arXiv subjects
Publications and source records attributed to Michelle Effros.
We show that the network coding and index coding problems are equivalent. This equivalence holds in the general setting which includes linear and non-linear codes. Specifically, we present an efficient reduction that maps a network coding instance to an index coding one while preserving feasibility. Previous connections were restricted to the linear case.
We consider networks of noisy degraded wiretap channels in the presence of an eavesdropper. For the case where the eavesdropper can wiretap at most one channel at a time, we show that the secrecy capacity region, for a broad class of channels and any given network topology and communication demands, is equivalent to that of a corresponding network where each noisy wiretap channel is replaced by a noiseless wiretap channel. Thus in this case there is a separation between wiretap channel coding on each channel and secure network coding on the resulting noiseless network. We show with an example that such separation does not hold when the eavesdropper can access multiple channels at the same time, for which case we provide upper and lower bounding noiseless networks.
We consider the delay of network coding compared to routing with retransmissions in packet erasure networks with probabilistic erasures. We investigate the sub-linear term in the block delay required for unicasting $n$ packets and show that there is an unbounded gap between network coding and routing. In particular, we show that delay benefit of network coding scales at least as $\sqrt{n}$. Our analysis of the delay function for the routing strategy involves a major technical challenge of computing the expectation of the maximum of two negative binomial random variables. This problem has been studied previously and we derive the first exact characterization which may be of independent interest. We also use a martingale bounded differences argument to show that the actual coding delay is tightly concentrated around its expectation.
In this work we study zero vs. epsilon-error capacity in network coding instances. For multicast network coding it is well known that all rates that can be delivered with arbitrarily small error probability can also be delivered with zero error probability; that is, the epsilon-error multicast capacity region and zero-error multicast capacity region are identical. For general network coding instances in which all sources originate at the same source node, Chan and Grant recently showed [ISIT 2010] that, again, epsilon-error communication has no rate advantage over zero-error communication. We start by revisiting the setting of co-located sources, where we present an alternative proof to that given by Chan and Grant. While the new proof is based on similar core ideas, our constructive strategy complements the previous argument.We then extend our results to the setting of index coding, which is a special and representative form of network coding that encapsulates the "source coding with side information" problem. Finally, we consider the "edge removal" problem (recently studied by Jalali, Effros, and Ho in [Allerton 2010] and [ITA 2011]) that aims to quantify the loss in capacity associated with removing a single edge from a given network. Using our proof for co-located sources, we tie the "zero vs. epsilon-error" problem in general network coding instances with the "edge removal" problem. Loosely speaking, we show that the two problem are equivalent.
In this paper, we demonstrate some applications of compressive sensing over networks. We make a connection between compressive sensing and traditional information theoretic techniques in source coding and channel coding. Our results provide an explicit trade-off between the rate and the decoding complexity. The key difference of compressive sensing and traditional information theoretic approaches is at their decoding side. Although optimal decoders to recover the original signal, compressed by source coding have high complexity, the compressive sensing decoder is a linear or convex optimization. First, we investigate applications of compressive sensing on distributed compression of correlated sources. Here, by using compressive sensing, we propose a compression scheme for a family of correlated sources with a modularized decoder, providing a trade-off between the compression rate and the decoding complexity. We call this scheme Sparse Distributed Compression. We use this compression scheme for a general multicast network with correlated sources. Here, we first decode some of the sources by a network decoding technique and then, we use a compressive sensing decoder to obtain the whole sources. Then, we investigate applications of compressive sensing on channel coding. We propose a coding scheme that combines compressive sensing and random channel coding for a high-SNR point-to-point Gaussian channel. We call this scheme Sparse Channel Coding. We propose a modularized decoder providing a trade-off between the capacity loss and the decoding complexity. At the receiver side, first, we use a compressive sensing decoder on a noisy signal to obtain a noisy estimate of the original signal and then, we apply a traditional channel coding decoder to find the original signal.
This work considers the multiple-access multicast error-correction scenario over a packetized network with $z$ malicious edge adversaries. The network has min-cut $m$ and packets of length $\ell$, and each sink demands all information from the set of sources $\sources$. The capacity region is characterized for both a "side-channel" model (where sources and sinks share some random bits that are secret from the adversary) and an "omniscient" adversarial model (where no limitations on the adversary's knowledge are assumed). In the "side-channel" adversarial model, the use of a secret channel allows higher rates to be achieved compared to the "omniscient" adversarial model, and a polynomial-complexity capacity-achieving code is provided. For the "omniscient" adversarial model, two capacity-achieving constructions are given: the first is based on random subspace code design and has complexity exponential in $\ell m$, while the second uses a novel multiple-field-extension technique and has $O(\ell m^{|\sources|})$ complexity, which is polynomial in the network size. Our code constructions are "end-to-end" in that all nodes except the sources and sinks are oblivious to the adversaries and may simply implement predesigned linear network codes (random or otherwise). Also, the sources act independently without knowledge of the data from other sources.
This paper studies the capacity of single-source single-sink noiseless networks under adversarial or arbitrary errors on no more than z edges. Unlike prior papers, which assume equal capacities on all links, arbitrary link capacities are considered. Results include new upper bounds, network error correction coding strategies, and examples of network families where our bounds are tight. An example is provided of a network where the capacity is 50% greater than the best rate that can be achieved with linear coding. While coding at the source and sink suffices in networks with equal link capacities, in networks with unequal link capacities, it is shown that intermediate nodes may have to do coding, nonlinear error detection, or error correction in order to achieve the network error correction capacity.
One major open problem in network coding is to characterize the capacity region of a general multi-source multi-demand network. There are some existing computational tools for bounding the capacity of general networks, but their computational complexity grows very quickly with the size of the network. This motivates us to propose a new hierarchical approach which finds upper and lower bounding networks of smaller size for a given network. This approach sequentially replaces components of the network with simpler structures, i.e., with fewer links or nodes, so that the resulting network is more amenable to computational analysis and its capacity provides an upper or lower bound on the capacity of the original network. The accuracy of the resulting bounds can be bounded as a function of the link capacities. Surprisingly, we are able to simplify some families of network structures without any loss in accuracy.
A family of equivalence tools for bounding network capacities is introduced. Part I treats networks of point-to-point channels. The main result is roughly as follows. Given a network of noisy, independent, memoryless point-to-point channels, a collection of communication demands can be met on the given network if and only if it can be met on another network where each noisy channel is replaced by a noiseless bit pipe with throughput equal to the noisy channel capacity. This result was known previously for the case of a single-source multicast demand. The result given here treats general demands -- including, for example, multiple unicast demands -- and applies even when the achievable rate region for the corresponding demands is unknown in the noiseless network. In part II, definitions of upper and lower bounding channel models for general channels are introduced. By these definitions, a collection of communication demands can be met on a network of independent channels if it can be met on a network where each channel is replaced by its lower bounding model andonly if it can be met on a network where each channel is replaced by its upper bounding model. This work derives general conditions under which a network of noiseless bit pipes is an upper or lower bounding model for a multiterminal channel. Example upper and lower bounding models for broadcast, multiple access, and interference channels are given. It is then shown that bounding the difference between the upper and lower bounding models for a given channel yields bounds on the accuracy of network capacity bounds derived using those models. By bounding the capacity of a network of independent noisy channels by the network coding capacity of a network of noiseless bit pipes, this approach represents one step towards the goal of building computational tools for bounding network capacities.
This paper proves the separation between source-network coding and channel coding in networks of noisy, discrete, memoryless channels. We show that the set of achievable distortion matrices in delivering a family of dependent sources across such a network equals the set of achievable distortion matrices for delivering the same sources across a distinct network which is built by replacing each channel by a noiseless, point-to-point bit-pipe of the corresponding capacity. Thus a code that applies source-network coding across links that are made almost lossless through the application of independent channel coding across each link asymptotically achieves the optimal performance across the network as a whole.
We focus on a particular form of network coding, reverse carpooling, in a wireless network where the potentially coded transmitted messages are to be decoded immediately upon reception. The network is fixed and known, and the system performance is measured in terms of the number of wireless broadcasts required to meet multiple unicast demands. Motivated by the structure of the coding scheme, we formulate the problem as a linear program by introducing a flow variable for each triple of connected nodes. This allows us to have a formulation polynomial in the number of nodes. Using dual decomposition and projected subgradient method, we present a decentralized algorithm to obtain optimal routing schemes in presence of coding opportunities. We show that the primal sub-problem can be expressed as a shortest path problem on an \emph{edge-graph}, and the proposed algorithm requires each node to exchange information only with its neighbors.
Polar codes have attracted much recent attention as the first codes with low computational complexity that provably achieve optimal rate-regions for a large class of information-theoretic problems. One significant drawback, however, is that for current constructions the probability of error decays sub-exponentially in the block-length (more detailed designs improve the probability of error at the cost of significantly increased computational complexity \cite{KorUS09}). In this work we show how the the classical idea of code concatenation -- using "short" polar codes as inner codes and a "high-rate" Reed-Solomon code as the outer code -- results in substantially improved performance. In particular, code concatenation with a careful choice of parameters boosts the rate of decay of the probability of error to almost exponential in the block-length with essentially no loss in computational complexity. We demonstrate such performance improvements for three sets of information-theoretic problems -- a classical point-to-point channel coding problem, a class of multiple-input multiple output channel coding problems, and some network source coding problems.
We analyze a simple network where a source and a receiver are connected by a line of erasure channels of different reliabilities. Recent prior work has shown that random linear network coding can achieve the min-cut capacity and therefore the asymptotic rate is determined by the worst link of the line network. In this paper we investigate the delay for transmitting a batch of packets, which is a function of all the erasure probabilities and the number of packets in the batch. We show a monotonicity result on the delay function and derive simple expressions which characterize the expected delay behavior of line networks. Further, we use a martingale bounded differences argument to show that the actual delay is tightly concentrated around its expectation.
We consider transmission of stationary and ergodic sources over non-ergodic composite channels with channel state information at the receiver (CSIR). Previously we introduced alternate capacity definitions to Shannon capacity, including the capacity versus outage and the expected capacity. These generalized definitions relax the constraint of Shannon capacity that all transmitted information must be decoded at the receiver. In this work alternate end-to-end distortion metrics such as the distortion versus outage and the expected distortion are introduced to relax the constraint that a single distortion level has to be maintained for all channel states. For transmission of stationary and ergodic sources over stationary and ergodic channels, the classical Shannon separation theorem enables separate design of source and channel codes and guarantees optimal performance. For generalized communication systems, we show that different end-to-end distortion metrics lead to different conclusions about separation optimality even for the same source and channel models.
We consider three capacity definitions for general channels with channel side information at the receiver, where the channel is modeled as a sequence of finite dimensional conditional distributions not necessarily stationary, ergodic, or information stable. The {\em Shannon capacity} is the highest rate asymptotically achievable with arbitrarily small error probability. The {\em capacity versus outage} is the highest rate asymptotically achievable with a given probability of decoder-recognized outage. The {\em expected capacity} is the highest average rate asymptotically achievable with a single encoder and multiple decoders, where the channel side information determines the decoder in use. As a special case of channel codes for expected rate, the code for capacity versus outage has two decoders: one operates in the non-outage states and decodes all transmitted information, and the other operates in the outage states and decodes nothing. Expected capacity equals Shannon capacity for channels governed by a stationary ergodic random process but is typically greater for general channels. These alternative capacity definitions essentially relax the constraint that all transmitted information must be decoded at the receiver. We derive capacity theorems for these capacity definitions through information density. Numerical examples are provided to demonstrate their connections and differences. We also discuss the implication of these alternative capacity definitions for end-to-end distortion, source-channel coding and separation.
We wish to minimize the resources used for network coding while achieving the desired throughput in a multicast scenario. We employ evolutionary approaches, based on a genetic algorithm, that avoid the computational complexity that makes the problem NP-hard. Our experiments show great improvements over the sub-optimal solutions of prior methods. Our new algorithms improve over our previously proposed algorithm in three ways. First, whereas the previous algorithm can be applied only to acyclic networks, our new method works also with networks with cycles. Second, we enrich the set of components used in the genetic algorithm, which improves the performance. Third, we develop a novel distributed framework. Combining distributed random network coding with our distributed optimization yields a network coding protocol where the resources used for coding are optimized in the setup phase by running our evolutionary algorithm at each node of the network. We demonstrate the effectiveness of our approach by carrying out simulations on a number of different sets of network topologies.
We present a capacity-achieving coding scheme for unicast or multicast over lossy packet networks. In the scheme, intermediate nodes perform additional coding yet do not decode nor even wait for a block of packets before sending out coded packets. Rather, whenever they have a transmission opportunity, they send out coded packets formed from random linear combinations of previously received packets. All coding and decoding operations have polynomial complexity. We show that the scheme is capacity-achieving as long as packets received on a link arrive according to a process that has an average rate. Thus, packet losses on a link may exhibit correlation in time or with losses on other links. In the special case of Poisson traffic with i.i.d. losses, we give error exponents that quantify the rate of decay of the probability of error with coding delay. Our analysis of the scheme shows that it is not only capacity-achieving, but that the propagation of packets carrying "innovative" information follows the propagation of jobs through a queueing network, and therefore fluid flow models yield good approximations. We consider networks with both lossy point-to-point and broadcast links, allowing us to model both wireline and wireless packet networks.
We examine the issue of separation and code design for networks that operate over finite fields. We demonstrate that source-channel (or source-network) separation holds for several canonical network examples like the noisy multiple access channel and the erasure degraded broadcast channel, when the whole network operates over a common finite field. This robustness of separation is predicated on the fact that noise and inputs are independent, and we examine the failure of separation when noise is dependent on inputs in multiple access channels. Our approach is based on the sufficiency of linear codes. Using a simple and unifying framework, we not only re-establish with economy the optimality of linear codes for single-transmitter, single-receiver channels and for Slepian-Wolf source coding, but also establish the optimality of linear codes for multiple access and for erasure degraded broadcast channels. The linearity allows us to obtain simple optimal code constructions and to study capacity regions of the noisy multiple access and the degraded broadcast channel. The linearity of both source and network coding blurs the delineation between source and network codes. While our results point to the fact that separation of source coding and channel coding is optimal in some canonical networks, we show that decomposing networks into canonical subnetworks may not be effective. Thus, we argue that it may be the lack of decomposability of a network into canonical network modules, rather than the lack of separation between source and channel coding, that presents major challenges for coding over networks.