arXiv subjects

Anubhav Kumar

Publications and source records attributed to Anubhav Kumar.

4 recordsLinked to original sources

arXiv2026

Joint Causal Structure and Cluster Discovery Using Variational Inference

Causal discovery aims to understand the relationships between individual random variables. In many applications, such as brain imaging and climate modeling, it is more meaningful to consider interactions among groups of variables. Existing methods assume that knowledge of such groups or clusters is explicitly available when modeling interactions. However, in practice, these clusters as well as the causal relationships among them, are latent. In this paper, we present a novel approach based on variational inference to simultaneously infer both the latent clusters and causal structures. We learn an approximate posterior over clusters and graph-structure by considering variational distributions based on categorical and Bernoulli models respectively. We derive variational lower bounds and estimation techniques to learn variational and model parameters. The effectiveness of our proposed methods for cluster and causal discovery are demonstrated on both synthetic and real data sets.

cs.LG↗

arXiv2026

VISTA: Visualization of Token Attribution via Efficient Analysis

Understanding how Large Language Models (LLMs) process information from prompts remains a significant challenge. To shed light on this "black box," attention visualization techniques have been developed to capture neuron-level perceptions and interpret how models focus on different parts of input data. However, many existing techniques are tailored to specific model architectures, particularly within the Transformer family, and often require backpropagation, resulting in nearly double the GPU memory usage and increased computational cost. A lightweight, model-agnostic approach for attention visualization remains lacking. In this paper, we introduce a model-agnostic token importance visualization technique to better understand how generative AI systems perceive and prioritize information from input text, without incurring additional computational cost. Our method leverages perturbation-based strategies combined with a three-matrix analytical framework to generate relevance maps that illustrate token-level contributions to model predictions. The framework comprises: (1) the Angular Deviation Matrix, which captures shifts in semantic direction; (2) the Magnitude Deviation Matrix, which measures changes in semantic intensity; and (3) the Dimensional Importance Matrix, which evaluates contributions across individual vector dimensions. By systematically removing each token and measuring the resulting impact across these three complementary dimensions, we derive a composite importance score that provides a nuanced and mathematically grounded measure of token significance. To support reproducibility and foster wider adoption, we provide open-source implementations of all proposed and utilized explainability techniques, with code and resources publicly available at https://github.com/Infosys/Infosys-Responsible-AI-Toolkit

cs.AI↗

arXiv2021

MatES: Web-based Forward Chaining Expert System for Maternal Care

The solution to prevent maternal complications are known and preventable by trained health professionals. But in countries like Ethiopia where the patient to physician ratio is 1 doctor to 1000 patients, maternal mortality and morbidity rate is high. To fill the gap of highly trained health professionals, Ethiopia introduced health extension programs. Task shifting to health extension workers (HEWs) contributed in decreasing mortality and morbidity rate in Ethiopia. Knowledge-gap has been one of the major challenges to HEWs. The reasons are trainings are not given in regular manner, there is no midwife, gynecologists or doctors around for consultation, and all guidelines are paper-based which are easily exposed to damage. In this paper, we describe the design and implementation of a web-based expert system for maternal care. We only targeted the major 10 diseases and complication of maternal health issues seen in Sub-Saharan Africa. The expert system can be accessed through the use of web browsers from computers as well as smart phones. Forward chaining rule-based expert system is used in order to give suggestions and create a new knowledge from the knowledge-base. This expert system can be used to train HEWs in the field of maternal health. Keywords: expert system, maternal care, forward-chaining, rule-based expert system, PHLIPS

cs.AI↗

arXiv2020

Short-term Wind Speed Forecasting based on LSSVM Optimized by Elitist QPSO

Nowadays, wind power is considered as one of the most widely used renewable energy applications due to its efficient energy use and low pollution. In order to maintain high integration of wind power into the electricity market, efficient models for wind speed forecasting are in high demand. The non-stationary and nonlinear characteristics of wind speed, however, makes the task of wind speed forecasting challenging. LSSVM has proven to be a good forecasting algorithm mainly for time-series applications such as wind data. To boost the learning performance and generalization capability of the algorithm, LSSVM has two hyperparameters, known as the regularization and kernel parameters, that require careful tuning. In this paper, a modified QPSO algorithm is proposed that uses the principle of transposon operators to breed the personal best and global best particles of QPSO and improve global searching capabilities. The optimization algorithm is then used to generate optimum values for the LSSVM hyperparameters. Finally, the performance of the proposed model is compared with previously known PSO and QPSO optimized LSSVM models. Empirical results show that the proposed model displayed improved performance compared to the competitive methods.

eess.SP↗