arXiv subjects

Vaneet Aggarwal

Publications and source records attributed to Vaneet Aggarwal.

At least 253 records · Page 14Linked to original sources

arXiv2016

Coded Caching with Distributed Storage

Content delivery networks store information distributed across multiple servers, so as to balance the load and avoid unrecoverable losses in case of node or disk failures. Coded caching has been shown to be a useful technique which can reduce peak traffic rates by pre-fetching popular content at the end users and encoding transmissions so that different users can extract different information from the same packet. On one hand, distributed storage limits the capability of combining content from different servers into a single message, causing performance losses in coded caching schemes. But, on the other hand, the inherent redundancy existing in distributed storage systems can be used to improve the performance of those schemes through parallelism. This paper designs a scheme combining distributed storage of the content in multiple servers and an efficient coded caching algorithm for delivery to the users. This scheme is shown to reduce the peak transmission rate below that of state-of-the-art algorithms.

cs.IT↗

arXiv2016

Unsupervised clustering under the Union of Polyhedral Cones (UOPC) model

In this paper, we consider clustering data that is assumed to come from one of finitely many pointed convex polyhedral cones. This model is referred to as the Union of Polyhedral Cones (UOPC) model. Similar to the Union of Subspaces (UOS) model where each data from each subspace is generated from a (unknown) basis, in the UOPC model each data from each cone is assumed to be generated from a finite number of (unknown) \emph{extreme rays}.To cluster data under this model, we consider several algorithms - (a) Sparse Subspace Clustering by Non-negative constraints Lasso (NCL), (b) Least squares approximation (LSA), and (c) K-nearest neighbor (KNN) algorithm to arrive at affinity between data points. Spectral Clustering (SC) is then applied on the resulting affinity matrix to cluster data into different polyhedral cones. We show that on an average KNN outperforms both NCL and LSA and for this algorithm we provide the deterministic conditions for correct clustering. For an affinity measure between the cones it is shown that as long as the cones are not very coherent and as long as the density of data within each cone exceeds a threshold, KNN leads to accurate clustering. Finally, simulation results on real datasets (MNIST and YaleFace datasets) depict that the proposed algorithm works well on real data indicating the utility of the UOPC model and the proposed algorithm.

stat.ML↗

arXiv2016

Low-tubal-rank Tensor Completion using Alternating Minimization

The low-tubal-rank tensor model has been recently proposed for real-world multidimensional data. In this paper, we study the low-tubal-rank tensor completion problem, i.e., to recover a third-order tensor by observing a subset of its elements selected uniformly at random. We propose a fast iterative algorithm, called {\em Tubal-Alt-Min}, that is inspired by a similar approach for low-rank matrix completion. The unknown low-tubal-rank tensor is represented as the product of two much smaller tensors with the low-tubal-rank property being automatically incorporated, and Tubal-Alt-Min alternates between estimating those two tensors using tensor least squares minimization. First, we note that tensor least squares minimization is different from its matrix counterpart and nontrivial as the circular convolution operator of the low-tubal-rank tensor model is intertwined with the sub-sampling operator. Second, the theoretical performance guarantee is challenging since Tubal-Alt-Min is iterative and nonconvex in nature. We prove that 1) Tubal-Alt-Min guarantees exponential convergence to the global optima, and 2) for an $n \times n \times k$ tensor with tubal-rank $r \ll n$, the required sampling complexity is $O(nr^2k \log^3 n)$ and the computational complexity is $O(n^2rk^2 \log^2 n)$. Third, on both synthetic data and real-world video data, evaluation results show that compared with tensor-nuclear norm minimization (TNN-ADMM), Tubal-Alt-Min improves the recovery error dramatically (by orders of magnitude). It is estimated that Tubal-Alt-Min converges at an exponential rate $10^{-0.4423 \text{Iter}}$ where $\text{Iter}$ denotes the number of iterations, which is much faster than TNN-ADMM's $10^{-0.0332 \text{Iter}}$, and the running time can be accelerated by more than $5$ times for a $200 \times 200 \times 20$ tensor.

cs.LG↗

arXiv2016

Tensor Completion by Alternating Minimization under the Tensor Train (TT) Model

Using the matrix product state (MPS) representation of tensor train decompositions, in this paper we propose a tensor completion algorithm which alternates over the matrices (tensors) in the MPS representation. This development is motivated in part by the success of matrix completion algorithms which alternate over the (low-rank) factors. We comment on the computational complexity of the proposed algorithm and numerically compare it with existing methods employing low rank tensor train approximation for data completion as well as several other recently proposed methods. We show that our method is superior to existing ones for a variety of real settings.

math.NA↗

arXiv2016

On the Symmetric $K$-user Interference Channels with Limited Feedback

In this paper, we develop achievability schemes for symmetric $K$-user interference channels with a rate-limited feedback from each receiver to the corresponding transmitter. We study this problem under two different channel models: the linear deterministic model, and the Gaussian model. For the deterministic model, the proposed scheme achieves a symmetric rate that is the minimum of the symmetric capacity with infinite feedback, and the sum of the symmetric capacity without feedback and the symmetric amount of feedback. For the Gaussian interference channel, we use lattice codes to propose a transmission strategy that incorporates the techniques of Han-Kobayashi message splitting, interference decoding, and decode and forward. This strategy achieves a symmetric rate which is within a constant number of bits to the minimum of the symmetric capacity with infinite feedback, and the sum of the symmetric capacity without feedback and the amount of symmetric feedback. This constant is obtained as a function of the number of users, $K$. The symmetric achievable rate is used to characterize the achievable generalized degrees of freedom which exhibits a gradual increase from no feedback to perfect feedback in the presence of feedback links with limited capacity.

cs.IT↗

arXiv2016

The DoF of Two-way Butterfly Networks

This paper studies the two-way butterfly network, a class of two-way four-unicast networks. We first show that bidirectional links do not increase the degrees of freedom for this network thus giving the first example for networks, to the best of our knowledge, where bidirectional links do not increase the degrees of freedom. Further, we see that sufficient caching at the relays or increasing the number of antennas in the relays can double the two-way degrees of freedom for butterfly network.

cs.IT↗

arXiv2016

On Deterministic Conditions for Subspace Clustering under Missing Data

In this paper we present deterministic conditions for success of sparse subspace clustering (SSC) under missing data, when data is assumed to come from a Union of Subspaces (UoS) model. We consider two algorithms, which are variants of SSC with entry-wise zero-filling that differ in terms of the optimization problems used to find affinity matrix for spectral clustering. For both the algorithms, we provide deterministic conditions for any pattern of missing data such that perfect clustering can be achieved. We provide extensive sets of simulation results for clustering as well as completion of data at missing entries, under the UoS model. Our experimental results indicate that in contrast to the full data case, accurate clustering does not imply accurate subspace identification and completion, indicating the natural order of relative hardness of these problems.

cs.IT↗

arXiv2016

On deterministic conditions for subspace clustering under missing data

In this paper we present deterministic analysis of sufficient conditions for sparse subspace clustering under missing data, when data is assumed to come from a Union of Subspaces (UoS) model. In this context we consider two cases, namely Case I when all the points are sampled at the same co-ordinates, and Case II when points are sampled at different locations. We show that results for Case I directly follow from several existing results in the literature, while results for Case II are not as straightforward and we provide a set of dual conditions under which, perfect clustering holds true. We provide extensive set of simulation results for clustering as well as completion of data under missing entries, under the UoS model. Our experimental results indicate that in contrast to the full data case, accurate clustering does not imply accurate subspace identification and completion, indicating the natural order of relative hardness of these problems.

cs.IT↗

arXiv2016

Differentiated latency in data center networks with erasure coded files through traffic engineering

This paper proposes an algorithm to minimize weighted service latency for different classes of tenants (or service classes) in a data center network where erasure-coded files are stored on distributed disks/racks and access requests are scattered across the network. Due to limited bandwidth available at both top-of-the-rack and aggregation switches and tenants in different service classes need differentiated services, network bandwidth must be apportioned among different intra- and inter-rack data flows for different service classes in line with their traffic statistics. We formulate this problem as weighted queuing and employ a class of probabilistic request scheduling policies to derive a closed-form upper-bound of service latency for erasure-coded storage with arbitrary file access patterns and service time distributions. The result enables us to propose a joint weighted latency (over different service classes) optimization over three entangled "control knobs": the bandwidth allocation at top-of-the-rack and aggregation switches for different service classes, dynamic scheduling of file requests, and the placement of encoded file chunks (i.e., data locality). The joint optimization is shown to be a mixed-integer problem. We develop an iterative algorithm which decouples and solves the joint optimization as 3 sub-problems, which are either convex or solvable via bipartite matching in polynomial time. The proposed algorithm is prototyped in an open-source, distributed file system, {\em Tahoe}, and evaluated on a cloud testbed with 16 separate physical hosts in an Openstack cluster using 48-port Cisco Catalyst switches. Experiments validate our theoretical latency analysis and show significant latency reduction for diverse file access patterns. The results provide valuable insights on designing low-latency data center networks with erasure coded storage.

cs.DC↗

arXiv2015

Adaptive Sampling of RF Fingerprints for Fine-grained Indoor Localization

Indoor localization is a supporting technology for a broadening range of pervasive wireless applications. One promis- ing approach is to locate users with radio frequency fingerprints. However, its wide adoption in real-world systems is challenged by the time- and manpower-consuming site survey process, which builds a fingerprint database a priori for localization. To address this problem, we visualize the 3-D RF fingerprint data as a function of locations (x-y) and indices of access points (fingerprint), as a tensor and use tensor algebraic methods for an adaptive tubal-sampling of this fingerprint space. In particular using a recently proposed tensor algebraic framework in [1] we capture the complexity of the fingerprint space as a low-dimensional tensor-column space. In this formulation the proposed scheme exploits adaptivity to identify reference points which are highly informative for learning this low-dimensional space. Further, under certain incoherency conditions we prove that the proposed scheme achieves bounded recovery error and near-optimal sampling complexity. In contrast to several existing work that rely on random sampling, this paper shows that adaptivity in sampling can lead to significant improvements in localization accuracy. The approach is validated on both data generated by the ray-tracing indoor model which accounts for the floor plan and the impact of walls and the real world data. Simulation results show that, while maintaining the same localization accuracy of existing approaches, the amount of samples can be cut down by 71% for the high SNR case and 55% for the low SNR case.

cs.IT↗

arXiv2015

Information-theoretic Bounds on Matrix Completion under Union of Subspaces Model

In this short note we extend some of the recent results on matrix completion under the assumption that the columns of the matrix can be grouped (clustered) into subspaces (not necessarily disjoint or independent). This model deviates from the typical assumption prevalent in the literature dealing with compression and recovery for big-data applications. The results have a direct bearing on the problem of subspace clustering under missing or incomplete information.

cs.IT↗

arXiv2014

Distributed Data Storage Systems with Opportunistic Repair

The reliability of erasure-coded distributed storage systems, as measured by the mean time to data loss (MTTDL), depends on the repair bandwidth of the code. Repair-efficient codes provide reliability values several orders of magnitude better than conventional erasure codes. Current state of the art codes fix the number of helper nodes (nodes participating in repair) a priori. In practice, however, it is desirable to allow the number of helper nodes to be adaptively determined by the network traffic conditions. In this work, we propose an opportunistic repair framework to address this issue. It is shown that there exists a threshold on the storage overhead, below which such an opportunistic approach does not lose any efficiency from the optimal storage-repair-bandwidth tradeoff; i.e. it is possible to construct a code simultaneously optimal for different numbers of helper nodes. We further examine the benefits of such opportunistic codes, and derive the MTTDL improvement for two repair models: one with limited total repair bandwidth and the other with limited individual-node repair bandwidth. In both settings, we show orders of magnitude improvement in MTTDL. Finally, the proposed framework is examined in a network setting where a significant improvement in MTTDL is observed.

cs.IT↗

arXiv2014

On the Capacity Regions of Two-Way Diamond Channels

In this paper, we study the capacity regions of two-way diamond channels. We show that for a linear deterministic model the capacity of the diamond channel in each direction can be simultaneously achieved for all values of channel parameters, where the forward and backward channel parameters are not necessarily the same. We divide the achievability scheme into three cases, depending on the forward and backward channel parameters. For the first case, we use a reverse amplify-and-forward strategy in the relays. For the second case, we use four relay strategies based on the reverse amplify-and-forward with some modifications in terms of replacement and repetition of some stream levels. For the third case, we use two relay strategies based on performing two rounds of repetitions in a relay. The proposed schemes for deterministic channels are used to find the capacity regions within constant gaps for two special cases of the Gaussian two-way diamond channel. First, for the general Gaussian two-way relay channel with a simple coding scheme the smallest gap is achieved compared to the prior works. Then, a special symmetric Gaussian two-way diamond model is considered and the capacity region is achieved within four bits.

cs.IT↗

arXiv2014

Multiuser Joint Energy-Bandwidth Allocation with Energy Harvesting - Part I: Optimum Algorithm & Multiple Point-to-Point Channels

In this paper, we develop optimal energy-bandwidth allocation algorithms in fading channels for multiple energy harvesting transmitters, each may communicate with multiple receivers via orthogonal channels. We first assume that the side information of both the channel states and the energy harvesting states is known for $K$ time slots {\em a priori}, and the battery capacity and the maximum transmission power in each time slot are bounded. The objective is to maximize the weighted sum-rate of all transmitters over the $K$ time slots by assigning the transmission power and bandwidth for each transmitter in each slot. The problem is formulated as a convex optimization problem with ${\cal O}(MK)$ constraints, where $M$ is the number of the receivers, making it hard to solve with a generic convex solver. An iterative algorithm is proposed that alternatively solves two subproblems in each iteration. The convergence and the optimality of this algorithm are also shown. We then consider the special case that each transmitter only communicates with one receiver and the objective is to maximize the total throughput. We develop efficient algorithms for solving the two subproblems and the optimal energy-bandwidth allocation can be obtained with an overall complexity of ${\cal O}(MK^2)$. Moreover, a heuristic algorithm is also proposed for energy-bandwidth allocation based on causal information of channel and energy harvesting states.

cs.IT↗

arXiv2014

Multiuser Joint Energy-Bandwidth Allocation with Energy Harvesting - Part II: Multiple Broadcast Channels & Proportional Fairness

In this paper, we consider the energy-bandwidth allocation for a network with multiple broadcast channels, where the transmitters access the network orthogonally on the assigned frequency band and each transmitter communicates with multiple receivers orthogonally or non-orthogonally. We assume that the energy harvesting state and channel gain of each transmitter can be predicted for $K$ slots {\em a priori}. To maximize the weighted throughput, we formulate an optimization problem with $O(MK)$ constraints, where $M$ is the number of the receivers, and decompose it into the energy and bandwidth allocation subproblems. In order to use the iterative algorithm proposed in [1] to solve the problem, we propose efficient algorithms to solve the two subproblems, so that the optimal energy-bandwidth allocation can be obtained with an overall complexity of ${\cal O}(MK^2)$, even though the problem is non-convex when the broadcast channel is non-orthogonal. For the orthogonal broadcast channel, we further formulate a proportionally-fair (PF) throughput maximization problem and derive the equivalence conditions such that the optimal solution can be obtained by solving a weighted throughput maximization problem. Further, the algorithm to obtain the proper weights is proposed. Simulation results show that the proposed algorithm can make efficient use of the harvested energy and the available bandwidth, and achieve significantly better performance than some heuristic policies for energy and bandwidth allocation. Moreover, it is seen that with energy-harvesting transmitters, non-orthogonal broadcast offers limited gain over orthogonal broadcast.

cs.IT↗

arXiv2014

Joint Latency and Cost Optimization for Erasure-coded Data Center Storage

Modern distributed storage systems offer large capacity to satisfy the exponentially increasing need of storage space. They often use erasure codes to protect against disk and node failures to increase reliability, while trying to meet the latency requirements of the applications and clients. This paper provides an insightful upper bound on the average service delay of such erasure-coded storage with arbitrary service time distribution and consisting of multiple heterogeneous files. Not only does the result supersede known delay bounds that only work for a single file or homogeneous files, it also enables a novel problem of joint latency and storage cost minimization over three dimensions: selecting the erasure code, placement of encoded chunks, and optimizing scheduling policy. The problem is efficiently solved via the computation of a sequence of convex approximations with provable convergence. We further prototype our solution in an open-source, cloud storage deployment over three geographically distributed data centers. Experimental results validate our theoretical delay analysis and show significant latency reduction, providing valuable insights into the proposed latency-cost tradeoff in erasure-coded storage.

cs.DC↗

arXiv2014

Layered, Exact-Repair Regenerating Codes Via Embedded Error Correction and Block Designs

A new class of exact-repair regenerating codes is constructed by stitching together shorter erasure correction codes, where the stitching pattern can be viewed as block designs. The proposed codes have the "help-by-transfer" property where the helper nodes simply transfer part of the stored data directly, without performing any computation. This embedded error correction structure makes the decoding process straightforward, and in some cases the complexity is very low. We show that this construction is able to achieve performance better than space-sharing between the minimum storage regenerating codes and the minimum repair-bandwidth regenerating codes, and it is the first class of codes to achieve this performance. In fact, it is shown that the proposed construction can achieve a non-trivial point on the optimal functional-repair tradeoff, and it is asymptotically optimal at high rate, i.e., it asymptotically approaches the minimum storage and the minimum repair-bandwidth simultaneously.

cs.IT↗

arXiv2014

Iterative Dynamic Water-filling for Fading Multiple-Access Channels with Energy Harvesting

In this paper, we develop optimal energy scheduling algorithms for $N$-user fading multiple-access channels with energy harvesting to maximize the channel sum-rate, assuming that the side information of both the channel states and energy harvesting states for $K$ time slots is known {\em a priori}, and the battery capacity and the maximum energy consumption in each time slot are bounded. The problem is formulated as a convex optimization problem with ${\cal O}(NK)$ constraints making it hard to solve using a general convex solver since the computational complexity of a generic convex solver is exponential in the number of constraints. This paper gives an efficient energy scheduling algorithm, called the iterative dynamic water-filling algorithm, that has a computational complexity of ${\cal O}(NK^2)$ per iteration. For the single-user case, a dynamic water-filling method is shown to be optimal. Unlike the traditional water-filling algorithm, in dynamic water-filling, the water level is not constant but changes when the battery overflows or depletes. An iterative version of the dynamic water-filling algorithm is shown to be optimal for the case of multiple users. Even though in principle the optimality is achieved under large number of iterations, in practice convergence is reached in only a few iterations. Moreover, a single iteration of the dynamic water-filling algorithm achieves a sum-rate that is within $(N-1)K/2$ nats of the optimal sum-rate.

cs.IT↗