Venkata Sriram Siddhardh Nadendla

Venkata Sriram Siddhardh Nadendla, Emrah Akyol, Cedric Langbort et al.

In this paper, we model a Stackelberg game in a simple Gaussian test channel where a human transmitter (leader) communicates a source message to a human receiver (follower). We model human decision making using prospect theory models proposed for continuous decision spaces. Assuming that the value function is the squared distortion at both the transmitter and the receiver, we analyze the effects of the weight functions at both the transmitter and the receiver on optimal communication strategies, namely encoding at the transmitter and decoding at the receiver, in the Stackelberg sense. We show that the optimal strategies for the behavioral agents in the Stackelberg sense are identical to those designed for unbiased agents. At the same time, we also show that the prospect-theoretic distortions at both the transmitter and the receiver are both larger than the expected distortion, thus making behavioral agents less contended than unbiased agents. Consequently, the presence of cognitive biases increases the need for transmission power in order to achieve a given distortion at both transmitter and receiver.

Nathan Lutes, Venkata Sriram Siddhardh Nadendla, K. Krishnamurthy

Objective: This work explores use of a few-shot transfer learning method to train and implement a convolutional spiking neural network (CSNN) on a BrainChip Akida AKD1000 neuromorphic system-on-chip for developing individual-level, instead of traditionally used group-level, models using electroencephalographic data. Main Results: Efficacy of the above methodology to develop individual-specific braking intention predictive models by rapidly adapting the group-level model in as few as three training epochs while achieving at least 90% accuracy, true positive rate and true negative rate is presented. Further, results show the energy-efficiency of the neuromorphic hardware through a power reduction of over 97% with only a $1.3* increase in latency when using the Akida AKD1000 processor for network inference compared to an Intel Xeon central processing unit. Similar results were obtained in a subsequent ablation study using a subset of five out of 19 channels.

Mukund Telukunta, Venkata Sriram Siddhardh Nadendla, Morgan Stuart et al.

Regression-based predictive analytics used in modern kidney transplantation is known to inherit biases from training data. This leads to social discrimination and inefficient organ utilization, particularly in the context of a few social groups. Despite this concern, there is limited research on fairness in regression and its impact on organ utilization and placement. This paper introduces three novel divergence-based group fairness notions: (i) independence, (ii) separation, and (iii) sufficiency to assess the fairness of regression-based analytics tools. In addition, fairness preferences are investigated from crowd feedback, in order to identify a socially accepted group fairness criterion for evaluating these tools. A total of 85 participants were recruited from the Prolific crowdsourcing platform, and a Mixed-Logit discrete choice model was used to model fairness feedback and estimate social fairness preferences. The findings clearly depict a strong preference towards the separation and sufficiency fairness notions, and that the predictive analytics is deemed fair with respect to gender and race groups, but unfair in terms of age groups.

Sree Pooja Akula, Mukund Telukunta, Venkata Sriram Siddhardh Nadendla

Drivers in ridesharing platforms exhibit cognitive atrophy and fatigue as they accept ride offers along the day, which can have a significant impact on the overall efficiency of the ridesharing platform. In contrast to the current literature which focuses primarily on modeling and learning driver's preferences across different ride offers, this paper proposes a novel Dynamic Discounted Satisficing (DDS) heuristic to model and predict driver's sequential ride decisions during a given shift. Based on DDS heuristic, a novel stochastic neural network with random activations is proposed to model DDS heuristic and predict the final decision made by a given driver. The presence of random activations in the network necessitated the development of a novel training algorithm called Sampling-Based Back Propagation Through Time (SBPTT), where gradients are computed for independent instances of neural networks (obtained via sampling the distribution of activation threshold) and aggregated to update the network parameters. Using both simulation experiments as well as on real Chicago taxi dataset, this paper demonstrates the improved performance of the proposed approach, when compared to state-of-the-art methods.

Mukund Telukunta, Venkata Sriram Siddhardh Nadendla

Algorithmic fairness literature presents numerous mathematical notions and metrics, and also points to a tradeoff between them while satisficing some or all of them simultaneously. Furthermore, the contextual nature of fairness notions makes it difficult to automate bias evaluation in diverse algorithmic systems. Therefore, in this paper, we propose a novel model called latent assessment model (LAM) to characterize binary feedback provided by human auditors, by assuming that the auditor compares the classifier's output to his or her own intrinsic judgment for each input. We prove that individual and group fairness notions are guaranteed as long as the auditor's intrinsic judgments inherently satisfy the fairness notion at hand, and are relatively similar to the classifier's evaluations. We also demonstrate this relationship between LAM and traditional fairness notions on three well-known datasets, namely COMPAS, German credit and Adult Census Income datasets. Furthermore, we also derive the minimum number of feedback samples needed to obtain PAC learning guarantees to estimate LAM for black-box classifiers. These guarantees are also validated via training standard machine learning algorithms on real binary feedback elicited from 400 human auditors regarding COMPAS.

Nathan Lutes, K. Krishnamurthy, Venkata Sriram Siddhardh Nadendla et al.

Adaptive methods are popular within the control literature due to the flexibility and forgiveness they offer in the area of modelling. Neural network adaptive control is favorable specifically for the powerful nature of the machine learning algorithm to approximate unknown functions and for the ability to relax certain constraints within traditional adaptive control. Deep neural networks are large framework networks with vastly superior approximation characteristics than their shallow counterparts. However, implementing a deep neural network can be difficult due to size specific complications such as vanishing/exploding gradients in training. In this paper, a neuro-adaptive controller is implemented featuring a deep neural network trained on a new weight update law that escapes the vanishing/exploding gradient problem by only incorporating the sign of the gradient. The type of controller designed is an adaptive dynamic inversion controller utilizing a modified state observer in a secondary estimation loop to train the network. The deep neural network learns the entire plant model on-line, creating a controller that is completely model free. The controller design is tested in simulation on a 2 link planar robot arm. The controller is able to learn the nonlinear plant quickly and displays good performance in the tracking control problem.

Qizi Zhang, Venkata Sriram Siddhardh Nadendla, S. N. Balakrishnan et al.

State-of-the-art driver-assist systems have failed to effectively mitigate driver inattention and had minimal impacts on the ever-growing number of road mishaps (e.g. life loss, physical injuries due to accidents caused by various factors that lead to driver inattention). This is because traditional human-machine interaction settings are modeled in classical and behavioral game-theoretic domains which are technically appropriate to characterize strategic interaction between either two utility maximizing agents, or human decision makers. Therefore, in an attempt to improve the persuasive effectiveness of driver-assist systems, we develop a novel strategic and personalized driver-assist system which adapts to the driver's mental state and choice behavior. First, we propose a novel equilibrium notion in human-system interaction games, where the system maximizes its expected utility and human decisions can be characterized using any general decision model. Then we use this novel equilibrium notion to investigate the strategic driver-vehicle interaction game where the car presents a persuasive recommendation to steer the driver towards safer driving decisions. We assume that the driver employs an open-quantum system cognition model, which captures complex aspects of human decision making such as violations to classical law of total probability and incompatibility of certain mental representations of information. We present closed-form expressions for players' final responses to each other's strategies so that we can numerically compute both pure and mixed equilibria. Numerical results are presented to illustrate both kinds of equilibria.

Mukund Telukunta, Venkata Sriram Siddhardh Nadendla

Bias evaluation in machine-learning based services (MLS) based on traditional algorithmic fairness notions that rely on comparative principles is practically difficult, making it necessary to rely on human auditor feedback. However, in spite of taking rigorous training on various comparative fairness notions, human auditors are known to disagree on various aspects of fairness notions in practice, making it difficult to collect reliable feedback. This paper offers a paradigm shift to the domain of algorithmic fairness via proposing a new fairness notion based on the principle of non-comparative justice. In contrary to traditional fairness notions where the outcomes of two individuals/groups are compared, our proposed notion compares the MLS' outcome with a desired outcome for each input. This desired outcome naturally describes a human auditor's expectation, and can be easily used to evaluate MLS on crowd-auditing platforms. We show that any MLS can be deemed fair from the perspective of comparative fairness (be it in terms of individual fairness, statistical parity, equal opportunity or calibration) if it is non-comparatively fair with respect to a fair auditor. We also show that the converse holds true in the context of individual fairness. Given that such an evaluation relies on the trustworthiness of the auditor, we also present an approach to identify fair and reliable auditors by estimating their biases with respect to a given set of sensitive attributes, as well as quantify the uncertainty in the estimation of biases within a given MLS. Furthermore, all of the above results are also validated on COMPAS, German credit and Adult Census Income datasets.

Sainath Sanga, Venkata Sriram Siddhardh Nadendla

Crowdsourcing-based content moderation is a platform that hosts content moderation tasks for crowd workers to review user submissions (e.g. text, images and videos) and make decisions regarding the admissibility of the posted content, along with a gamut of other tasks such as image labeling and speech-to-text conversion. In an attempt to reduce cognitive overload at the workers and improve system efficiency, these platforms offer personalized task recommendations according to the worker's preferences. However, the current state-of-the-art recommendation systems disregard the effects on worker's mental health, especially when they are repeatedly exposed to content moderation tasks with extreme content (e.g. violent images, hate-speech). In this paper, we propose a novel, strategic recommendation system for the crowdsourcing platform that recommends jobs based on worker's mental status. Specifically, this paper models interaction between the crowdsourcing platform's recommendation system (leader) and the worker (follower) as a Bayesian Stackelberg game where the type of the follower corresponds to the worker's cognitive atrophy rate and task preferences. We discuss how rewards and costs should be designed to steer the game towards desired outcomes in terms of maximizing the platform's productivity, while simultaneously improving the working conditions of crowd workers.

Mukund Telukunta, Venkata Sriram Siddhardh Nadendla

Decision-support systems are information systems that offer support to people's decisions in various applications such as judiciary, real-estate and banking sectors. Lately, these support systems have been found to be discriminatory in the context of many practical deployments. In an attempt to evaluate and mitigate these biases, algorithmic fairness literature has been nurtured using notions of comparative justice, which relies primarily on comparing two/more individuals or groups within the society that is supported by such systems. However, such a fairness notion is not very useful in the identification of fair auditors who are hired to evaluate latent biases within decision-support systems. As a solution, we introduce a paradigm shift in algorithmic fairness via proposing a new fairness notion based on the principle of non-comparative justice. Assuming that the auditor makes fairness evaluations based on some (potentially unknown) desired properties of the decision-support system, the proposed fairness notion compares the system's outcome with that of the auditor's desired outcome. We show that the proposed fairness notion also provides guarantees in terms of comparative fairness notions by proving that any system can be deemed fair from the perspective of comparative fairness (e.g. individual fairness and statistical parity) if it is non-comparatively fair with respect to an auditor who has been deemed fair with respect to the same fairness notions. We also show that the converse holds true in the context of individual fairness. A brief discussion is also presented regarding how our fairness notion can be used to identify fair and reliable auditors, and how we can use them to quantify biases in decision-support systems.

Venkata Sriram Siddhardh Nadendla, Lav R. Varshney

Blockchain systems often employ proof-of-work consensus protocols to validate and add transactions into hashchains. These protocols stimulate competition among miners in solving cryptopuzzles (e.g. SHA-256 hash computation in Bitcoin) in exchange for a monetary reward. Here, we model mining as an all-pay auction, where miners' computational efforts are interpreted as bids, and the allocation function is the probability of solving the cryptopuzzle in a single attempt with unit (normalized) computational capability. Such an allocation function captures how blockchain systems control the difficulty of the cryptopuzzle as a function of miners' computational abilities (bids). In an attempt to reduce mining costs, we investigate designing a mining auction mechanism which induces a logit equilibrium amongst the miners with choice distributions that are unilaterally decreasing with costs at each miner. We show it is impossible to design a lenient allocation function that does this. Specifically, we show that there exists no allocation function that discourages miners to bid higher costs at logit equilibrium, if the rate of change of difficulty with respect to each miner's cost is bounded by the inverse of the sum of costs at all the miners.

Doris E. M. Brown, Venkata Sriram Siddhardh Nadendla

Strategic information design is a framework where a sender designs information strategically to steer its receiver's decision towards a desired choice. Traditionally, such frameworks have always assumed that the sender and the receiver comprehends the state of the choice environment, and that the receiver always trusts the sender's signal. This paper deviates from these assumptions and re-investigates strategic information design in the presence of distrustful receiver and when both sender and receiver cannot observe/comprehend the environment state space. Specifically, we assume that both sender and receiver has access to non-identical beliefs about choice rewards (with sender's belief being more accurate), but not the environment state that determines these rewards. Furthermore, given that the receiver does not trust the sender, we also assume that the receiver updates its prior in a non-Bayesian manner. We evaluate the Stackelberg equilibrium and investigate effects of information framing (i.e. send complete signal, or just expected value of the signal) on the equilibrium. Furthermore, we also investigate trust dynamics at the receiver, under the assumption that the receiver minimizes regret in hindsight. Simulation results are presented to illustrate signaling effects and trust dynamics in strategic information design.

Venkata Sriram Siddhardh Nadendla, Cedric Langbort

Revealed preference theory studies the possibility of modeling an agent's revealed preferences and the construction of a consistent utility function. However, modeling agent's choices over preference orderings is not always practical and demands strong assumptions on human rationality and data-acquisition abilities. Therefore, we propose a simple generative choice model where agents are assumed to generate the choice probabilities based on latent factor matrices that capture their choice evaluation across multiple attributes. Since the multi-attribute evaluation is typically hidden within the agent's psyche, we consider a signaling mechanism where agents are provided with choice information through private signals, so that the agent's choices provide more insight about his/her latent evaluation across multiple attributes. We estimate the choice model via a novel multi-stage matrix factorization algorithm that minimizes the average deviation of the factor estimates from choice data. Simulation results are presented to validate the estimation performance of our proposed algorithm.