Anusha Lalitha
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Anusha Lalitha has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Tara Javidi
Department of Electrical and Computer Engineering University of California San Diego
5 shared publications - Vinod Sharma
Department of Electrical Communication Engineering, Indian Institute of Science, Bangalore, India
2 shared publications - Anand D. Sarwate
Rutgers University, Piscataway, NJ, USA
1 shared publication - Andrea Goldsmith
Stony Brook University, Stony Brook, NY, USA
1 shared publication - Farinaz Koushanfar
University of California San Diego, La Jolla, CA, USA
1 shared publication Kumar V Satya
Department of Electrical Communications, Indian Institute of Science, Bangalore, India
1 shared publication
Latest Publications
- 11 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Information Theory
- Vol. 3 (2) , 172-182
Peer-to-Peer Variational Federated Learning Over Arbitrary Graphs
This paper proposes a federated supervised learning framework over a general peer-to-peer network with agents that act in a variational Bayesian fashion. The proposed framework consists of local agents where each of which keeps a local “posterior probability distribution” over the parameters of a global model; the updating of the posterior over time happens in a local fashion according to two subroutines of: 1) variational model training given (a batch of) local labeled data, and 2) asynchronous communication and model aggregation with the 1-hop neighbors. Inspired by the popular federated learning (model averaging), the framework allows the training data to remain distributed on mobile devices while utilizing a peer-to-peer model aggregation in a social network. The proposed framework is shown to allow for a systematic treatment of model aggregation over any arbitrary connected graph with consistent (in general, non-iid) local labeled data. Specifically, under mild technical conditions, the proposed algorithm allows agents with local data to learn a shared model explaining the global training data in a decentralized fashion over an arbitrary peering/connectivity graph. Furthermore, the rate of convergence is characterized and shown to be a function of each individual agent’s data quality weighted by its eigenvector centrality. Empirically, the proposed methodology is shown to work well with efficient variation Bayesian inference techniques to train Bayesian neural networks in a decentralized manner even when the local data batches are not identically distributed.
- 11 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Information Theory
- Vol. 3 (2) , 172-182
Peer-to-Peer Variational Federated Learning Over Arbitrary Graphs
This paper proposes a federated supervised learning framework over a general peer-to-peer network with agents that act in a variational Bayesian fashion. The proposed framework consists of local agents where each of which keeps a local “posterior probability distribution” over the parameters of a global model; the updating of the posterior over time happens in a local fashion according to two subroutines of: 1) variational model training given (a batch of) local labeled data, and 2) asynchronous communication and model aggregation with the 1-hop neighbors. Inspired by the popular federated learning (model averaging), the framework allows the training data to remain distributed on mobile devices while utilizing a peer-to-peer model aggregation in a social network. The proposed framework is shown to allow for a systematic treatment of model aggregation over any arbitrary connected graph with consistent (in general, non-iid) local labeled data. Specifically, under mild technical conditions, the proposed algorithm allows agents with local data to learn a shared model explaining the global training data in a decentralized fashion over an arbitrary peering/connectivity graph. Furthermore, the rate of convergence is characterized and shown to be a function of each individual agent’s data quality weighted by its eigenvector centrality. Empirically, the proposed methodology is shown to work well with efficient variation Bayesian inference techniques to train Bayesian neural networks in a decentralized manner even when the local data batches are not identically distributed.
- 18 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Information Theory
- Vol. 2 (2) , 564-583
Bayesian Algorithms for Decentralized Stochastic Bandits
We study a decentralized cooperative multi-agent multi-armed bandit (MAB) problem with K arms and N agents connected over a network. In this model, each arm's reward distribution is the same for every agent, and rewards are drawn independently across agents and over time steps. At each iteration, agents independently choose an arm to play and exchange at most poly(K) real-valued messages with their neighbors. Existing lower bound on the average per-agent regret over the network shows that cooperation with other agents can achieve a reduction of O(\frac 1N) over when playing in isolation. Motivated by this, we study a message-passing algorithm that can be combined with existing Bayesian MAB algorithms. Using this, we propose a decentralized Thompson Sampling (TS) algorithm and a decentralized Bayes-UCB algorithm. Under decentralized TS for bounded rewards, we establish a problem-dependent upper bound on the average per-agent regret in terms of the number of agents in the network and the network topology. For Bernoulli rewards, our upper bound asymptotically matches the lower bound. We empirically show that the proposed decentralized TS algorithm incurs significantly lesser per-agent regret than previously proposed algorithms. Furthermore, we show that the proposed decentralized TS can be extended to general bandit problems, where posterior distribution cannot be computed in closed form. We combine our decentralized TS algorithm with Variational Inference to apply our proposed algorithm to complex realistic reward distributions in a computationally efficient manner. We implement our proposed decentralized TS under gossip protocol and over time-varying networks, where each communication link has a fixed probability of failure and show that it incurs logarithmic regret.
- 18 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Information Theory
- Vol. 2 (2) , 564-583
Bayesian Algorithms for Decentralized Stochastic Bandits
We study a decentralized cooperative multi-agent multi-armed bandit (MAB) problem with K arms and N agents connected over a network. In this model, each arm's reward distribution is the same for every agent, and rewards are drawn independently across agents and over time steps. At each iteration, agents independently choose an arm to play and exchange at most poly(K) real-valued messages with their neighbors. Existing lower bound on the average per-agent regret over the network shows that cooperation with other agents can achieve a reduction of O(\frac 1N) over when playing in isolation. Motivated by this, we study a message-passing algorithm that can be combined with existing Bayesian MAB algorithms. Using this, we propose a decentralized Thompson Sampling (TS) algorithm and a decentralized Bayes-UCB algorithm. Under decentralized TS for bounded rewards, we establish a problem-dependent upper bound on the average per-agent regret in terms of the number of agents in the network and the network topology. For Bernoulli rewards, our upper bound asymptotically matches the lower bound. We empirically show that the proposed decentralized TS algorithm incurs significantly lesser per-agent regret than previously proposed algorithms. Furthermore, we show that the proposed decentralized TS can be extended to general bandit problems, where posterior distribution cannot be computed in closed form. We combine our decentralized TS algorithm with Variational Inference to apply our proposed algorithm to complex realistic reward distributions in a computationally efficient manner. We implement our proposed decentralized TS under gossip protocol and over time-varying networks, where each communication link has a fixed probability of failure and show that it incurs logarithmic regret.
- 29 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 12 (5) , 871-885
Improved Target Acquisition Rates With Feedback Codes
This paper considers the problem of acquiring an unknown target location (among a finite number of locations) via a sequence of measurements, where each measurement consists of simultaneously probing a group of locations. The resulting observation consists of a sum of an indicator of the target's presence in the probed region, and a zero mean Gaussian noise term whose variance is a function of the measurement vector. An equivalence between the target acquisition problem and channel coding over a binary input additive white Gaussian noise (BAWGN) channel with state and feedback is established. Utilizing this information theoretic perspective, a two-stage adaptive target search strategy based on the sorted Posterior Matching channel coding strategy is proposed. Furthermore, using information theoretic converses, the fundamental limits on the target acquisition rate for adaptive and non-adaptive strategies are characterized. As a corollary to the non-asymptotic upper bound of the expected number of measurements under the proposed two-stage strategy, and to non-asymptotic lower bound of the expected number of measurements for optimal non-adaptive search strategy, a lower bound on the adaptivity gain is obtained. The adaptivity gain is further investigated in different asymptotic regimes of interest.
- 29 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 12 (5) , 871-885
Improved Target Acquisition Rates With Feedback Codes
This paper considers the problem of acquiring an unknown target location (among a finite number of locations) via a sequence of measurements, where each measurement consists of simultaneously probing a group of locations. The resulting observation consists of a sum of an indicator of the target's presence in the probed region, and a zero mean Gaussian noise term whose variance is a function of the measurement vector. An equivalence between the target acquisition problem and channel coding over a binary input additive white Gaussian noise (BAWGN) channel with state and feedback is established. Utilizing this information theoretic perspective, a two-stage adaptive target search strategy based on the sorted Posterior Matching channel coding strategy is proposed. Furthermore, using information theoretic converses, the fundamental limits on the target acquisition rate for adaptive and non-adaptive strategies are characterized. As a corollary to the non-asymptotic upper bound of the expected number of measurements under the proposed two-stage strategy, and to non-asymptotic lower bound of the expected number of measurements for optimal non-adaptive search strategy, a lower bound on the adaptivity gain is obtained. The adaptivity gain is further investigated in different asymptotic regimes of interest.
- 1 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 321-325
Bit-wise Sequential Coding with Feedback
This paper considers the problem of bit-wise channel coding over a Binary Symmetric Channel (BSC) with feedback. While it is known that feedback does not increase the capacity of a memoryless channel, it is believed to simplify the coding schemes for some channels. The most significant one is the Binary Erasure Channel (BEC) where capacity is achieved by a simple sequential bit-wise repetition code under which each bit is (re-)transmitted until it is received. This sequential bit-wise feedback code has the added advantage that it can be used for streaming applications over BECs. In contrast, there is no known sequential bit-wise code with feedback that can achieve nonzero transmission rate for a BSC. For example, under Posterior Matching for a binary input channel with feedback, also known as Horstein scheme, each message is considered in its entirety in a block coding manner. This paper proposes a sequential feedback coding scheme with a nested bit-wise structure that generalizes repetition codes. This scheme is shown to achieve strictly positive rate for a large class of binary input channels including a BSC with arbitrary cross-over probability p ∈ (0, 1/2). The analysis relies on characterizing a lower bound on the step-wise Extrinsic Jensen Shannon divergence.
- 1 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 321-325
Bit-wise Sequential Coding with Feedback
This paper considers the problem of bit-wise channel coding over a Binary Symmetric Channel (BSC) with feedback. While it is known that feedback does not increase the capacity of a memoryless channel, it is believed to simplify the coding schemes for some channels. The most significant one is the Binary Erasure Channel (BEC) where capacity is achieved by a simple sequential bit-wise repetition code under which each bit is (re-)transmitted until it is received. This sequential bit-wise feedback code has the added advantage that it can be used for streaming applications over BECs. In contrast, there is no known sequential bit-wise code with feedback that can achieve nonzero transmission rate for a BSC. For example, under Posterior Matching for a binary input channel with feedback, also known as Horstein scheme, each message is considered in its entirety in a block coding manner. This paper proposes a sequential feedback coding scheme with a nested bit-wise structure that generalizes repetition codes. This scheme is shown to achieve strictly positive rate for a large class of binary input channels including a BSC with arbitrary cross-over probability p ∈ (0, 1/2). The analysis relies on characterizing a lower bound on the step-wise Extrinsic Jensen Shannon divergence.
- Top Cited Papers
- 15 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 64 (9) , 6161-6179
Social Learning and Distributed Hypothesis Testing
This paper considers a problem of distributed hypothesis testing over a network. Individual nodes in a network receive noisy local (private) observations whose distribution is parameterized by a discrete parameter (hypothesis). The marginals of the joint observation distribution conditioned on each hypothesis are known locally at the nodes, but the true parameter/hypothesis is not known. An update rule is analyzed in which nodes first perform a Bayesian update of their belief (distribution estimate) of each hypothesis based on their local observations, communicate these updates to their neighbors, and then perform a “non-Bayesian” linear consensus using the log-beliefs of their neighbors. Under mild assumptions, we show that the belief of any node on a wrong hypothesis converges to zero exponentially fast. We characterize the exponential rate of learning, which we call the network divergence, in terms of the nodes’ influence of the network and the divergences between the observations’ distributions. For a broad class of observation statistics which includes distributions with unbounded support such as Gaussian mixtures, we show that rate of rejection of wrong hypothesis satisfies a large deviation principle i.e., the probability of sample paths on which the rate of rejection of wrong hypothesis deviates from the mean rate vanishes exponentially fast and we characterize the rate function in terms of the nodes’ influence of the network and the local observation models.
- 15 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 64 (9) , 6161-6179
Top Cited PapersSocial Learning and Distributed Hypothesis Testing
This paper considers a problem of distributed hypothesis testing over a network. Individual nodes in a network receive noisy local (private) observations whose distribution is parameterized by a discrete parameter (hypothesis). The marginals of the joint observation distribution conditioned on each hypothesis are known locally at the nodes, but the true parameter/hypothesis is not known. An update rule is analyzed in which nodes first perform a Bayesian update of their belief (distribution estimate) of each hypothesis based on their local observations, communicate these updates to their neighbors, and then perform a “non-Bayesian” linear consensus using the log-beliefs of their neighbors. Under mild assumptions, we show that the belief of any node on a wrong hypothesis converges to zero exponentially fast. We characterize the exponential rate of learning, which we call the network divergence, in terms of the nodes’ influence of the network and the divergences between the observations’ distributions. For a broad class of observation statistics which includes distributions with unbounded support such as Gaussian mixtures, we show that rate of rejection of wrong hypothesis satisfies a large deviation principle i.e., the probability of sample paths on which the rate of rejection of wrong hypothesis deviates from the mean rate vanishes exponentially fast and we characterize the rate function in terms of the nodes’ influence of the network and the local observation models.
- 1 November 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1065-1069
Large deviation analysis for learning rate in distributed hypothesis testing
This paper considers a problem of distributed hypothesis testing and cooperative learning. Individual nodes in a network receive noisy local (private) observations whose distribution is parameterized by a discrete parameter (hypotheses). The conditional distributions are known locally at the nodes, but the true parameter/hypothesis is not known. We consider a social ("non-Bayesian") learning rule from previous literature, in which nodes first perform a Bayesian update of their belief (distribution estimate) of the parameter based on their local observation, communicate these updates to their neighbors, and then perform a "non-Bayesian" linear consensus using the log-beliefs of their neighbors. For this learning rule, we know that under mild assumptions, the belief of any node in any incorrect parameter converges to zero exponentially fast, and the exponential rate of learning is a characterized by the network structure and the divergences between the observations' distributions. Furthermore, any (large) deviation from this nominal rate of rejecting wrong hypothesis is known to occur with an exponentially small probability when the bounded likelihood functions is uniformly bounded. While relaxing the assumption of uniformly bounded log-likelihood functions, we show that the rates of rejecting wrong hypotheses, collectively, satisfy a large deviation principle under a mild technical condition on the log-moment generating functions of log-likelihood random variables.
- 1 November 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1065-1069
Large deviation analysis for learning rate in distributed hypothesis testing
This paper considers a problem of distributed hypothesis testing and cooperative learning. Individual nodes in a network receive noisy local (private) observations whose distribution is parameterized by a discrete parameter (hypotheses). The conditional distributions are known locally at the nodes, but the true parameter/hypothesis is not known. We consider a social ("non-Bayesian") learning rule from previous literature, in which nodes first perform a Bayesian update of their belief (distribution estimate) of the parameter based on their local observation, communicate these updates to their neighbors, and then perform a "non-Bayesian" linear consensus using the log-beliefs of their neighbors. For this learning rule, we know that under mild assumptions, the belief of any node in any incorrect parameter converges to zero exponentially fast, and the exponential rate of learning is a characterized by the network structure and the divergences between the observations' distributions. Furthermore, any (large) deviation from this nominal rate of rejecting wrong hypothesis is known to occur with an exponentially small probability when the bounded likelihood functions is uniformly bounded. While relaxing the assumption of uniformly bounded log-likelihood functions, we show that the rates of rejecting wrong hypotheses, collectively, satisfy a large deviation principle under a mild technical condition on the log-moment generating functions of log-likelihood random variables.
- 1 September 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
On the rate of learning in distributed hypothesis testing
This paper considers a problem of distributed hypothesis testing and cooperative learning. Individual nodes in a network receive noisy local (private) observations whose distribution is parameterized by a discrete parameter (hypotheses). The conditional distributions are known locally at the nodes, but the true parameter/hypothesis is not known. We consider a social (“non-Bayesian”) learning rule from previous literature, in which nodes first perform a Bayesian update of their belief (distribution estimate) of the parameter based on their local observation, communicate these updates to their neighbors, and then perform a “non-Bayesian” linear consensus using the log-beliefs of their neighbors. For this learning rule, we know that under mild assumptions, the belief of any node in any incorrect parameter converges to zero exponentially fast, and the exponential rate of learning is a characterized by the network structure and the divergences between the observations' distributions. Tight bounds on the probability of deviating from this nominal rate in aperiodic networks is derived. The bounds are shown to hold for all conditional distributions which satisfy a mild bounded moment condition.
- 1 September 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
On the rate of learning in distributed hypothesis testing
This paper considers a problem of distributed hypothesis testing and cooperative learning. Individual nodes in a network receive noisy local (private) observations whose distribution is parameterized by a discrete parameter (hypotheses). The conditional distributions are known locally at the nodes, but the true parameter/hypothesis is not known. We consider a social (“non-Bayesian”) learning rule from previous literature, in which nodes first perform a Bayesian update of their belief (distribution estimate) of the parameter based on their local observation, communicate these updates to their neighbors, and then perform a “non-Bayesian” linear consensus using the log-beliefs of their neighbors. For this learning rule, we know that under mild assumptions, the belief of any node in any incorrect parameter converges to zero exponentially fast, and the exponential rate of learning is a characterized by the network structure and the divergences between the observations' distributions. Tight bounds on the probability of deviating from this nominal rate in aperiodic networks is derived. The bounds are shown to hold for all conditional distributions which satisfy a mild bounded moment condition.
- 1 February 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Power-optimal scheduling for a Green Base station with delay constraints
We consider a power optimization problem with average delay constraint on the downlink of a Green Base-station. A Green Base-station is powered by both renewable energy such as solar or wind energy as well as conventional sources like diesel generators or the power grid. We try to minimize the energy drawn from conventional energy sources and utilize the harvested energy to the maximum extent. Each user also has an average delay constraint for its data. The optimal action consists of scheduling the users and allocating the optimal transmission rate for the chosen user. In this paper, we formulate the problem as a Markov Decision Problem and show the existence of a stationary average-cost optimal policy. We also derive some structural results for the optimal policy.
- 1 February 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Power-optimal scheduling for a Green Base station with delay constraints
We consider a power optimization problem with average delay constraint on the downlink of a Green Base-station. A Green Base-station is powered by both renewable energy such as solar or wind energy as well as conventional sources like diesel generators or the power grid. We try to minimize the energy drawn from conventional energy sources and utilize the harvested energy to the maximum extent. Each user also has an average delay constraint for its data. The optimal action consists of scheduling the users and allocating the optimal transmission rate for the chosen user. In this paper, we formulate the problem as a Markov Decision Problem and show the existence of a stationary average-cost optimal policy. We also derive some structural results for the optimal policy.
- 1 February 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Power and delay optimal policies for wireless systems
In this paper we consider a single discrete time queue with infinite buffer. The channel may experience fading. The transmission rate is a linear function of power used for transmission. In this scenario we explicitly obtain power control policies which minimize mean power and/or mean delay. There may also be peak power constraint.
- 1 February 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Power and delay optimal policies for wireless systems
In this paper we consider a single discrete time queue with infinite buffer. The channel may experience fading. The transmission rate is a linear function of power used for transmission. In this scenario we explicitly obtain power control policies which minimize mean power and/or mean delay. There may also be peak power constraint.