arXiv subjects

Mayank Baranwal

Publications and source records attributed to Mayank Baranwal.

35 records · Page 2Linked to original sources

arXiv2022

Accelerating Distributed Optimization via Fixed-time Convergent Flows: Extensions to Non-convex Functions and Consistent Discretization

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.

eess.SY↗

arXiv2022

Breaking the Convergence Barrier: Optimization via Fixed-Time Convergent Flows

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.

math.OC↗

arXiv2022

A Learning Based Framework for Handling Uncertain Lead Times in Multi-Product Inventory Management

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.

cs.LG↗

arXiv2021

Revisiting State Augmentation methods for Reinforcement Learning with Stochastic Delays

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.

cs.LG↗

arXiv2020

Robust Distributed Fixed-Time Economic Dispatch under Time-Varying Topology

The centralized power generation infrastructure that defines the North American electric grid is slowly moving to the distributed architecture due to the explosion in use of renewable generation and distributed energy resources (DERs), such as residential solar, wind turbines and battery storage. Furthermore, variable pricing policies and profusion of flexible loads entail frequent and severe changes in power outputs required from the individual generation units, requiring fast availability of power allocation. To this end, a fixed-time convergent, fully distributed economic dispatch algorithm for scheduling optimal power generation among a set of DERs is proposed. The proposed algorithm incorporates both load balance and generation capacity constraints.

math.OC↗

arXiv2020

On sparse identification of complex dynamical systems: A study on discovering influential reactions in chemical reaction networks

A wide variety of real life complex networks are prohibitively large for modeling, analysis and control. Understanding the structure and dynamics of such networks entails creating a smaller representative network that preserves its relevant topological and dynamical properties. While modern machine learning methods have enabled identification of governing laws for complex dynamical systems, their inability to produce white-box models with sufficient physical interpretation renders such methods undesirable to domain experts. In this paper, we introduce a hybrid black-box, white-box approach for the sparse identification of the governing laws for complex, highly coupled dynamical systems with particular emphasis on finding the influential reactions in chemical reaction networks for combustion applications, using a data-driven sparse-learning technique. The proposed approach identifies a set of influential reactions using species concentrations and reaction rates,with minimal computational cost without requiring additional data or simulations. The new approach is applied to analyze the combustion chemistry of H2 and C3H8 in a constant-volume homogeneous reactor. The influential reactions determined by the sparse-learning method are consistent with the current kinetics knowledge of chemical mechanisms. Additionally, we show that a reduced version of the parent mechanism can be generated as a combination of the significantly reduced influential reactions identified at different times and conditions and that for both H2 and C3H8 fuel, the reduced mechanisms perform closely to the parent mechanisms as a function of the ignition delay time over a wide range of conditions. Our results demonstrate the potential of the sparse-learning approach as an effective and efficient tool for dynamical system analysis and reduction. The uniqueness of this approach as applied to combustion systems lies in the ability to identify influential reactions in specified conditions and times during the evolution of the combustion process. This ability is of great interest to understand chemical reaction systems.

physics.chem-ph↗

arXiv2020

CAPPA: Continuous-time Accelerated Proximal Point Algorithm for Sparse Recovery

This paper develops a novel Continuous-time Accelerated Proximal Point Algorithm (CAPPA) for $\ell_1$-minimization problems with provable fixed-time convergence guarantees. The problem of $\ell_1$-minimization appears in several contexts, such as sparse recovery (SR) in Compressed Sensing (CS) theory, and sparse linear and logistic regressions in machine learning to name a few. Most existing algorithms for solving $\ell_1$-minimization problems are discrete-time, inefficient and require exhaustive computer-guided iterations. CAPPA alleviates this problem on two fronts: (a) it encompasses a continuous-time algorithm that can be implemented using analog circuits; (b) it betters LCA and finite-time LCA (recently developed continuous-time dynamical systems for solving SR problems) by exhibiting provable fixed-time convergence to optimal solution. Consequently, CAPPA is better suited for fast and efficient handling of SR problems. Simulation studies are presented that corroborate computational advantages of CAPPA.

math.OC↗

arXiv2020

Fundamental Limits of Deep Graph Convolutional Networks

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.

stat.ML↗

arXiv2020

The Power of Graph Convolutional Networks to Distinguish Random Graph Models: Short Version

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.

stat.ML↗

arXiv2019

Multiway k-Cut in Static and Dynamic Graphs: A Maximum Entropy Principle Approach

This work presents a maximum entropy principle based algorithm for solving minimum multiway $k$-cut problem defined over static and dynamic {\em digraphs}. A multiway $k$-cut problem requires partitioning the set of nodes in a graph into $k$ subsets, such that each subset contains one prespecified node, and the corresponding total cut weight is minimized. These problems arise in many applications and are computationally complex (NP-hard). In the static setting this article presents an approach that uses a relaxed multiway $k$-cut cost function; we show that the resulting algorithm converges to a local minimum. This iterative algorithm is designed to avoid poor local minima with its run-time complexity as $\sim O(kIN^3)$, where $N$ is the number of vertices and $I$ is the number of iterations. In the dynamic setting, the edge-weight matrix has an associated dynamics with some of the edges in the graph capable of being influenced by an external input. The objective is to design the dynamics of the controllable edges so that multiway $k$-cut value remains small (or decreases) as the graph evolves under the dynamics. Also it is required to determine the time-varying partition that defines the minimum multiway $k$-cut value. Our approach is to choose a relaxation of multiway $k$-cut value, derived using maximum entropy principle, and treat it as a control Lyapunov function to design control laws that affect the weight dynamics. Simulations on practical examples of interactive foreground-background segmentation, minimum multiway $k$-cut optimization for non-planar graphs and dynamically evolving graphs that demonstrate the efficacy of the algorithm, are presented.

math.OC↗

arXiv2018

On the Persistence of Clustering Solutions and True Number of Clusters in a Dataset

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.

cs.LG↗

arXiv2017

Robust Distributed Control of DC Microgrids with Time-Varying Power Sharing

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.

math.OC↗

arXiv2016

Clustering with Capacity and Size Constraints: A Deterministic Approach

This paper discusses a deterministic clustering approach to capacitated resource allocation problems. In particular, the Deterministic Annealing (DA) algorithm from the data-compression literature, which bears a distinct analogy to the phase transformation under annealing process in statistical physics, is adapted to address problems pertaining to clustering with several forms of size constraints. These constraints are addressed through appropriate modifications of the basic DA formulation by judiciously adjusting the free-energy function in the DA algorithm. At a given value of the annealing parameter, the iterations of the DA algorithm are of the form of a Descent Method, which motivate scaling principles for faster convergence.

math.OC↗

arXiv2016

Robust Control Framework for Time-Varying Power-Sharing among Distributed Energy Resources

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.

math.OC↗

arXiv2016

A Deterministic Annealing Approach to the Multiple Traveling Salesmen and Related Problems

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.

math.OC↗

arXiv2016

Robust Decentralized Voltage Control of DC-DC Converters with Applications to Power Sharing and Ripple Sharing

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.

math.OC↗

arXiv2016

Vehicle Routing Problem with Time Windows: A Deterministic Annealing approach

The Vehicle Routing Problem with Time-Windows (VRPTW) is an important problem in allocating resources on networks in time and space. We present in this paper a Deterministic Annealing (DA)-based approach to solving the VRPTW with its aspects of routing and scheduling, as well as to model additional constraints of heterogeneous vehicles and shipments. This is the first time, to our knowledge, that a DA approach has been used for problems in the class of the VRPTW. We describe how the DA approach can be adapted to generate an effective heuristic approach to the VRPTW. Our DA approach is also designed to not get trapped in local minima, and demonstrates less sensitivity to initial solutions. The algorithm trades off routing and scheduling in an n-dimensional space using a tunable parameter that allows us to generate qualitatively good solutions. These solutions differ in the degree of intersection of the routes, making the case for transfer points where shipments can be exchanged. Simulation results on randomly generated instances show that the constraints are respected and demonstrate near optimal results (when verifiable) in terms of schedules and tour length of individual tours in each solution.

math.OC↗