with feedback used on discrete memoryless channels (DMCs). The new conve…
The Rate-Distortion-Perception Tradeoff: The Role of Common Randomness
Aaron B. Wagner
A rate-distortion-perception (RDP) tradeoff has recently been proposed by Blau and Michaeli and also Matsumoto. Focusing on the case of perfect realism, which coincides with the pr…
Minimax Rate-Distortion
Adeel Mahmood, Aaron B. Wagner
We show the existence of variable-rate rate-distortion codes that meet the disortion constraint almost surely and are minimax, i.e., strongly, universal with respect to an unknown…