Conventional image compression techniques are primarily developed for the human visual system. However, with the extensive use of deep neural networks (DNNs) for computer vision, more and more images will be consumed by DNN-based intelligent machines, which makes it crucial to develop image compression techniques customized for DNN vision while being JPEG compliant. In this paper, we revisit the JPEG rate distortion theory for DNN vision. First, we propose a novel distortion measure, dubbed the sensitivity weighted error (SWE), for DNN vision.

Wireless communication links suffer from outage events caused by fading and interference. To facilitate a tractable analysis of network communication throughput and latency, we propose an outage link model to represent a communication link in the slow fading phenomenon. For a line-topology network with outage links, we study three types of intermediate network node schemes: random linear network coding, store-and-forward, and hop-by-hop retransmission. We provide the analytical formulas for the maximum throughputs and the end-to-end latency for each scheme.

Generative adversarial networks (GANs), modeled as a zero-sum game between a generator (G) and a discriminator (D), allow generating synthetic data with formal guarantees. Noting that D is a classifier, we begin by reformulating the GAN value function using class probability estimation (CPE) losses. We prove a two-way correspondence between CPE loss GANs and f-GANs which minimize f-divergences. We also show that all symmetric f-divergences are equivalent in convergence.

We consider a line network of nodes, connected by additive white noise channels, equipped with local feedback. We study the velocity at which information spreads over this network. For transmission of a data packet, we give an explicit positive lower bound on the velocity, for any packet size. Furthermore, we consider streaming, that is, transmission of data packets generated at a given average arrival rate. We show that a positive velocity exists as long as the arrival rate is below the individual Gaussian channel capacity, and provide an explicit lower bound.

While much of the rapidly growing literature on fair decision-making focuses on metrics for one-shot decisions, recent work has raised the intriguing possibility of designing sequential decision-making to positively impact long-term social fairness. In selection processes such as college admissions or hiring, biasing slightly towards applicants from under-represented groups is hypothesized to provide positive feedback that increases the pool of under-represented applicants in future selection rounds, thus enhancing fairness in the long term.

Federated Learning (FL) is the standard protocol for collaborative learning. In FL, multiple workers jointly train a shared model. They exchange model updates calculated on their data, while keeping the raw data itself local. Since workers naturally form groups based on common interests and privacy policies, we are motivated to extend standard FL to reflect a setting with multiple, potentially overlapping groups.

We consider the Distributed Source Coding (DSC) problem concerning the task of encoding an input in the absence of correlated side information that is only available to the decoder. Remarkably, Slepian and Wolf showed in 1973 that an encoder without access to the side information can asymptotically achieve the same compression rate as when the side information is available to it. This seminal result was later extended to lossy compression of distributed sources by Wyner, Ziv, Berger, and Tung.

The large communication cost for exchanging gradients between different nodes significantly limits the scalability of distributed training for large-scale learning models. Motivated by this observation, there has been significant recent interest in techniques that reduce the communication cost of distributed Stochastic Gradient Descent (SGD), with gradient sparsification techniques such as top-k and random-k shown to be particularly effective.

We consider a finite-armed structured bandit problem in which mean rewards of different arms are known functions of a common hidden parameter 8*. Since we do not place any restrictions on these functions, the problem setting subsumes several previously studied frameworks that assume linear or invertible reward functions. We propose a novel approach to gradually estimate the hidden 8* and use the estimate together with the mean reward functions to substantially reduce exploration of sub-optimal arms.

We study the minimax estimation of α-divergences between discrete distributions for integer α ≥ 1, which include the Kullback-Leibler divergence and the χ2-divergences as special examples. Dropping the usual theoretical tricks to acquire independence, we construct the first minimax rate-optimal estimator which does not require any Poissonization, sample splitting, or explicit construction of approximating polynomials.