Searcharxiv⌕ Search

arXiv subjects

Pranav Gupta

Publications and source records attributed to Pranav Gupta.

At least 19 recordsLinked to original sources

Feedback-Linearised Trajectory Tracking via Model-Informed Robust Geometric DDPC

Data-driven predictive control (DDPC) predicts system responses from recorded trajectories, but nonlinear dynamics can limit the accuracy of fixed linear predictors. This paper studies geometric robust DDPC for trajectory tracking of a fully actuated manipulator using model-based feedback linearisation. A mechanical model maps virtual acceleration commands into joint torques, while recorded data capture residual dynamics arising from imperfect model parameters. The controller minimises worst-case prediction error over an open Grassmannian ball centred at the fitted trajectory subspace. Simulations on a planar 2R manipulator under gravity compare the proposed method with double-integrator model predictive control (MPC) and direct regularised data-enabled predictive control (DeePC). Results show improved tracking over double-integrator MPC despite increased torque effort, while performance relative to DeePC depends on the reference trajectory.

cs.RO↗

Certified Algorithms for Gaussian Location Mixture NPMLEs via Discretized Gradient Flows

We study the computation of approximate nonparametric maximum likelihood estimators (NPMLEs) for Gaussian location mixtures in arbitrary dimension $d\ge 1$ via the Fisher-Rao gradient flow. We provide a certified algorithm based on an entropic proximal discretization of the flow which, given a sufficiently small $\varepsilon > 0$, returns an absolutely continuous mixing measure $\tildeμ$ admitting an exact finite-dimensional representation and satisfying $\hat L_n-L_n(f_{\tildeμ})\le\varepsilon$. For almost every dataset $X_1,\cdots, X_n \in \mathbb{R}^d$ satisfying $n>2(d+1)(m+1)^2$, where $m$ is the number of support points of the NPMLE, the algorithm requires $O(n\varepsilon^{-1}\log^{d+2}(1/\varepsilon))$ time. En route, we also establish results on the well-posedness and convergence properties of the continuous-time Fisher--Rao flow. In particular, initializing the flow at the uniform probability measure on a ball containing the convex hull of the observations, we show that $\hat L_n-L_n(f_{μ_t})=O(\log t/t)$. We also establish that, for almost every dataset satisfying the same condition on $n$ as above, the set of global maxima of the optimal score is the same as the support of the NPMLE, and the Hessian of the optimal score is nondegenerate at these points, extending a result of (Polyanskiy-Sellke, 2025) to higher dimensions.

math.ST↗

Determinantal sampling on general spaces: fast approximation via diffusion geometry

Determinantal point processes (DPPs) have recently emerged as a kernel-based alternative to standard independent sampling for constructing efficient minibatches, coresets, and other compact representations of large-scale datasets. One of the key strengths of DPP based samplers is that they can be deployed over very general spaces, in contrast to more classical sampling methods beyond i.i.d. which tend to be tailored to particular well-structured settings, principally Euclidean spaces. In this work, we establish explicit rate guarantees for determinantal sampling in spaces that extend far beyond known Euclidean setups, focussing on spectral kernels obtained from eigenspaces of naturally associated Markov diffusion operators, including in particular the Laplacian on manifolds and nearest-neighbour type graphs on data point clouds and the discrete Schrodinger operator on large scale networks. This covers, in particular, the settings of Riemannian manifolds and discrete networks, as well as the problem of batch sampling from discrete datasets. Overall, our approach achieves guarantees comparable to $\big(\text{sample size}\big)^{-\frac{1}{2}-\frac{1}{2d_{\text{int}}}}$ , which match with the rates for well-known determinantal samplers on Euclidean spaces of comparable dimension. In terms of techniques, we connect to the celebrated Weyl's Law for spectra on general spaces, and leverage tools from the theory of Markov diffusion operators and Dirichlet forms, which could be of independent interest in this area. Our approach is applicable to a very wide plethora of ambient spaces beyond Euclidean as soon as these ingredients are available, including e.g. fractals, leading to guarantees that will be governed by the intrinsic structural constants of such spaces.

stat.ML↗

Causal inference and model explainability analysis of a real world sales dataset

Most major retailers today have multiple divisions focused on various aspects, such as marketing, supply chain, online customer experience, store customer experience, employee productivity, and vendor fulfillment. They also regularly collect data corresponding to all these aspects as dashboards and weekly/monthly/quarterly reports. Although several machine learning and statistical techniques have been in place to analyze and predict key metrics, such models typically lack interpretability. Moreover, such techniques also do not allow the validation or discovery of causal links. In this paper, we aim to provide a recipe for applying model interpretability and causal inference for deriving sales insights. In this paper, we review the existing literature on causal inference and interpretability in the context of problems in e-commerce and retail, and apply them to a real-world dataset. We find that an inherently explainable model has a lower variance of SHAP values, and show that including multiple confounders through a double machine learning approach allows us to get the correct sign of causal effect.

cs.LG↗

QC-Stark: A Multi-Task Benchmark Revealing Capability Dissociations in LLMs Evaluated on Quantum Computing Tasks

We introduce QC-Stark, a benchmark for evaluating large language models (LLMs) on 11 quantum computing (QC) tasks, spanning circuit construction, debugging, compilation, error correction, and simulation. Across 2,750 evaluations (10 models $\times$ 11 tasks x 5 difficulty levels x 5 seeds), we find that overall rankings mask substantial per-task variation. The Spearman correlation between overall and per-task rankings is statistically insignificant for 4 out of the 11 tasks included in this benchmark. A 2-parameter Item Response Theory (IRT) model validates measurement quality, and prompt sensitivity analysis confirms ranking robustness across prompt conditions. All tasks are auto-verifiable via execution, thus not requiring any manual evaluation. We make the code and data publicly available on Huggingface.

quant-ph↗

Explicit Second-Order Bounds on the Domain of Validity for Lyapunov-Schmidt Reduction

Lyapunov-Schmidt reduction is a widely used dimensionality reduction technique for bifurcation analysis in high-dimensional systems. While classical formulations guarantee the local existence of reduced-order equations, they typically lack explicit quantitative estimates on the size of the neighbourhoods in which these representations faithfully capture the full bifurcation structure. In recent work, we have addressed this limitation by deriving bounds on the domain of validity of this reduction using first-order conditions on the vector field together with a quantitative result for the implicit function theorem. In this article we explore beyond, and adopt second-order conditions that incorporate the Hessians of the vector field to develop these bounds, and obtain a new set of results. We then investigate the applicability of these newly derived bounds to Hopfield-like networked dynamical systems, evaluate these bounds for pitchfork bifurcations on connected regular graphs, and finally examine the relationship between the two certified domains for this class of systems.

eess.SY↗

Exploring Automated Vulnerability Identification in JavaScript Code Using Large Language Models

JavaScript powers approximately 98.8% of all websites, making vulnerabilities in its code a significant security risk, yet existing detection approaches such as Static Application Security Testing (SAST) tools often fail to identify many real-world vulnerabilities when applied to isolated code snippets. This paper presents an empirical study of Large Language Model (LLM)-based vulnerability identification for JavaScript programs, evaluating three LLM families (Gemini 1.5 Flash, GPT-4o Mini, DeepSeek-R1-Distill-Llama-8B) across multiple prompting strategies (zero-shot, chain-of-thought, few-shot) and fine-tuning approaches on a dataset of 1,125 JavaScript code snippets spanning five Common Weakness Enumeration (CWE) categories: Injection (CWE-74), OS Command Injection (CWE-78), Cross-Site Scripting (CWE-79), SQL Injection (CWE-89), and Uncontrolled Resource Consumption (CWE-400). Our experiments show that LLMs substantially outperform traditional SAST tools on snippet-level vulnerability identification, with a fine-tuned Gemini 1.5 Flash model achieving 60% detection accuracy compared to near-zero performance from rule-based analyzers. We find that fine-tuning improves accuracy from 29% to 60%, Chain-of-Thought prompting benefits reasoning-capable models such as GPT-4o Mini, few-shot prompting is effective for polymorphic vulnerabilities such as Cross-Site Scripting, and performance varies across vulnerability categories, reaching up to 84% accuracy for structured vulnerabilities such as SQL Injection. These results indicate that LLMs provide a practical approach for automated vulnerability identification in JavaScript code, particularly when combined with task-aligned supervision, though they should complement rather than replace existing security analysis workflows due to limited recall and uneven performance across vulnerability types.

cs.CR↗

Two-player Alternate Uses Test: A Controlled Testbed for Interactive Human-AI and Human-Human Co-Creation

Controlled research on AI ideation typically compares independent agents, while field studies of human-AI collaboration sacrifice experimental control. We introduce a controlled, two-player extension of the Alternate Uses Test (AUT) that enables comparison of human-human and human-AI co-creation under matched interactive conditions, alongside calibrated non-interactive baselines. The platform supports decomposition of performance into three typically confounded factors: participant traits, partner perceptions, and content dynamics. An in-person pilot (N = 62) demonstrates its utility. Under matched time limits, originality with a GPT-4 partner is statistically equivalent to that with a human partner. Approach motivation (BAS Drive) moderates whether interactive partnership benefits originality, and self-reported cognitive outsourcing predicts lower originality specifically in human-human dyads. Prior exposure to highly creative ideas improves later performance, suggesting a "seeding" intervention. We release the platform, code, and dataset as a shared testbed for controlled studies of human-AI co-creation.

cs.HC↗

State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives

Determinantal point processes (DPPs) have emerged as a kernelized alternative to vanilla independent sampling for generating efficient minibatches, coresets and other parsimonious representations of large-scale datasets. While theoretical foundations and promising empirical performance have been demonstrated, there are two challenges for current proposals for DPP-based coresets or minibatches. The first is the need for families of DPPs with certain key variance reduction properties, usually constructed in a continuous setting, of which there are few known examples. The second is the need for an ad-hoc construction of a discrete DPP defined on a given dataset, that inherits such variance reduction. In this work, we contribute to the programme of establishing DPPs as a subsampling toolbox for ML by advancing on these two fronts. First, we propose new DPPs on the Euclidean space based on wavelets, with provably better accuracy guarantees than the best known rates. Second, we introduce a general method to convert such continuous DPPs, which are more amenable to proving analytical statements, into discrete kernels, which are pertinent for subsampling tasks such as minibatch and coreset constructions. This conversion mechanism simultaneously preserves the desired variance decay and reveals a low-rank decomposition of the discrete kernel, which makes sampling the corresponding DPP computationally inexpensive. En route, we enlarge the class of ML tasks amenable to improvements via DPP-based minibatches and coresets to include objective functions with arbitrarily low regularity, and rate guarantees that explicitly adapt to this regularity.

stat.ML↗

Bounds of Validity for Bifurcations of Equilibria in a Class of Networked Dynamical Systems

Local bifurcation analysis plays a central role in understanding qualitative transitions in networked nonlinear dynamical systems, including dynamic neural network and opinion dynamics models. In this article we establish explicit bounds of validity for the classification of bifurcation diagrams in two classes of continuous-time networked dynamical systems, analogous in structure to the Hopfield and the Firing Rate dynamic neural network models. Our approach leverages recent advances in computing the bounds for the validity of Lyapunov-Schmidt reduction, a reduction method widely employed in nonlinear systems analysis. Using these bounds we rigorously characterize neighbourhoods around bifurcation points where predictions from reduced-order bifurcation equations remain reliable. We further demonstrate how these bounds can be applied to an illustrative family of nonlinear opinion dynamics on k-regular graphs, which emerges as a special case of the general framework. These results provide new analytical tools for quantifying the robustness of bifurcation phenomena in dynamics over networked systems and highlight the interplay between network structure and nonlinear dynamical behaviour.

eess.SY↗

NLP for Social Good: A Survey and Outlook of Challenges, Opportunities, and Responsible Deployment

Natural language processing (NLP) now shapes many aspects of our world, yet its potential for positive social impact is underexplored. This paper surveys work in ``NLP for Social Good" (NLP4SG) across nine domains relevant to global development and risk agendas, summarizing principal tasks and challenges. We analyze ACL Anthology trends, finding that inclusion and AI harms attract the most research, while domains such as poverty, peacebuilding, and environmental protection remain underexplored. Guided by our review, we outline opportunities for responsible and equitable NLP and conclude with a call for cross-disciplinary partnerships and human-centered approaches to ensure that future NLP technologies advance the public good.

cs.CL↗

OpenStaxQA: A multilingual dataset based on open-source college textbooks

We present OpenStaxQA, an evaluation benchmark specific to college-level educational applications based on 43 open-source college textbooks in English, Spanish, and Polish, available under a permissive Creative Commons license. We finetune and evaluate large language models (LLMs) with approximately 7 billion parameters on this dataset using quantized low rank adapters (QLoRa). Additionally we also perform a zero-shot evaluation on the AI2 reasoning challenge dev dataset in order to check if OpenStaxQA can lead to an improved performance on other tasks. We also discuss broader impacts relevant to datasets such as OpenStaxQA.

cs.CL↗

Pagoda: An Energy and Time Roofline Study for DNN Workloads on Edge Accelerators

Edge accelerators such as Nvidia Jetsons are becoming an integral part of the computing continuum, and are often used for DNN inferencing and training. Nvidia Jetson edge devices have $2000$+ CUDA cores within a $70$W power envelope and offer $1000$s of power modes to customize CPU, GPU and memory frequencies. Their widely varying power--performance trade-offs can be exploited for energy and power-constrained deployments. While data-driven methods to predict the power and latency of DNN workloads for edge devices exist, there is a lack of principled study to understand why edge accelerators and their power modes perform the way they do. We develop a time roofline and a novel energy roofline model for the Jetson Orin AGX for diverse power modes, and couple it with an analytical model of the compute (FLOP) and memory access (bytes) for DNN inference workloads to analyze them from first principles. These reveal unique, sometimes counter-intuitive, insights into the power and performance behavior of DNN workloads on edge accelerators, e.g., the default power mode MAXN is not the most energy efficient and time efficiency implies energy efficiency for all power modes. We also extend our analytical roofline models to DNN training. Finally, we apply these methods to tune the power mode (and hence the roofline) of the edge device to optimize the latency and energy for DNN inference, with up to $15\%$ lower energy and minimal degradation in inference time.

cs.DC↗

Fulcrum: Optimizing Concurrent DNN Training and Inferencing on Edge Accelerators

The proliferation of GPU accelerated edge devices like Nvidia Jetsons and the rise in privacy concerns are placing an emphasis on concurrent DNN training and inferencing on edge devices. Inference and training have different computing and QoS goals. But edge accelerators like Jetson do not support native GPU sharing and expose 1000s of power modes. This requires careful time-sharing of concurrent workloads to meet power--performance goals, while limiting costly profiling. In this paper, we design an intelligent time-slicing approach for concurrent DNN training and inferencing on Jetsons. We formulate an optimization problem to interleave training and inferencing minibatches, and decide the device power mode and inference minibatch size, while maximizing the training throughput and staying within latency and power budgets, with modest profiling costs. We propose GMD, an efficient multi-dimensional gradient descent search which profiles just $15$ power modes; and ALS, an Active Learning technique which identifies reusable Pareto-optimal power modes, but profiles $50$--$150$ power modes. We evaluate these within our Fulcrum scheduler for $273,000+$ configurations across $15$ DNN workloads. We also evaluate our strategies on dynamic arrival inference and concurrent inferences. ALS and GMD outperform simpler and more complex baselines with larger-scale profiling. Their solutions satisfy the latency and power budget for $>97\%$ of our runs, and on average are within $7\%$ of the optimal throughput.

cs.DC↗

GCN-TULHOR: Trajectory-User Linking Leveraging GCNs and Higher-Order Spatial Representations

Trajectory-user linking (TUL) aims to associate anonymized trajectories with the users who generated them, which is crucial for personalized recommendations, privacy-preserving analytics, and secure location-based services. Existing methods struggle with sparse data, incomplete routes, and limited modeling of complex spatial dependencies, often relying on low-level check-in data or ignoring spatial patterns. In this paper, we introduced GCN-TULHOR, a method that transforms raw location data into higher-order mobility flow representations using hexagonal tessellation, reducing data sparsity and capturing richer spatial semantics, and integrating Graph Convolutional Networks (GCNs). Our approach converts both sparse check-in and continuous GPS trajectory data into unified higher-order flow representations, mitigating sparsity while capturing deeper semantic information. The GCN layer explicitly models complex spatial relationships and non-local dependencies without requiring side information such as timestamps or points of interest. Experiments on six real-world datasets show consistent improvements over classical baselines, RNN- and Transformer-based models, and the TULHOR method in accuracy, precision, recall, and F1-score. GCN-TULHOR achieves 1-8% relative gains in accuracy and F1. Sensitivity analysis identifies an optimal setup with a single GCN layer and 512-dimensional embeddings. The integration of GCNs enhances spatial learning and improves generalizability across mobility data. This work highlights the value of combining graph-based spatial learning with sequential modeling, offering a robust and scalable solution for TUL with applications in recommendations, urban planning, and security.

cs.LG↗

Discrete non-abelian X-ray transforms

We define a discrete version of the non-abelian X-ray transform, going back in particular to Manakov, Zakharov (1981) and Strichartz (1982). We extend to this transform non-overdetermined reconstruction results obtained for the abelian case in the recent article by Novikov, Sharma (2025). In addition, we establish relations with the continuous non-abelian X-ray transform. In this respect, our results include an explicit and exact non-overdetermined layer-stripping reconstruction procedure for piecewise constant matrix-valued functions from their continuous non-abelian X-ray transform. To our knowledge, this result is new even for the classical X-ray transform.

math.FA↗

CueBuddy: helping non-native English speakers navigate English-centric STEM education

Students across the world in STEM classes, especially in the Global South, fall behind their peers who are more fluent in English, despite being at par with them in terms of scientific prerequisites. While many of them are able to follow everyday English at ease, key terms in English stay challenging. In most cases, such students have had most of their course prerequisites in a lower resource language. Live speech translation to lower resource languages is a promising area of research, however, models for speech translation can be too expensive on a large scale and often struggle with technical content. In this paper, we describe CueBuddy, which aims to remediate these issues by providing real-time "lexical cues" through technical keyword spotting along real-time multilingual glossary lookup to help students stay up to speed with complex English jargon without disrupting their concentration on the lecture. We also describe the limitations and future extensions of our approach.

cs.CL↗

A Breadth-First Catalog of Text Processing, Speech Processing and Multimodal Research in South Asian Languages

We review the recent literature (January 2022- October 2024) in South Asian languages on text-based language processing, multimodal models, and speech processing, and provide a spotlight analysis focused on 21 low-resource South Asian languages, namely Saraiki, Assamese, Balochi, Bhojpuri, Bodo, Burmese, Chhattisgarhi, Dhivehi, Gujarati, Kannada, Kashmiri, Konkani, Khasi, Malayalam, Meitei, Nepali, Odia, Pashto, Rajasthani, Sindhi, and Telugu. We identify trends, challenges, and future research directions, using a step-wise approach that incorporates relevance classification and clustering based on large language models (LLMs). Our goal is to provide a breadth-first overview of the recent developments in South Asian language technologies to NLP researchers interested in working with South Asian languages.

cs.CL↗