# Lav VarshneyIBM · Thomas J. Watson Research Center

Lav Varshney

## About

182

Publications

11,305

Reads

**How we measure 'reads'**

A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more

1,782

Citations

## Publications

Publications (182)

Concrete is the most widely used engineered material in the world with more than 10 billion tons produced annually. Unfortunately, with that scale comes a significant burden in terms of energy, water, and release of greenhouse gases and other pollutants; indeed 8% of worldwide carbon emissions are attributed to the production of cement, a key ingre...

This work investigates functional source coding problems with maximal distortion, motivated by approximate function computation in many modern applications. The maximal distortion treats imprecise reconstruction of a function value as good as perfect computation if it deviates less than a tolerance level, while treating reconstruction that differs...

This paper presents a quantized Kalman filter implemented using unreliable memories. We consider that both the quantization and the unreliable memories introduce errors in the computations, and we develop an error propagation model that takes into account these two sources of errors. In addition to providing updated Kalman filter equations, the pro...

Humans can generalize from only a few examples and from little pre-training on similar tasks. Yet, machine learning (ML) typically requires large data to learn or pre-learn to transfer. Inspired by nativism, we directly model basic human-innate priors in abstract visual tasks e.g., character/doodle recognition. This yields a white-box model that le...

The Invariant Risk Minimization (IRM) framework aims to learn invariant features from a set of environments for solving the out-of-distribution (OOD) generalization problem. The underlying assumption is that the causal components of the data generating distributions remain constant across the environments or alternately, the data "overlaps" across...

Background
Social capital has been associated with health outcomes in communities and can explain variations in different geographic localities. Social capital has also been associated with behaviors that promote better health and reduce the impacts of diseases. During the COVID-19 pandemic, social distancing, face masking, and vaccination have all...

We model an epidemic where the per-person infectiousness in a network of geographic localities changes with the total number of active cases. This would happen as people adopt more stringent non-pharmaceutical precautions when the population has a larger number of active cases. We show that there exists a sharp threshold: if the curing rate of the...

Consider a Bayesian binary decision-making problem in star networks, where local agents make selfish decisions independently, and a fusion agent makes a final decision based on aggregated decisions and its own private signal. In particular, we assume all agents have private beliefs for the true prior probability, based on which they perform Bayesia...

This paper presents a quantized Kalman filter implemented using unreliable memories. We consider that both the quantization and the unreliable memories introduce errors in the computations, and develop an error propagation model that takes into account these two sources of errors. In addition to providing updated Kalman filter equations, the propos...

Blockchains store transaction data in the form of a distributed ledger where each node in the network stores a current copy of the sequence of transactions as a hash chain. This requirement of storing the entire ledger incurs a high storage cost that grows undesirably large for high transaction rates and large networks. In this work we use secret k...

The papers in this special section focuses on signal processing advances in wireless transmission of power and information. Wireless power transfer (WPT) and wireless information and power transfer (WIPT) have received growing attention in the research community in the past few years. In this special issue, a total of fourteen papers present state-...

Wireless power transfer (WPT) is an emerging paradigm that will enable using wireless to its full potential in future networks, not only to convey information but also to deliver energy. Such networks will enable trillions of future low-power devices to sense, compute, connect, and energize anywhere, anytime, and on the move. The design of such fut...

Evaluating the inherent difficulty of a given data-driven classification problem is important for establishing absolute benchmarks and evaluating progress in the field. To this end, a natural quantity to consider is the \emph{Bayes error}, which measures the optimal classification error theoretically achievable for a given data distribution. While...

Neural text decoding algorithms strongly influence the quality of texts generated using language models, but popular algorithms like top-k, top-p (nucleus), and temperature-based sampling may yield texts that have objectionable repetition or incoherence. Although these methods generate high-quality text after ad hoc parameter tuning that depends on...

The CEO problem has received much attention since first introduced by Berger et al., but there are limited results on non-Gaussian models with non-quadratic distortion measures. In this work, we extend the quadratic Gaussian CEO problem to two non-Gaussian settings with general rth power of difference distortion. Assuming an identical observation c...

Recent works show that including group equivariance as an inductive bias improves neural network performance for both classification and generation tasks. Designing group-equivariant neural networks is, however, challenging when the group of interest is large and is unknown. Moreover, inducing equivariance can significantly reduce the number of ind...

Missing values imputation is often evaluated on some similarity measure between actual and imputed data. However, it may be more meaningful to evaluate downstream algorithm performance after imputation than the imputation itself. We describe a straightforward unsupervised imputation algorithm, a minimax approach based on optimal recovery, and deriv...

We model an epidemic where the per-person infectiousness in a network of geographic localities changes with the total number of active cases. This would happen as people adopt more stringent non-pharmaceutical precautions when the population has a larger number of active cases. We show that there exists a sharp threshold such that when the curing r...

Constrained coding is used widely in digital communication and storage systems. In this article, we study a generalized sliding window constraint called the skip-sliding window. A skip-sliding window (SSW) code is defined in terms of the length
$L$
of a sliding window, skip length
$J$
, and cost constraint
$E$
in each sliding window. Each val...

Wireless power transfer (WPT) is an emerging paradigm that will enable using wireless to its full potential in future networks, not only to convey information but also to deliver energy. Such networks will enable trillions of future low-power devices to sense, compute, connect, and energize anywhere, anytime, and on the move. The design of such fut...

This paper studies the adversarial graphical contextual bandits, a variant of adversarial multi-armed bandits that leverage two categories of the most common side information: \emph{contexts} and \emph{side observations}. In this setting, a learning agent repeatedly chooses from a set of $K$ actions after being presented with a $d$-dimensional cont...

Many information sources are not just sequences of distinguishable symbols but rather have invariances governed by alternative counting paradigms such as permutations, combinations, and partitions. We consider an entire classification of these invariances called the twelvefold way in enumerative combinatorics and develop a method to characterize lo...

Previous work has shown that for contagion processes on extended star networks (trees with exactly one node of degree > 2), there is a simple, closed-form expression for a highly accurate approximation to the maximum likelihood infection source. Here, we generalize that result to a class of hypertrees which, although somewhat structurally analogous...

Human creativity is often described as the mental process of combining associative elements into a new form, but emerging computational creativity algorithms may not operate in this manner. Here we develop an inverse problem formulation to deconstruct the products of combinatorial and compositional creativity into associative chains as a form of po...

We consider reinforcement learning (RL) in episodic Markov decision processes (MDPs) with linear function approximation under drifting environment. Specifically, both the reward and state transition functions can evolve over time, as long as their respective total variations, quantified by suitable metrics, do not exceed certain \textit{variation b...

The “bee-identification problem” was formally defined by Tandon, Tan and Varshney [
IEEE Trans. Commun.
, vol. 67, 2019], and the error exponent was studied. This work extends the results for the “absentee bees” scenario, where a fraction of the bees are absent in the beehive image used for identification. For this setting, we present an
exact
c...

We consider transmission of packets over queue-length sensitive unreliable links, where packets are randomly corrupted through a noisy channel whose transition probabilities are modulated by the queue-length. The goal is to characterize the capacity of this channel. We particularly consider multiple-access systems, where transmitters dispatch encod...

Neural text decoding is important for generating high-quality texts using language models. To generate high-quality text, popular decoding algorithms like top-k, top-p (nucleus), and temperature-based sampling truncate or distort the unreliable low probability tail of the language model. Though these methods generate high-quality text after paramet...

We investigate fusing several unreliable computational units that perform the same task. We model an unreliable computational outcome as an additive perturbation to its error-free result in terms of its fidelity and cost. We analyze reliability of replication-based strategies that distribute cost across several unreliable units and fuse their outco...

Interpretability of machine learning models has gained more and more attention among researchers in the artificial intelligence (AI) and human-computer interaction (HCI) communities. Most existing work focuses on decision making, whereas we consider knowledge discovery. In particular, we focus on evaluating AI-discovered knowledge/rules in the arts...

We propose the use of binary skip-sliding window (SSW) codes in the emerging area of simultaneous energy and information transfer, where the receiver uses the received signal for decoding information as well as for harvesting energy to run its circuitry. Binary SSW codes satisfy certain weight constraints over a skip-sliding window, and generalize...

Due to energy-efficiency requirements, computational systems are now being implemented using noisy nanoscale semiconductor devices whose reliability depends on energy consumed. We study circuit-level energy-reliability limits for deep feedforward neural networks (multilayer perceptrons) built using such devices, and en route also establish the same...

Full-duplex communication allows a terminal to transmit and receive signals simultaneously, and hence, it is helpful in general to adapt transmissions to received signals. However, this often requires unaffordable complexity. This work focuses on simple non-adaptive transmission, and provides two classes of channels for which Shannon’s information...

We study the problem of image registration in the finite-resolution regime and characterize the error probability of algorithms as a function of properties of the transformation and the image capture noise. Specifically, we define a channel-aware Feinstein decoder to obtain upper bounds on the minimum achievable error probability under finite resol...

Consider a social learning problem in a parallel network, where $N$ distributed agents make independent selfish binary decisions, and a central agent aggregates them together with a private signal to make a final decision. In particular, all agents have private beliefs for the true prior, based on which they perform binary hypothesis testing. We fo...

Neurobiological systems operate at power levels that are unattainable by modern electronic systems while exhibiting broader information processing capabilities for a number of important tasks. A variety of engineered systems designed for energy efficiency or hardware simplicity use time-based signal representations, which share similar mathematical...

The "bee-identification problem" was formally defined by Tandon, Tan and Varshney [IEEE Trans. Commun. (2019) [Online early access]], and the error exponent was studied. This work extends the results for the "absentee bees" scenario, where a small fraction of the bees are absent in the beehive image used for identification. For this setting, we pre...

We consider the problem of coding for computing with maximal distortion, where the sender communicates with a receiver, which has its own private data and wants to compute a function of their combined data with some fidelity constraint known to both agents. We show that the minimum rate for this problem is equal to the conditional entropy of a hype...

Isometries and their induced symmetries are ubiquitous in the world. Taking a computational perspective, this paper considers isometries of $\mathbb{Z}^n$ (since values are discrete in digital computers), and tackles the problem of orbit computation under various isometry subgroup actions on $\mathbb{Z}^n$. Rather than just conceptually, we aim for...

We present a principled framework to address resource allocation for realizing boosting algorithms on substrates with communication or computation noise. Boosting classifiers (e.g., AdaBoost) make a final decision via a weighted vote from the outputs of many base classifiers (weak classifiers). Suppose that the base classifiers' outputs are noisy o...

This work explores a social learning problem with agents having nonidentical noise variances and mismatched beliefs. We consider an
$N$
-agent binary hypothesis test in which each agent sequentially makes a decision based not only on a private observation, but also on preceding agents' decisions. In addition, the agents have their own beliefs ins...

Consider the problem of identifying a massive number of bees, uniquely labeled with barcodes, using noisy measurements. We formally introduce this “bee-identification problem”, define its error exponent, and derive efficiently computable upper and lower bounds for this exponent. We show that joint decoding of barcodes provides a significantly bette...

Full-duplex communication allows a terminal to transmit and receive signals simultaneously, and hence, it is helpful in general to adapt transmissions to received signals. However, this often requires unaffordable complexity. This work focuses on simple non-adaptive transmission, and provides two classes of channels for which Shannon's information...

It is commonly observed that higher workload lowers job performance. We model the workload as a queueing process and study the information-theoretic limits of reliable communication through a system with queue-length dependent service quality. The goal is to investigate a multiple-access setting, where transmitters dispatch encoded symbols over a s...

Run-length limited (RLL) codes are a well-studied class of constrained codes having application in diverse areas, such as optical and magnetic data recording systems, DNA-based storage, and visible light communication. RLL codes have also been proposed for the emerging area of simultaneous energy and information transfer, where the receiver uses th...

We extend the approximation-theoretic technique of optimal recovery to the setting of imputing missing values in clustered data, specifically for non-negative matrix factorization (NMF), and develop an implementable algorithm. Under certain geometric conditions, we prove tight upper bounds on NMF relative error, which is the first bound of this typ...

Concrete is the most widely used engineered material in the world with more than 10 billion tons produced annually. Unfortunately, with that scale comes a significant burden in terms of energy, water, and release of greenhouse gases and other pollutants. As such, there is interest in creating concrete formulas that minimize this environmental burde...

Consider the problem of identifying a massive number of bees, uniquely labeled with barcodes, using noisy measurements. We formally introduce this ``bee-identification problem'', define its error exponent, and derive efficiently computable upper and lower bounds for this exponent. We show that joint decoding of barcodes provides a significantly bet...

This work investigates the fundamental limits of communication over a noisy discrete memoryless channel that wears out, in the sense of signal-dependent catastrophic failure. In particular, we consider a channel that starts as a memoryless binary-input channel and when the number of transmitted ones causes a sufficient amount of damage, the channel...

This paper considers the problem of simultaneous information and energy transmission (SIET), where the energy harvesting function is only known experimentally at sample points, e.g., due to nonlinearities and parameter uncertainties in harvesting circuits. We investigate the performance loss due to this partial knowledge of the harvesting function...

In a recent essay on the role of modern information technologies in democratic processes, Zeynep Tufekci described the actions of Egyptian leader Hosni Mubarak in cutting off Internet and cellular service during the 2011 Tahrir uprising as follows: "The move backfired: it restricted the flow of information coming out of Tahrir Square but caused int...

Computational creativity is an emerging branch of artificial intelligence that places computers in the center of the creative process. Broadly, creativity involves a generative step to produce many ideas and a selective step to determine the ones that are the best. Many previous attempts at computational creativity, however, have not been able to a...

Computational creativity is an emerging branch of artificial intelligence (AI) concerned with algorithms that can create novel and high-quality ideas or artifacts, either autonomously or semi-autonomously in collaboration with people. Quite simply, such algorithms may be described as artificial innovation engines. These technologies raise questions...

Blockchain systems store transaction data in the form of a distributed ledger where each peer is to maintain an identical copy. Blockchain systems resemble repetition codes, incurring high storage cost. Recently, distributed storage blockchain (DSB) systems have been proposed to improve storage efficiency by incorporating secret sharing, private ke...

The CEO problem has received a lot of attention since Berger et al.~first investigated it, however, there are limited results on non-Gaussian models with non-quadratic distortion measures. In this work, we extend the CEO problem to two continuous alphabet settings with general $r$th power of difference and logarithmic distortions, and study asympto...