SMSumanta Mukherjee

Sumanta Mukherjee

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Sumanta Mukherjee has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Percolation in a three-dimensional non-symmetric multi-color loop model

    by Soumya Kanti Ganguly, Sumanta Mukherjee, Chandan Dasgupta

    We conducted Monte Carlo simulations to analyze the percolation transition of a non-symmetric loop model on a regular three-dimensional lattice. We calculated the critical exponents for the percolation transition of this model. The percolation transition occurs at a temperature that is close to, but not exactly the thermal critical temperature. Our finite-size study on this model yielded a correlation length exponent that agrees with that of the three-dimensional XY model with an error margin of six per cent.

  • Percolation in a three-dimensional nonsymmetric multicolor loop model

    by Soumya Kanti Ganguly, Sumanta Mukherjee, Chandan Dasgupta

    We conduct Monte Carlo simulations to analyze the percolation transition of a nonsymmetric loop model on a regular three-dimensional lattice. We calculate the critical exponents for the percolation transition of this model. The percolation transition occurs at a temperature that is close to, but not exactly, the thermal critical temperature. Our finite-size study on this model yields a correlation length exponent that agrees with that of the three-dimensional XY model with an error margin of 6%.


  • Thermodynamics of multicolored loop models in three dimensions

    by Soumya Kanti Ganguly, Sumanta Mukherjee, Chandan Dasgupta

    We study order-disorder transitions in three-dimensional multicolored loop models using Monte Carlo simulations. We show that the nature of the transition is intimately related to the nature of the loops. The symmetric loops undergo a first-order phase transition, while the nonsymmetric loops show a second-order transition. The critical exponents for the nonsymmetric loops are calculated. In three dimensions, the regular loop model with no interactions is dual to the XY model. We argue that, due to interactions among the colors, the specific-heat exponent is found to be different from that of the regular loop model. The continuous nature of the transition is altered to a discontinuous one due to the strong intercolor interactions.


  • Open Access

    AI Explainability 360 Toolkit for Time-Series and Industrial Use Cases

    by Giridhar Ganapavarapu, Sumanta Mukherjee, Natalia Martinez Gil, Kanthi Sarpatwar, Amaresh Rajasekharan, Amit Dhurandhar, Vijay Arya, Roman Vaculin

    With the growing adoption of AI, trust and explainability have become critical which has attracted a lot of research attention over the past decade and has led to the development of many popular AI explainability libraries such as AIX360, Alibi, OmniXAI, etc. Despite that, applying explainability techniques in practice often poses challenges such as lack of consistency between explainers, semantically incorrect explanations, or scalability. Furthermore, one of the key modalities that has been less explored, both from the algorithmic and practice point of view, is time-series. Several application domains involve time-series including Industry 4.0, asset monitoring, supply chain or finance to name a few. The AIX360 library (https://github.com/Trusted-AI/AIX360) has been incubated by the Linux Foundation AI & Data open-source projects and it has gained significant popularity: its public GitHub repository has over 1.3K stars and has been broadly adopted in the academic and applied settings. Motivated by industrial applications, large scale client projects and deployments in software products in the areas of IoT, asset management or supply chain, the AIX360 library has been recently expanded significantly to address the above challenges. AIX360 now includes new techniques including support for time-series modality introducing time series based explainers such as TS-LIME, TS Saliency explainer, TS-ICE and TS-SHAP. It also introduces improvements in generating model agnostic, consistent, diverse, and scalable explanations, and new algorithms for tabular data. In this hands-on tutorial, we provide an overview of the library with the focus on the latest additions, time series explainers and use cases such as forecasting, time series anomaly detection or classification, and hands-on demonstrations based on industrial use-cases selected to demonstrate practical challenges and how they are addressed. The audience will be able to evaluate different types of explanations with a focus on practical aspects motivated by real deployments.


  • Open Access

    Hierarchical Proxy Modeling for Improved HPO in Time Series Forecasting

    by Arindam Jati, Vijay Ekambaram, Shaonli Pal, Brian Quanz, Wesley M. Gifford, Pavithra Harsha, Stuart Siegel, Sumanta Mukherjee, Chandra Narayanaswami

    Selecting the right set of hyperparameters is crucial in time series forecasting. The classical temporal cross-validation framework for hyperparameter optimization (HPO) often leads to poor test performance because of a possible mismatch between validation and test periods. To address this test-validation mismatch, we propose a novel technique, H-Pro to drive HPO via test proxies by exploiting data hierarchies often associated with time series datasets. Since higher-level aggregated time series often show less irregularity and better predictability as compared to the lowest-level time series which can be sparse and intermittent, we optimize the hyperparameters of the lowest-level base-forecaster by leveraging the proxy forecasts for the test period generated from the forecasters at higher levels. H-Pro can be applied on any off-the-shelf machine learning model to perform HPO. We validate the efficacy of our technique with extensive empirical evaluation on five publicly available hierarchical forecasting datasets. Our approach outperforms existing state-of-the-art methods in Tourism, Wiki, and Traffic datasets, and achieves competitive result in Tourism-L dataset, without any model-specific enhancements. Moreover, our method outperforms the winning method of the M5 forecast accuracy competition.