Animashree Anandkumar

Distributed Algorithms for Learning and Cognitive Medium Access with Logarithmic Regret

The problem of distributed learning and channel access is considered in a cognitive network with multiple secondary users. The availability statistics of the channels are initially unknown to the secondary users and are estimated using sensing decisions. There is no explicit information exchange or prior agreement among the secondary users and sensing and access decisions are undertaken by them in a completely distributed manner. We propose policies for distributed learning and access which achieve order-optimal cognitive system throughput (number of successful secondary transmissions) under self play, i.e., when implemented at all the secondary users. Equivalently, our policies minimize the sum regret in distributed learning and access, which is the loss in secondary throughput due to learning and distributed access. For the scenario when the number of secondary users is known to the policy, we prove that the total regret is logarithmic in the number of transmission slots. This policy achieves order-optimal regret based on a logarithmic lower bound for regret under any uniformly-good learning and access policy. We then consider the case when the number of secondary users is fixed but unknown, and is estimated at each user through feedback. We propose a policy whose sum regret grows only slightly faster than logarithmic in the number of transmission slots.

Opportunistic Spectrum Access with Multiple Users: Learning under Competition

The problem of cooperative allocation among multiple secondary users to maximize cognitive system throughput is considered. The channel availability statistics are initially unknown to the secondary users and are learnt via sensing samples. Two distributed learning and allocation schemes which maximize the cognitive system throughput or equivalently minimize the total regret in distributed learning and allocation are proposed. The first scheme assumes minimal prior information in terms of pre-allocated ranks for secondary users while the second scheme is fully distributed and assumes no such prior information. The two schemes have sum regret which is provably logarithmic in the number of sensing time slots. A lower bound is derived for any learning scheme which is asymptotically logarithmic in the number of slots. Hence, our schemes achieve asymptotic order optimality in terms of regret in distributed learning and allocation.

Learning Sparsely Used Overcomplete Dictionaries via Alternating Minimization

We consider the problem of sparse coding, where each sample consists of a sparse linear combination of a set of dictionary atoms, and the task is to learn both the dictionary elements and the mixing coefficients. Alternating minimization is a popular heuristic for sparse coding, where the dictionary and the coefficients are estimated in alternate steps, keeping the other fixed. Typically, the coefficients are estimated via

Type-Based Random Access for Distributed Detection Over Multiaccess Fading Channels

\ell_1

High-dimensional structure estimation in Ising models: Local separation criterion

minimization, keeping the dictionary fixed, and the dictionary is estimated through least squares, keeping the coefficients fixed. In this paper, we establish local linear convergence for this variant of alternating minimization and establish that the basin of attraction for the global optimum (corresponding to the true dictionary and the coefficients) is

Detection of Gauss–Markov Random Fields With Nearest-Neighbor Dependency

\order{1/s^2}

Robust Rate Maximization Game Under Bounded Channel Uncertainty

, where

A Large-Deviation Analysis of the Maximum-Likelihood Learning of Markov Tree Structures

s

Learning Gaussian Tree Models: Analysis of Error Exponents and Extremal Structures

is the sparsity level in each sample and the dictionary satisfies RIP. Combined with the recent results of approximate dictionary estimation, this yields provable guarantees for exact recovery of both the dictionary elements and the coefficients, when the dictionary elements are incoherent.

Tracking in a spaghetti bowl: monitoring transactions using footprints

The problem of distributed detection in a sensor network over multiaccess fading channels is considered. A random-access transmission scheme referred to as the type-based random access (TBRA) is proposed and analyzed. Error exponents of TBRA under noncoherent detection are characterized with respect to the mean transmission rate and the channel-coherence index. For the zero-mean multiaccess fading channels, it is shown that there exists an optimal mean-transmission rate that maximizes the detection-error exponents. The optimal mean-transmission rate can be calculated numerically or estimated using the Gaussian approximation, and it gives a sensor-activation strategy that achieves an optimal allocation of transmission energy to spatial and temporal domains. Numerical examples and simulations are used to compare TBRA with the conventional centralized time-division multiple access (TDMA) scheme. It is shown that for the zero-mean multiaccess fading channels, TBRA gives substantial improvement in the low signal-to-noise ratio (SNR) regime whereas for the nonzero mean fading channels, TBRA performs better over a wide range of SNR.