arXiv subjects

Karthik Mohan

Publications and source records attributed to Karthik Mohan.

13 recordsLinked to original sources

arXiv2026

Modeling mental health trajectories during the COVID-19 pandemic using UK-wide data in the presence of sociodemographic variables

Background: The negative effects of the COVID-19 pandemic on the mental health and well-being of populations are an important public health issue. Our study aims to determine the underlying factors shaping mental health trajectories during the COVID-19 pandemic in the UK. Methods: Data from the Understanding Society COVID-19 Study were utilized and the core analysis focussed on GHQ36 scores as the outcome variable. We used GAMs to evaluate trends over time and the role of sociodemographic variables, i.e., age, sex, ethnicity, country of residence (in UK), job status (employment), household income, living with a partner, living with children under age 16, and living with a long-term illness, on the variation of mental health during the study period. Results: Statistically significant differences in mental health were observed for age, sex,ethnicity, country of residence (in UK), job status (employment), household income, living with a partner, living with children under age 16, and living with a long-term illness. Women experienced higher GHQ36 scores relative to men with the GHQ36 score expected to increase by 1.260 (95%CI: 1.176, 1.345). Individuals living without a partner were expected to have higher GHQ36 scores, of 1.050 (95%CI: 0.949, 1.148) more than those living with a partner, and age groups 16-34, 35-44, 45-54, 55-64 experienced higher GHQ36 scores relative to those who were 65+. Individuals with relatively lower household income were likely to have poorer mental health relative to those who were more well off. Conclusion: This study identifies key demographic determinants shaping mental health trajectories during the COVID-19 pandemic in the UK. Policies aiming to reduce mental health inequalities should target women, youth, individuals living without a partner, individuals living with children under 16, individuals with a long-term illness, and lower income families.

stat.AP↗

arXiv2025

BeLLA: End-to-End Birds Eye View Large Language Assistant for Autonomous Driving

The rapid development of Vision-Language models (VLMs) and Multimodal Language Models (MLLMs) in autonomous driving research has significantly reshaped the landscape by enabling richer scene understanding, context-aware reasoning, and more interpretable decision-making. However, a lot of existing work often relies on either single-view encoders that fail to exploit the spatial structure of multi-camera systems or operate on aggregated multi-view features, which lack a unified spatial representation, making it more challenging to reason about ego-centric directions, object relations, and the wider context. We thus present BeLLA, an end-to-end architecture that connects unified 360{\deg} BEV representations with a large language model for question answering in autonomous driving. We primarily evaluate our work using two benchmarks - NuScenes-QA and DriveLM, where BeLLA consistently outperforms existing approaches on questions that require greater spatial reasoning, such as those involving relative object positioning and behavioral understanding of nearby objects, achieving up to +9.3% absolute improvement in certain tasks. In other categories, BeLLA performs competitively, demonstrating the capability of handling a diverse range of questions.

cs.CV↗

arXiv2025

Carrier-Assisted Entanglement Purification

Entanglement distillation, a fundamental building block of quantum networks, enables the purification of noisy entangled states shared among distant nodes by local operations and classical communication. Its practical realization presents several technical challenges, including the storage of quantum states in quantum memory and the execution of coherent quantum operations on multiple copies of states within the quantum memory. In this work, we present an entanglement purification protocol via quantum communication, namely a carrier-assisted entanglement purification protocol, which utilizes two elements only: i) quantum memory for a single-copy entangled state shared by parties and ii) single qubits travelling between parties. We show that the protocol, when single-qubit transmission is noiseless, can purify a noisy entangled state shared by parties. When single-qubit transmission is noisy, the purification relies on types of noisy qubit channels; we characterize Pauli channels such that the protocol works for the purification. We address this limitation by using multiple carrier qubits, and show that for any non-entanglement-breaking Pauli channel, the protocol's fixed-point fidelity approaches unity as the number of carriers increases. Our results significantly reduce the experimental overhead required for distilling entanglement: the practical advantage is demonstrated through parameters directly related to the capability of entanglement purification, such as noise in quantum memory, local measurements, channel use, and entanglement fidelity. We envisage that the protocol would make long-distance pure entanglement closer to a practical realization.

quant-ph↗

arXiv2025

Random Exclusion Codes: Quantum Advantages of Single-Shot Communication

Useful applications of quantum information technologies can be found by identifying tasks in which quantum resources outperform their classical counterparts. In this work, we introduce a two-party communication primitive, random exclusion code (REC), which is a single-shot prepare-and-measure protocol where a sender encodes a random message into a shorter sequence and a receiver attempts to exclude a randomly chosen letter in the original message. We present quantum advantages in RECs in two ways: probability and dimension. We show that RECs with quantum resources achieve higher success probabilities than classical strategies. We verify that the quantum resources required to describe detection events of RECs have a smaller dimension than classical ones. We also show that a guessing counterpart, random access codes (RACs), may not have a dimension advantage over classical resources. Our results elucidate various possibilities of achieving quantum advantages in two-party communication.

quant-ph↗

arXiv2025

A study on performance limitations in Federated Learning

Increasing privacy concerns and unrestricted access to data lead to the development of a novel machine learning paradigm called Federated Learning (FL). FL borrows many of the ideas from distributed machine learning, however, the challenges associated with federated learning makes it an interesting engineering problem since the models are trained on edge devices. It was introduced in 2016 by Google, and since then active research is being carried out in different areas within FL such as federated optimization algorithms, model and update compression, differential privacy, robustness, and attacks, federated GANs and privacy preserved personalization. There are many open challenges in the development of such federated machine learning systems and this project will be focusing on the communication bottleneck and data Non IID-ness, and its effect on the performance of the models. These issues are characterized on a baseline model, model performance is evaluated, and discussions are made to overcome these issues.

cs.LG↗

arXiv2025

Embedding-Based Approaches to Hyperpartisan News Detection

In this report, I describe the systems in which the objective is to determine whether a given news article could be considered as hyperpartisan. Hyperpartisan news takes an extremely polarized political standpoint with an intention of creating political divide among the public. Several approaches, including n-grams, sentiment analysis, as well as sentence and document representations using pre-tained ELMo models were used. The best system is using LLMs for embedding generation achieving an accuracy of around 92% over the previously best system using pre-trained ELMo with Bidirectional LSTM which achieved an accuracy of around 83% through 10-fold cross-validation.

cs.LG↗

arXiv2024

KANs for Computer Vision: An Experimental Study

This paper presents an experimental study of Kolmogorov-Arnold Networks (KANs) applied to computer vision tasks, particularly image classification. KANs introduce learnable activation functions on edges, offering flexible non-linear transformations compared to traditional pre-fixed activation functions with specific neural work like Multi-Layer Perceptrons (MLPs) and Convolutional Neural Networks (CNNs). While KANs have shown promise mostly in simplified or small-scale datasets, their effectiveness for more complex real-world tasks such as computer vision tasks remains less explored. To fill this gap, this experimental study aims to provide extended observations and insights into the strengths and limitations of KANs. We reveal that although KANs can perform well in specific vision tasks, they face significant challenges, including increased hyperparameter sensitivity and higher computational costs. These limitations suggest that KANs require architectural adaptations, such as integration with other architectures, to be practical for large-scale vision problems. This study focuses on empirical findings rather than proposing new methods, aiming to inform future research on optimizing KANs, in particular computer vision applications or alike.

cs.CV↗

arXiv2020

Best Practices for Data-Efficient Modeling in NLG:How to Train Production-Ready Neural Models with Less Data

Natural language generation (NLG) is a critical component in conversational systems, owing to its role of formulating a correct and natural text response. Traditionally, NLG components have been deployed using template-based solutions. Although neural network solutions recently developed in the research community have been shown to provide several benefits, deployment of such model-based solutions has been challenging due to high latency, correctness issues, and high data needs. In this paper, we present approaches that have helped us deploy data-efficient neural solutions for NLG in conversational systems to production. We describe a family of sampling and modeling techniques to attain production quality with light-weight neural network models using only a fraction of the data that would be necessary otherwise, and show a thorough comparison between each. Our results show that domain complexity dictates the appropriate approach to achieve high data efficiency. Finally, we distill the lessons from our experimental findings into a list of best practices for production-level NLG model development, and present them in a brief runbook. Importantly, the end products of all of the techniques are small sequence-to-sequence models (2Mb) that we can reliably deploy in production.

cs.CL↗

arXiv2019

Sequential random access codes and self-testing of quantum measurement instruments

Quantum Random Access Codes (QRACs) are key tools for a variety of protocols in quantum information theory. These are commonly studied in prepare-and-measure scenarios in which a sender prepares states and a receiver measures them. Here, we consider a three-party prepare-transform-measure scenario in which the simplest QRAC is implemented twice in sequence based on the same physical system. We derive optimal trade-off relations between the two QRACs. We apply our results to construct semi-device independent self-tests of quantum instruments, i.e. measurement channels with both a classical and quantum output. Finally, we show how sequential QRACs enable inference of upper and lower bounds on the sharpness parameter of a quantum instrument.

quant-ph↗

arXiv2014

Learning Graphical Models With Hubs

We consider the problem of learning a high-dimensional graphical model in which certain hub nodes are highly-connected to many other nodes. Many authors have studied the use of an l1 penalty in order to learn a sparse graph in high-dimensional setting. However, the l1 penalty implicitly assumes that each edge is equally likely and independent of all other edges. We propose a general framework to accommodate more realistic networks with hub nodes, using a convex formulation that involves a row-column overlap norm penalty. We apply this general framework to three widely-used probabilistic graphical models: the Gaussian graphical model, the covariance graph model, and the binary Ising model. An alternating direction method of multipliers algorithm is used to solve the corresponding convex optimization problems. On synthetic data, we demonstrate that our proposed framework outperforms competitors that do not explicitly model hub nodes. We illustrate our proposal on a webpage data set and a gene expression data set.

stat.ML↗

arXiv2014

Node-Based Learning of Multiple Gaussian Graphical Models

We consider the problem of estimating high-dimensional Gaussian graphical models corresponding to a single set of variables under several distinct conditions. This problem is motivated by the task of recovering transcriptional regulatory networks on the basis of gene expression data {containing heterogeneous samples, such as different disease states, multiple species, or different developmental stages}. We assume that most aspects of the conditional dependence networks are shared, but that there are some structured differences between them. Rather than assuming that similarities and differences between networks are driven by individual edges, we take a node-based approach, which in many cases provides a more intuitive interpretation of the network differences. We consider estimation under two distinct assumptions: (1) differences between the K networks are due to individual nodes that are perturbed across conditions, or (2) similarities among the K networks are due to the presence of common hub nodes that are shared across all K networks. Using a row-column overlap norm penalty function, we formulate two convex optimization problems that correspond to these two assumptions. We solve these problems using an alternating direction method of multipliers algorithm, and we derive a set of necessary and sufficient conditions that allows us to decompose the problem into independent subproblems so that our algorithm can be scaled to high-dimensional settings. Our proposal is illustrated on synthetic data, a webpage data set, and a brain cancer gene expression data set.

stat.ML↗

arXiv2013

ADMM Algorithm for Graphical Lasso with an $\ell_{\infty}$ Element-wise Norm Constraint

We consider the problem of Graphical lasso with an additional $\ell_{\infty}$ element-wise norm constraint on the precision matrix. This problem has applications in high-dimensional covariance decomposition such as in \citep{Janzamin-12}. We propose an ADMM algorithm to solve this problem. We also use a continuation strategy on the penalty parameter to have a fast implemenation of the algorithm.

cs.LG↗

arXiv2011

A Simplified Approach to Recovery Conditions for Low Rank Matrices

Recovering sparse vectors and low-rank matrices from noisy linear measurements has been the focus of much recent research. Various reconstruction algorithms have been studied, including $\ell_1$ and nuclear norm minimization as well as $\ell_p$ minimization with $p<1$. These algorithms are known to succeed if certain conditions on the measurement map are satisfied. Proofs of robust recovery for matrices have so far been much more involved than in the vector case. In this paper, we show how several robust classes of recovery conditions can be extended from vectors to matrices in a simple and transparent way, leading to the best known restricted isometry and nullspace conditions for matrix recovery. Our results rely on the ability to "vectorize" matrices through the use of a key singular value inequality.

math.OC↗