Mayank Baranwal

Mayank Baranwal, Srinivasa M. Salapaka, Murti V. Salapaka

This paper addresses the problem of output voltage regulation for multiple DC-DC converters connected to a grid, and prescribes a robust scheme for sharing power among different sources. Also it develops a method for sharing 120 Hz ripple among DC power sources in a prescribed proportion, which accommodates the different capabilities of DC power sources to sustain the ripple. We present a decentralized control architecture, where a nested (inner-outer) control design is used at every converter. An interesting aspect of the proposed design is that the analysis and design of the entire multi-converter system can be done using an equivalent single converter system, where the multi-converter system inherits the performance and robustness achieved by a design for the single-converter system. Another key aspect of this work is that the voltage regulation problem is addressed as a disturbance-rejection problem, where {\em unknown} load current is viewed as an external signal, and thus, no prior information is required on the nominal loading conditions. The control design is obtained using robust optimal-control framework. Case studies presented show the enhanced performance of prescribed optimal controllers.

Ajnabiul Hoque, Manajit Das, Mayank Baranwal et al.

A chemical reaction mechanism (CRM) is a sequence of molecular-level events involving bond-breaking/forming processes, generating transient intermediates along the reaction pathway as reactants transform into products. Understanding such mechanisms is crucial for designing and discovering new reactions. One of the currently available methods to probe CRMs is quantum mechanical (QM) computations. The resource-intensive nature of QM methods and the scarcity of mechanism-based datasets motivated us to develop reliable ML models for predicting mechanisms. In this study, we created a comprehensive dataset with seven distinct classes, each representing uniquely characterized elementary steps. Subsequently, we developed an interpretable attention-based GNN that achieved near-unity and 96% accuracy, respectively for reaction step classification and the prediction of reactive atoms in each such step, capturing interactions between the broader reaction context and local active regions. The near-perfect classification enables accurate prediction of both individual events and the entire CRM, mitigating potential drawbacks of Seq2Seq approaches, where a wrongly predicted character leads to incoherent CRM identification. In addition to interpretability, our model adeptly identifies key atom(s) even from out-of-distribution classes. This generalizabilty allows for the inclusion of new reaction types in a modular fashion, thus will be of value to experts for understanding the reactivity of new molecules.

Anandsingh Chauhan, Mayank Baranwal, Ansuma Basumatary

Power grids, across the world, play an important societal and economical role by providing uninterrupted, reliable and transient-free power to several industries, businesses and household consumers. With the advent of renewable power resources and EVs resulting into uncertain generation and highly dynamic load demands, it has become ever so important to ensure robust operation of power networks through suitable management of transient stability issues and localize the events of blackouts. In the light of ever increasing stress on the modern grid infrastructure and the grid operators, this paper presents a reinforcement learning (RL) framework, PowRL, to mitigate the effects of unexpected network events, as well as reliably maintain electricity everywhere on the network at all times. The PowRL leverages a novel heuristic for overload management, along with the RL-guided decision making on optimal topology selection to ensure that the grid is operated safely and reliably (with no overloads). PowRL is benchmarked on a variety of competition datasets hosted by the L2RPN (Learning to Run a Power Network). Even with its reduced action space, PowRL tops the leaderboard in the L2RPN NeurIPS 2020 challenge (Robustness track) at an aggregate level, while also being the top performing agent in the L2RPN WCCI 2020 challenge. Moreover, detailed analysis depicts state-of-the-art performances by the PowRL agent in some of the test scenarios.

Mayank Baranwal, Srinivasa M. Salapaka

One of the most important challenges facing an electric grid is to incorporate renewables and distributed energy resources (DERs) to the grid. Because of the associated uncertainties in power generations and peak power demands, opportunities for improving the functioning and reliability of the grid lie in the design of an efficient, yet pragmatic distributed control framework with guaranteed robustness margins. This paper addresses the problem of output voltage regulation for multiple DC-DC converters connected to a grid, and prescribes a robust scheme for sharing power among different sources. More precisely, we develop a control architecture where, unlike most standard control frameworks, the desired power ratios appear as reference signals to individual converter systems, and not as internal parameters of the system of parallel converters. This makes the proposed approach suited for scenarios when the desired power ratios vary rapidly with time. Additionally, the proposed control framework is suitable to both centralized and decentralized implementations, i.e., the same control architecture can be employed for voltage regulation irrespective of the availability of common load-current (or power) measurement, without the need to modify controller parameters. The control design is obtained using robust optimal-control framework. Case studies presented show the enhanced performance of prescribed optimal controllers for voltage regulation and power sharing.

Mayank Baranwal, Param Budhraja, Vishal Raj et al.

Gradient-based first-order convex optimization algorithms find widespread applicability in a variety of domains, including machine learning tasks. Motivated by the recent advances in fixed-time stability theory of continuous-time dynamical systems, we introduce a generalized framework for designing accelerated optimization algorithms with strongest convergence guarantees that further extend to a subclass of non-convex functions. In particular, we introduce the GenFlow algorithm and its momentum variant that provably converge to the optimal solution of objective functions satisfying the Polyak-Łojasiewicz (PL) inequality in a fixed time. Moreover, for functions that admit non-degenerate saddle-points, we show that for the proposed GenFlow algorithm, the time required to evade these saddle-points is uniformly bounded for all initial conditions. Finally, for strongly convex-strongly concave minimax problems whose optimal solution is a saddle point, a similar scheme is shown to arrive at the optimal solution again in a fixed time. The superior convergence properties of our algorithm are validated experimentally on a variety of benchmark datasets.

Mayank Baranwal, Alireza Askarian, Srinivasa M. Salapaka

This paper addresses the problem of output voltage regulation for multiple DC/DC converters connected to a microgrid, and prescribes a scheme for sharing power among different sources. This architecture is structured in such a way that it admits quantifiable analysis of the closed-loop performance of the network of converters; the analysis simplifies to studying closed-loop performance of an equivalent {\em single-converter} system. The proposed architecture allows for the proportion in which the sources provide power to vary with time; thus overcoming limitations of our previous designs. Additionally, the proposed control framework is suitable to both centralized and decentralized implementations, i.e., the same control architecture can be employed for voltage regulation irrespective of the availability of common load-current (or power) measurement, without the need to modify controller parameters. The performance becomes quantifiably better with better communication of the demanded load to all the controllers at all the converters (in the centralized case); however guarantees viability when such communication is absent. Case studies comprising of battery, PV and generic sources are presented and demonstrate the enhanced performance of prescribed optimal controllers for voltage regulation and power sharing.

Kunal Garg, Mayank Baranwal

This study develops a fixed-time convergent saddle point dynamical system for solving min-max problems under a relaxation of standard convexity-concavity assumption. In particular, it is shown that by leveraging the dynamical systems viewpoint of an optimization algorithm, accelerated convergence to a saddle point can be obtained. Instead of requiring the objective function to be strongly-convex--strongly-concave (as necessitated for accelerated convergence of several saddle-point algorithms), uniform fixed-time convergence is guaranteed for functions satisfying only the two-sided Polyak-Łojasiewicz (PL) inequality. A large number of practical problems, including the robust least squares estimation, are known to satisfy the two-sided PL inequality. The proposed method achieves arbitrarily fast convergence compared to any other state-of-the-art method with linear or even super-linear convergence, as also corroborated in numerical case studies.

Kunal Garg, Mayank Baranwal

Distributed optimization has gained significant attention in recent years, primarily fueled by the availability of a large amount of data and privacy-preserving requirements. This paper presents a fixed-time convergent optimization algorithm for solving a potentially non-convex optimization problem using a first-order multi-agent system. Each agent in the network can access only its private objective function, while local information exchange is permitted between the neighbors. The proposed optimization algorithm combines a fixed-time convergent distributed parameter estimation scheme with a fixed-time distributed consensus scheme as its solution methodology. The results are presented under the assumption that the team objective function is strongly convex, as opposed to the common assumptions in the literature requiring each of the local objective functions to be strongly convex. The results extend to the class of possibly non-convex team objective functions satisfying only the Polyak-Łojasiewicz (PL) inequality. It is also shown that the proposed continuous-time scheme, when discretized using Euler's method, leads to consistent discretization, i.e., the fixed-time convergence behavior is preserved under discretization. Numerical examples comprising large-scale distributed linear regression and training of neural networks corroborate our theoretical analysis.

Kushal Chakrabarti, Mayank Baranwal

Adaptive gradient-descent optimizers are the standard choice for training neural network models. Despite their faster convergence than gradient-descent and remarkable performance in practice, the adaptive optimizers are not as well understood as vanilla gradient-descent. A reason is that the dynamic update of the learning rate that helps in faster convergence of these methods also makes their analysis intricate. Particularly, the simple gradient-descent method converges at a linear rate for a class of optimization problems, whereas the practically faster adaptive gradient methods lack such a theoretical guarantee. The Polyak-Łojasiewicz (PL) inequality is the weakest known class, for which linear convergence of gradient-descent and its momentum variants has been proved. Therefore, in this paper, we prove that AdaGrad and Adam, two well-known adaptive gradient methods, converge linearly when the cost function is smooth and satisfies the PL inequality. Our theoretical framework follows a simple and unified approach, applicable to both batch and stochastic gradients, which can potentially be utilized in analyzing linear convergence of other variants of Adam.

Mayank Baranwal, Kushal Chakrabarti

Optimizing problems in a distributed manner is critical for systems involving multiple agents with private data. Despite substantial interest, a unified method for analyzing the convergence rates of distributed optimization algorithms is lacking. This paper introduces an energy conservation approach for analyzing continuous-time dynamical systems in dilated coordinates. Instead of directly analyzing dynamics in the original coordinate system, we establish a conserved quantity, akin to physical energy, in the dilated coordinate system. Consequently, convergence rates can be explicitly expressed in terms of the inverse time-dilation factor. Leveraging this generalized approach, we formulate a novel second-order distributed accelerated gradient flow with a convergence rate of $O\left(1/t^{2-ε}\right)$ in time $t$ for $ε>0$. We then employ a semi second-order symplectic Euler discretization to derive a rate-matching algorithm with a convergence rate of $O\left(1/k^{2-ε}\right)$ in $k$ iterations. To the best of our knowledge, this represents the most favorable convergence rate for any distributed optimization algorithm designed for smooth convex optimization. Its accelerated convergence behavior is benchmarked against various state-of-the-art distributed optimization algorithms on practical, large-scale problems.

Kushal Chakrabarti, Mayank Baranwal

This paper considers solving distributed optimization problems in peer-to-peer multi-agent networks. The network is synchronous and connected. By using the proportional-integral (PI) control strategy, various algorithms with fixed stepsize have been developed. Two notable among them are the PI algorithm and the PI consensus algorithm. Although the PI algorithm has provable linear or exponential convergence without the standard requirement of (strong) convexity, a similar guarantee for the PI consensus algorithm is unavailable. In this paper, using Lyapunov theory, we guarantee exponential convergence of the PI consensus algorithm for global cost functions that satisfy the restricted secant inequality, with rate-matching discretization, without requiring convexity. To accelerate the PI consensus algorithm, we incorporate local pre-conditioning in the form of constant positive definite matrices and numerically validate its efficiency compared to the prominent distributed convex optimization algorithms. Unlike classical pre-conditioning, where only the gradients are multiplied by a pre-conditioner, the proposed pre-conditioning modifies both the gradients and the consensus terms, thereby controlling the effect of the communication graph on the algorithm.

Hardik Meisheri, Somjit Nath, Mayank Baranwal et al.

Most existing literature on supply chain and inventory management consider stochastic demand processes with zero or constant lead times. While it is true that in certain niche scenarios, uncertainty in lead times can be ignored, most real-world scenarios exhibit stochasticity in lead times. These random fluctuations can be caused due to uncertainty in arrival of raw materials at the manufacturer's end, delay in transportation, an unforeseen surge in demands, and switching to a different vendor, to name a few. Stochasticity in lead times is known to severely degrade the performance in an inventory management system, and it is only fair to abridge this gap in supply chain system through a principled approach. Motivated by the recently introduced delay-resolved deep Q-learning (DRDQN) algorithm, this paper develops a reinforcement learning based paradigm for handling uncertainty in lead times (\emph{action delay}). Through empirical evaluations, it is further shown that the inventory management with uncertain lead times is not only equivalent to that of delay in information sharing across multiple echelons (\emph{observation delay}), a model trained to handle one kind of delay is capable to handle delays of another kind without requiring to be retrained. Finally, we apply the delay-resolved framework to scenarios comprising of multiple products subjected to stochasticity in lead times, and elucidate how the delay-resolved framework negates the effect of any delay to achieve near-optimal performance.

Aritra Pal, Anandsingh Chauhan, Mayank Baranwal

Efficient task allocation among multiple robots is crucial for optimizing productivity in modern warehouses, particularly in response to the increasing demands of online order fulfillment. This paper addresses the real-time multi-robot task allocation (MRTA) problem in dynamic warehouse environments, where tasks emerge with specified start and end locations. The objective is to minimize both the total travel distance of robots and delays in task completion, while also considering practical constraints such as battery management and collision avoidance. We introduce MRTAgent, a dual-agent Reinforcement Learning (RL) framework inspired by self-play, designed to optimize task assignments and robot selection to ensure timely task execution. For safe navigation, a modified linear quadratic controller (LQR) approach is employed. To the best of our knowledge, MRTAgent is the first framework to address all critical aspects of practical MRTA problems while supporting continuous robot movements.

Durgesh Kalwar, Mayank Baranwal, Harshad Khadilkar

In today's data-sensitive landscape, distributed learning emerges as a vital tool, not only fortifying privacy measures but also streamlining computational operations. This becomes especially crucial within fully decentralized infrastructures where local processing is imperative due to the absence of centralized aggregation. Here, we introduce DYNAWEIGHT, a novel framework to information aggregation in multi-agent networks. DYNAWEIGHT offers substantial acceleration in decentralized learning with minimal additional communication and memory overhead. Unlike traditional static weight assignments, such as Metropolis weights, DYNAWEIGHT dynamically allocates weights to neighboring servers based on their relative losses on local datasets. Consequently, it favors servers possessing diverse information, particularly in scenarios of substantial data heterogeneity. Our experiments on various datasets MNIST, CIFAR10, and CIFAR100 incorporating various server counts and graph topologies, demonstrate notable enhancements in training speeds. Notably, DYNAWEIGHT functions as an aggregation scheme compatible with any underlying server-level optimization algorithm, underscoring its versatility and potential for widespread integration.

Manajit Das, Ajnabiul Hoque, Mayank Baranwal et al.

Prediction of complete step-by-step chemical reaction mechanisms (CRMs) remains a major challenge. Whereas the traditional approaches in CRM tasks rely on expert-driven experiments or costly quantum chemical computations, contemporary deep learning (DL) alternatives ignore key intermediates and mechanistic steps and often suffer from hallucinations. We present DeepMech, an interpretable graph-based DL framework employing atom- and bond-level attention, guided by generalized templates of mechanistic operations (TMOps), to generate CRMs. Trained on our curated ReactMech dataset (~30K CRMs with 100K atom-mapped and mass-balanced elementary steps), DeepMech achieves 98.98+/-0.12% accuracy in predicting elementary steps and 95.94+/-0.21% in complete CRM tasks, besides maintaining high fidelity even in out-of-distribution scenarios as well as in predicting side and/or byproducts. Extension to multistep CRMs relevant to prebiotic chemistry, demonstrates the ability of DeepMech in effectively reconstructing pathways from simple primordial substrates to complex biomolecules such as serine and aldopentose. Attention analysis identifies reactive atoms/bonds in line with chemical intuition, rendering our model interpretable and suitable for reaction design.

Aditya Kapoor, Kale-ab Tessera, Mayank Baranwal et al.

Credit assignmen, disentangling each agent's contribution to a shared reward, is a critical challenge in cooperative multi-agent reinforcement learning (MARL). To be effective, credit assignment methods must preserve the environment's optimal policy. Some recent approaches attempt this by enforcing return equivalence, where the sum of distributed rewards must equal the team reward. However, their guarantees are conditional on a learned model's regression accuracy, making them unreliable in practice. We introduce Temporal-Agent Reward Redistribution (TAR$^2$), an approach that decouples credit modeling from this constraint. A neural network learns unnormalized contribution scores, while a separate, deterministic normalization step enforces return equivalence by construction. We demonstrate that this method is equivalent to a valid Potential-Based Reward Shaping (PBRS), which guarantees the optimal policy is preserved regardless of model accuracy. Empirically, on challenging SMACLite and Google Research Football (GRF) benchmarks, TAR$^2$ accelerates learning and achieves higher final performance than strong baselines. These results establish our method as an effective solution for the agent-temporal credit assignment problem.

Aditya Kapoor, Sushant Swamy, Kale-ab Tessera et al.

In multi-agent environments, agents often struggle to learn optimal policies due to sparse or delayed global rewards, particularly in long-horizon tasks where it is challenging to evaluate actions at intermediate time steps. We introduce Temporal-Agent Reward Redistribution (TAR$^2$), a novel approach designed to address the agent-temporal credit assignment problem by redistributing sparse rewards both temporally and across agents. TAR$^2$ decomposes sparse global rewards into time-step-specific rewards and calculates agent-specific contributions to these rewards. We theoretically prove that TAR$^2$ is equivalent to potential-based reward shaping, ensuring that the optimal policy remains unchanged. Empirical results demonstrate that TAR$^2$ stabilizes and accelerates the learning process. Additionally, we show that when TAR$^2$ is integrated with single-agent reinforcement learning algorithms, it performs as well as or better than traditional multi-agent reinforcement learning methods.

Param Budhraja, Mayank Baranwal, Kunal Garg et al.

Accelerated gradient methods are the cornerstones of large-scale, data-driven optimization problems that arise naturally in machine learning and other fields concerning data analysis. We introduce a gradient-based optimization framework for achieving acceleration, based on the recently introduced notion of fixed-time stability of dynamical systems. The method presents itself as a generalization of simple gradient-based methods suitably scaled to achieve convergence to the optimizer in a fixed-time, independent of the initialization. We achieve this by first leveraging a continuous-time framework for designing fixed-time stable dynamical systems, and later providing a consistent discretization strategy, such that the equivalent discrete-time algorithm tracks the optimizer in a practically fixed number of iterations. We also provide a theoretical analysis of the convergence behavior of the proposed gradient flows, and their robustness to additive disturbances for a range of functions obeying strong convexity, strict convexity, and possibly nonconvexity but satisfying the Polyak-Łojasiewicz inequality. We also show that the regret bound on the convergence rate is constant by virtue of the fixed-time convergence. The hyperparameters have intuitive interpretations and can be tuned to fit the requirements on the desired convergence rates. We validate the accelerated convergence properties of the proposed schemes on a range of numerical examples against the state-of-the-art optimization algorithms. Our work provides insights on developing novel optimization algorithms via discretization of continuous-time flows.

Somjit Nath, Mayank Baranwal, Harshad Khadilkar

Several real-world scenarios, such as remote control and sensing, are comprised of action and observation delays. The presence of delays degrades the performance of reinforcement learning (RL) algorithms, often to such an extent that algorithms fail to learn anything substantial. This paper formally describes the notion of Markov Decision Processes (MDPs) with stochastic delays and shows that delayed MDPs can be transformed into equivalent standard MDPs (without delays) with significantly simplified cost structure. We employ this equivalence to derive a model-free Delay-Resolved RL framework and show that even a simple RL algorithm built upon this framework achieves near-optimal rewards in environments with stochastic delays in actions and observations. The delay-resolved deep Q-network (DRDQN) algorithm is bench-marked on a variety of environments comprising of multi-step and stochastic delays and results in better performance, both in terms of achieving near-optimal rewards and minimizing the computational overhead thereof, with respect to the currently established algorithms.

Abram Magner, Mayank Baranwal, Alfred O. Hero

Graph convolutional networks (GCNs) are a widely used method for graph representation learning. We investigate the power of GCNs, as a function of their number of layers, to distinguish between different random graph models on the basis of the embeddings of their sample graphs. In particular, the graph models that we consider arise from graphons, which are the most general possible parameterizations of infinite exchangeable graph models and which are the central objects of study in the theory of dense graph limits. We exhibit an infinite class of graphons that are well-separated in terms of cut distance and are indistinguishable by a GCN with nonlinear activation functions coming from a certain broad class if its depth is at least logarithmic in the size of the sample graph. These results theoretically match empirical observations of several prior works. Finally, we show a converse result that for pairs of graphons satisfying a degree profile separation property, a very simple GCN architecture suffices for distinguishability. To prove our results, we exploit a connection to random walks on graphs.

Abram Magner, Mayank Baranwal, Alfred O. Hero

Graph convolutional networks (GCNs) are a widely used method for graph representation learning. To elucidate the capabilities and limitations of GCNs, we investigate their power, as a function of their number of layers, to distinguish between different random graph models (corresponding to different class-conditional distributions in a classification problem) on the basis of the embeddings of their sample graphs. In particular, the graph models that we consider arise from graphons, which are the most general possible parameterizations of infinite exchangeable graph models and which are the central objects of study in the theory of dense graph limits. We give a precise characterization of the set of pairs of graphons that are indistinguishable by a GCN with nonlinear activation functions coming from a certain broad class if its depth is at least logarithmic in the size of the sample graph. This characterization is in terms of a degree profile closeness property. Outside this class, a very simple GCN architecture suffices for distinguishability. We then exhibit a concrete, infinite class of graphons arising from stochastic block models that are well-separated in terms of cut distance and are indistinguishable by a GCN. These results theoretically match empirical observations of several prior works. To prove our results, we exploit a connection to random walks on graphs. Finally, we give empirical results on synthetic and real graph classification datasets, indicating that indistinguishable graph distributions arise in practice.

Amber Srivastava, Mayank Baranwal, Srinivasa Salapaka

Typically clustering algorithms provide clustering solutions with prespecified number of clusters. The lack of a priori knowledge on the true number of underlying clusters in the dataset makes it important to have a metric to compare the clustering solutions with different number of clusters. This article quantifies a notion of persistence of clustering solutions that enables comparing solutions with different number of clusters. The persistence relates to the range of data-resolution scales over which a clustering solution persists; it is quantified in terms of the maximum over two-norms of all the associated cluster-covariance matrices. Thus we associate a persistence value for each element in a set of clustering solutions with different number of clusters. We show that the datasets where natural clusters are a priori known, the clustering solutions that identify the natural clusters are most persistent - in this way, this notion can be used to identify solutions with true number of clusters. Detailed experiments on a variety of standard and synthetic datasets demonstrate that the proposed persistence-based indicator outperforms the existing approaches, such as, gap-statistic method, $X$-means, $G$-means, $PG$-means, dip-means algorithms and information-theoretic method, in accurately identifying the clustering solutions with true number of clusters. Interestingly, our method can be explained in terms of the phase-transition phenomenon in the deterministic annealing algorithm, where the number of distinct cluster centers changes (bifurcates) with respect to an annealing parameter.

Mayank Baranwal, Brian Roehl, Srinivasa M. Salapaka

This paper presents a novel and efficient heuristic framework for approximating the solutions to the multiple traveling salesmen problem (m-TSP) and other variants on the TSP. The approach adopted in this paper is an extension of the Maximum-Entropy-Principle (MEP) and the Deterministic Annealing (DA) algorithm. The framework is presented as a general tool that can be suitably adapted to a number of variants on the basic TSP. Additionally, unlike most other heuristics for the TSP, the framework presented in this paper is independent of the edges defined between any two pairs of nodes. This makes the algorithm particularly suited for variants such as the close-enough traveling salesman problem (CETSP) which are challenging due to added computational complexity. The examples presented in this paper illustrate the effectiveness of this new framework for use in TSP and many variants thereof.