arXiv subjects

Neelesh S. Upadhye

Publications and source records attributed to Neelesh S. Upadhye.

4 recordsLinked to original sources

arXiv2025

Advances and Challenges in Semantic Textual Similarity: A Comprehensive Survey

Semantic Textual Similarity (STS) research has expanded rapidly since 2021, driven by advances in transformer architectures, contrastive learning, and domain-specific techniques. This survey reviews progress across six key areas: transformer-based models, contrastive learning, domain-focused solutions, multi-modal methods, graph-based approaches, and knowledge-enhanced techniques. Recent transformer models such as FarSSiBERT and DeBERTa-v3 have achieved remarkable accuracy, while contrastive methods like AspectCSE have established new benchmarks. Domain-adapted models, including CXR-BERT for medical texts and Financial-STS for finance, demonstrate how STS can be effectively customized for specialized fields. Moreover, multi-modal, graph-based, and knowledge-integrated models further enhance semantic understanding and representation. By organizing and analyzing these developments, the survey provides valuable insights into current methods, practical applications, and remaining challenges. It aims to guide researchers and practitioners alike in navigating rapid advancements, highlighting emerging trends and future opportunities in the evolving field of STS.

cs.CL↗

arXiv2025

Adaptive Efficiency Optimization in SDLC: An MILP Approach for Balanced and Cost-Effective Resource Allocation

The efficient allocation of human resources is a critical concern in software development and other industries. This paper introduces a rigorous mathematical methodology for task assignment, employing Mixed Integer Linear Programming (MILP) to ensure both balanced workloads and cost minimization. The proposed model systematically integrates individual employee efficiency, task complexity, and performance metrics to reflect real organizational dynamics. The formulation is guided by two principal objectives: firstly, to achieve equitable work load distribution commensurate with employee efficiency, and secondly, to minimize overall project costs by accounting for task difficulty and individual proficiency. Furthermore, the approach incorporates adaptive updates to efficiency parameters based on observed performance, thereby enhancing its practical applicability. Empirical evaluation using simulated datasets demonstrates the superiority of the proposed method over conventional assignment strategies in terms of both workload fairness and cost reduction. The findings underscore the potential of this MILP based framework as a robust, scalable, and adaptable solution for contemporary human resource allocation challenges in project management contexts.

math.OC↗

arXiv2020

Bayesian Filtering for Multi-period Mean-Variance Portfolio Selection

For a long investment time horizon, it is preferable to rebalance the portfolio weights at intermediate times. This necessitates a multi-period market model in which portfolio optimization is usually done through dynamic programming. However, this assumes a known distribution for the parameters of the financial time series. We consider the situation where this distribution is unknown and needs to be estimated from the data that is arriving dynamically. We applied Bayesian filtering through dynamic linear models to sequentially update the parameters. We considered uncertain investment lifetime to make the model more adaptive to the market conditions. These updated parameters are put into the dynamic mean-variance problem to arrive at optimal efficient portfolios. Extensive simulations are conducted to study the effect of varying underlying parameters and investment horizon on the performance of the method. An implementation of this model to the S&P500 illustrates that the Bayesian updating is strongly favored by the data and that it is practically implementable.

q-fin.PM↗

arXiv2020

Approximations Related to the Sums of $m$-dependent Random Variables

In this paper, we consider the sums of non-negative integer valued $m$-dependent random variables, and its approximation to the power series distribution. We first discuss some relevant results for power series distribution such as Stein operator, uniform and non-uniform bounds on the solution of Stein equation, and etc. Using Stein's method, we obtain the error bounds for the approximation problem considered. As special cases, we discuss two applications, namely, $2$-runs and $(k_1,k_2)$-runs and compare the bound with the existing bounds.

math.PR↗