We investigate the fundamental problem of generating bipartite classical distributions or quantum states. By designing efficient communication protocols and proving their optimality, we establish a number of intriguing connections to fundamental measures in optimization, convex geometry, and information theory. 1) To generate a classical distribution P(x,y), we tightly characterize the minimum amount of quantum communication needed by the psd-rank of P (as a matrix), a measure recently proposed by Fiorini et al. (Proc. 44th ACM Symp. Theory Comput., pp. 95-106, 2012) in studies of the minimum size of extended formulations of optimization problems such as TSP. This echos the previous characterization for the optimal classical communication cost by the nonnegative rank of P. The result is obtained via investigating the more general case of bipartite quantum state generation and designing an optimal protocol for it. 2) When an approximation ϵ is allowed to generate a distribution (X,Y)~P, we present a classical protocol of the communication cost O((C(X,Y)+1)/ϵ, where C(X,Y) is common information, a well-studied measure in information theory introduced by Wyner (IEEE Trans. Inf. Theory, 21 (2):163-179, 1975). This also links nonnegative rank and common information, two seemingly unrelated quantities in different fields. 3) For approximately generating a quantum pure state |ψ〉, we completely characterize the minimum cost by a corresponding approximate rank, closing a possibly exponential gap left in Ambainis etal. (SIAM J. Comput., 32 (6):1570-1585, 2003).
We investigate the fundamental problem of generating bipartite classical distributions or quantum states. By designing efficient communication protocols and proving their optimality, we establish a number of intriguing connections to fundamental measures in optimization, convex geometry, and information theory. 1) To generate a classical distribution P(x,y), we tightly characterize the minimum amount of quantum communication needed by the psd-rank of P (as a matrix), a measure recently proposed by Fiorini et al. (Proc. 44th ACM Symp. Theory Comput., pp. 95-106, 2012) in studies of the minimum size of extended formulations of optimization problems such as TSP. This echos the previous characterization for the optimal classical communication cost by the nonnegative rank of P. The result is obtained via investigating the more general case of bipartite quantum state generation and designing an optimal protocol for it. 2) When an approximation ϵ is allowed to generate a distribution (X,Y)~P, we present a classical protocol of the communication cost O((C(X,Y)+1)/ϵ, where C(X,Y) is common information, a well-studied measure in information theory introduced by Wyner (IEEE Trans. Inf. Theory, 21 (2):163-179, 1975). This also links nonnegative rank and common information, two seemingly unrelated quantities in different fields. 3) For approximately generating a quantum pure state |ψ〉, we completely characterize the minimum cost by a corresponding approximate rank, closing a possibly exponential gap left in Ambainis etal. (SIAM J. Comput., 32 (6):1570-1585, 2003).
We investigate the fundamental problem of generating bipartite classical distributions or quantum states. By designing efficient communication protocols and proving their optimality, we establish a number of intriguing connections to fundamental measures in optimization, convex geometry, and information theory. 1. To generate a classical distribution P(x, y), we tightly characterize the minimum amount of quantum communication needed by the psd-rank of P (as a matrix), a measure recently proposed by Fiorini, Massar, Pokutta, Tiwary and de Wolf (Proceedings of the 44th A CM Symposium on Theory of Computing, pages 95–106, 2012) in studies of the minimum size of extended formulations of optimization problems such as TSP. This echos the previous characterization for the optimal classical communication cost by the nonnegative rank of P. The result is obtained via investigating the more general case of bipartite quantum state generation and designing an optimal protocol for it. 2. When an approximation of ε is allowed to generate a distribution (X, Y) ∼ P, we present a classical protocol of the communication cost O((C(X, Y) + 1)/ε), where C(X, Y) is common information, a well-studied measure in information theory introduced by Wyner (IEEE Transactions on Information Theory, 21(2):163–179, 1975). This also links nonnegative rank and common information, two seemingly unrelated quantities in different fields. 3. For approximately generating a quantum pure state |ψ〉, we completely characterize the minimum cost by a corresponding approximate rank, closing a possibly exponential gap left in Ambainis, Schulman, Ta-Shma, Vazirani and Wigderson (SIAM Journal on Computing, 32(6):1570–1585, 2003).
We study the correlation complexity (or equivalently, the communication complexity) of generating a bipartite quantum state ρ. When ρ is a pure state, we completely characterize the complexity for approximately generating ρ by a corresponding approximate rank, closing a gap left in Ambainis, Schulman, Ta-Shma, Vazirani and Wigderson (SIAM Journal on Computing, 32(6):1570-1585, 2003). When ρ is a classical distribution P(x,y), we tightly characterize the complexity of generating P by the psd-rank, a measure recently proposed by Fiorini, Massar, Pokutta, Tiwary and de Wolf (STOC 2012). We also present a characterization of the complexity of generating a general quantum state ρ.
The concepts of quantum correlation and communication complexity have been proposed to quantify the worst-case computational resources needed in generating bipartite classical distributions or bipartite quantum states in the single-shot setting by Zhang (Proc. 3rd Innov Theor Comput., pp. 39-59, 2012). The former characterizes the minimal size of the initial shared state needed if no communication is allowed, and the latter characterizes the minimal amount of communication needed if sharing nothing at the beginning. In this paper, we generalize these two concepts to approximate bipartite cases and various multipartite cases. 1. To generate a bipartite classical distribution P (x, y) approximately, we show that the minimal amount of quantum communication needed can be characterized completely by the approximate PSD-rank of P . This result is obtained based on the fact that the cost to approximate a bipartite quantum state equals that to approximate its exact purifications, which also implies a result for a general bipartite quantum state. 2. In the bipartite case, correlation complexity is always equivalent to communication complexity, but in multipartite cases, this is not true any more. For multipartite pure states, we show that both of them could be characterized by local ranks of subsystems. 3. For any bipartite quantum state, its correlation complexity is always equivalent to that of its optimal purification, while in multipartite cases the former could be smaller strictly than the latter. We characterize the relationship between them by giving upper and lower bounds. 4. For multipartite classical distributions, we show that the approximate correlation complexity could also be characterized by the generalized PSD-rank.
We consider a realistic setting of quantum tasks that generate shared bipartite quantum states. Suppose \alice and \bob are located at different places and need to produce a target shared quantum state ρ. In order to save quantum communication, they can choose to share a proper smaller quantum state σ first, and then turn σ to ρ by performing only local quantum operations and classical communications (LOCC). We hope σ is the optimal such that the quantum communication needed is as little as possible, which is called the generation cost of ρ. In this paper, for an arbitrary bipartite ρ, we characterize its generation cost completely by proving that it is exactly equivalent to the logarithm of the Schmidt number of ρ. Similar quantum schemes where classical communication is not allowed have actually been considered. By comparing the two settings, we are able to look into the role that classical communication plays in these fundamental tasks, where we exhibit some instances in which classical communication is not helpful completely.
We study the problem of simulating protocols in a quantum communication setting over noisy channels. This problem falls at the intersection of quantum information theory and quantum communication complexity, and it will be of importance for eventual real-world applications of interactive quantum protocols, which can be proved to have exponentially lower communication costs than their classical counterparts for some problems. These are the first results concerning the quantum version of this problem, originally studied by Schulman in a classical setting [L. J. Schulman, Communication on noisy channels: A coding theorem for computation, in Proceedings of the 33rd Annual IEEE Symposium on Foundations of Computer Science, IEEE, 1992, pp. 724--733], [L. J. Schulman, Deterministic coding for interactive communication, in Proceedings of the 25th Annual ACM Symposium on Theory of Computing, ACM, 1993, pp. 747--756]. We simulate a length N quantum communication protocol by a length O(N) protocol with arbitrarily small error. Under adversarial noise, our strategy can withstand, for arbitrarily small ε>0, error rates as high as 1/2−ε when parties preshare perfect entanglement, but the classical channel is noisy. We show that this is optimal. We provide extension of these results in several other models of communication, including when also the entanglement is noisy, and when there is no preshared entanglement but communication is quantum and noisy. We also study the case of random noise, for which we provide simulation protocols with positive communication rates and no preshared entanglement over some quantum channels with quantum capacity CQ=0, proving that CQ is in general not the right characterization of a channel's capacity for interactive quantum communication. Our results are stated for a general quantum communication protocol in which Alice and Bob collaborate, and these results hold in particular in the quantum communication complexity settings of the Yao and Cleve--Buhrman models.
We study a model of communication complexity that encompasses many well-studied problems, including classical and quantum communication complexity, the complexity of simulating distributions arising from bipartite measurements of shared quantum states, and XOR games. In this model, Alice gets an input x, Bob gets an input y, and their goal is to each produce an output a,b distributed according to some pre-specified joint distribution p(a,b∣x,y). Our results apply to any non-signaling distribution, that is, those where Alice's marginal distribution does not depend on Bob's input, and vice versa.~~~By taking a geometric view of the non-signaling distributions, we introduce a simple new technique based on affine combinations of lower-complexity distributions, and we give the first general technique to apply to all these settings, with elementary proofs and very intuitive interpretations. Specifically, we introduce two complexity measures, one which gives lower bounds on classical communication, and one for quantum communication. These measures can be expressed as convex optimization problems. We show that the dual formulations have a striking interpretation, since they coincide with maximum violations of Bell and Tsirelson inequalities. The dual expressions are closely related to the winning probability of XOR games. Despite their apparent simplicity, these lower bounds subsume many known communication complexity lower bound methods, most notably the recent lower bounds of Linial and Shraibman for the special case of Boolean functions. We show that as in the case of Boolean functions, the gap between the quantum and classical lower bounds is at most linear in the size of the support of the distribution, and does not depend on the size of the inputs. This translates into a bound on the gap between maximal Bell and Tsirelson inequality violations, which was previously known only for the case of distributions with Boolean outcomes and uniform marginals. It also allows us to show that for some distributions, information theoretic methods are necessary to prove strong lower bounds. ~~~ Finally, we give an exponential upper bound on quantum and classical communication complexity in the simultaneous messages model, for any non-signaling distribution. One consequence of this is a simple proof that any quantum distribution can be approximated with a constant number of bits of communication.