arXiv subjects

Rahul Singh

Publications and source records attributed to Rahul Singh.

At least 55 records · Page 3Linked to original sources

arXiv2025

Jointly Optimal Policies for Remote Estimation of Autoregressive Markov Processes over Time-Correlated Fading Channel

We study a remote estimation setup with an autoregressive (AR) Markov process, a sensor, and a remote estimator. The sensor observes the process and sends encoded observations to the estimator as packets over an unreliable communication channel modeled as the Gilbert-Elliot (GE) channel. We assume that the sensor gets to observe the channel state by the ACK/NACK feedback mechanism only when it attempts a transmission while it does not observe the channel state when no transmission attempt is made. The objective is to design a transmission scheduling strategy for the sensor, and an estimation strategy for the estimator that are jointly optimal, i.e., they minimize the expected value of an infinite-horizon cumulative discounted cost defined as the sum of squared estimation error over time and the sensor's transmission power. Since the sensor and the estimator have access to different information sets, this constitutes a decentralized stochastic control problem. We formulate this problem as a partially observed Markov decision process (POMDP) and show the existence of jointly optimal transmission and estimation strategies that have a simple structure. More specifically, an optimal transmission strategy exhibits a threshold structure, i.e., the sensor attempts a transmission only when its belief about the channel being in a good state exceeds a threshold that depends on a certain error. Moreover, an optimal estimation strategy follows a `Kalman-like' update rule. When the channel parameters are unknown, we exploit this structure to design an actor-critic reinforcement learning algorithm that converges to a locally optimal policy. Simulations show the learned policy performs close to a globally optimal one, with about a 5.5% average relative gap across evaluated parameters.

math.OC↗

arXiv2025

Delay-Optimal Transmission Scheduling Policies for Time-Correlated Fading Channels

Millimeter-wave (mmWave) networks have the potential to support high throughput and low-latency requirements of 5G-and-beyond communication standards. But transmissions in this band are highly vulnerable to attenuation and blockages from humans, buildings, and foliage, which increase end-to-end packet delays. This work designs dynamic scheduling policies that minimize end-to-end packet delays while keeping packet transmission costs low. Specifically, we consider a mmWave network that consists of a transmitter that transmits data packets over an unreliable communication channel modeled as a Gilbert-Elliott channel.The transmitter operates under an ACK/NACK feedback model and does not observe the channel state unless it attempts a transmission. The objective is to minimize a weighted average cost consisting of end-to-end packet delays and packet transmission costs. We pose this dynamic optimization problem as a partially observable Markov decision process (POMDP). To the best of our knowledge, this is the first POMDP formulation for mmWave network with partial channel state information that considers delay minimization. We show that the POMDP admits a solution that has a threshold structure, i.e., for each queue length, the belief (the conditional probability that the channel is in a good state) is partitioned into intervals, and the transmitter sends j packets when the belief lies in the j-th interval. We then consider the case when the system parameters such as the packet arrival rate, and the transition probabilities of the channel are not known, and leverage these structural results in order to use the actor-critic algorithm to efficiently search for a policy that is locally optimal.

math.OC↗

arXiv2025

Policy Zooming: Adaptive Discretization-based Infinite-Horizon Average-Reward Reinforcement Learning

We study the infinite-horizon average-reward reinforcement learning (RL) for continuous space Lipschitz MDPs in which an agent can play policies from a given set $Φ$. The proposed algorithms efficiently explore the policy space by ''zooming'' into the ''promising regions'' of $Φ$, thereby achieving adaptivity gains in the performance. We upper bound their regret as $\tilde{\mathcal{O}}\big(T^{1 - d_{\text{eff.}}^{-1}}\big)$, where $d_{\text{eff.}} = d^Φ_z+2$ for model-free algoritahm $\textit{PZRL-MF}$ and $d_{\text{eff.}} = 2d_\mathcal{S} + d^Φ_z + 3$ for model-based algorithm $\textit{PZRL-MB}$. Here, $d_\mathcal{S}$ is the dimension of the state space, and $d^Φ_z$ is the zooming dimension given a set of policies $Φ$. $d^Φ_z$ is an alternative measure of the complexity of the problem, and it depends on the underlying MDP as well as on $Φ$. Hence, the proposed algorithms exhibit low regret in case the problem instance is benign and/or the agent competes against a low-complexity $Φ$ (that has a small $d^Φ_z$). When specialized to the case of finite-dimensional policy space, we obtain that $d_{\text{eff.}}$ scales as the dimension of this space under mild technical conditions; and also obtain $d_{\text{eff.}} = 2$, or equivalently $\tilde{\mathcal{O}}(\sqrt{T})$ regret for $\textit{PZRL-MF}$, under a curvature condition on the average reward function that is commonly used in the multi-armed bandit (MAB) literature.

cs.LG↗

arXiv2025

Automatic Debiased Machine Learning for Covariate Shifts

We present machine learning estimators for causal and predictive parameters under covariate shift, where covariate distributions differ between training and target populations. One such parameter is the average effect of a policy that alters the covariate distribution, such as a treatment modifying surrogate covariates used to predict long-term outcomes. Another example is the average treatment effect for a population with a shifted covariate distribution, like the effect of a policy on the treated group. We propose a debiased machine learning method to estimate a broad class of these parameters in a statistically reliable and automatic manner. Our method eliminates regularization biases arising from the use of machine learning tools in high-dimensional settings, relying solely on the parameter's defining formula. It employs data fusion by combining samples from target and training data to eliminate biases. We prove that our estimator is consistent and asymptotically normal. Computational experiments and an empirical study on the impact of minimum wage increases on teen employment--using the difference-in-differences framework with unconfoundedness--demonstrate the effectiveness of our method.

stat.ME↗

arXiv2025

RF characterization and beam measurements with 3D printed Fast Faraday Cups

The early stages of most particle accelerator chains produce sub-ns bunches with velocities in the range of 1 to 20% of the speed of light. Fast Faraday Cups (FFC) are designed to measure the longitudinal charge distribution of these short bunches of free charges. Coaxial designs have been utilized at the GSI's linear accelerator UNILAC to characterize ion bunches with bunch lengths ranging from a few hundred ps to a few ns. The typical design goals are to avoid the pre-field of the charges and to suppress secondary electron emission, while retaining the capability of bunch-by-bunch measurements. In this contribution, a novel FFC design manufactured using additive manufacturing, e.g. laser powder bed fusion is presented and compared with a traditionally produced FFC. The design considerations, RF characterization, and selected measurements with ion beam at GSI are shown.

physics.acc-ph↗

arXiv2025

A Personalized Exercise Assistant using Reinforcement Learning (PEARL): Results from a four-arm Randomized-controlled Trial

Consistent physical inactivity poses a major global health challenge. Mobile health (mHealth) interventions, particularly Just-in-Time Adaptive Interventions (JITAIs), offer a promising avenue for scalable, personalized physical activity (PA) promotion. However, developing and evaluating such interventions at scale, while integrating robust behavioral science, presents methodological hurdles. The PEARL study was the first large-scale, four-arm randomized controlled trial to assess a reinforcement learning (RL) algorithm, informed by health behavior change theory, to personalize the content and timing of PA nudges via a Fitbit app. We enrolled and randomized 13,463 Fitbit users into four study arms: control, random, fixed, and RL. The control arm received no nudges. The other three arms received nudges from a bank of 155 nudges based on behavioral science principles. The random arm received nudges selected at random. The fixed arm received nudges based on a pre-set logic from survey responses about PA barriers. The RL group received nudges selected by an adaptive RL algorithm. We included 7,711 participants in primary analyses (mean age 42.1, 86.3% female, baseline steps 5,618.2). We observed an increase in PA for the RL group compared to all other groups from baseline to 1 and 2 months. The RL group had significantly increased average daily step count at 1 month compared to all other groups: control (+296 steps, p=0.0002), random (+218 steps, p=0.005), and fixed (+238 steps, p=0.002). At 2 months, the RL group sustained a significant increase compared to the control group (+210 steps, p=0.0122). Generalized estimating equation models also revealed a sustained increase in daily steps in the RL group vs. control (+208 steps, p=0.002). These findings demonstrate the potential of a scalable, behaviorally-informed RL approach to personalize digital health interventions for PA.

cs.LG↗

arXiv2025

Revealing Temporal Label Noise in Multimodal Hateful Video Classification

The rapid proliferation of online multimedia content has intensified the spread of hate speech, presenting critical societal and regulatory challenges. While recent work has advanced multimodal hateful video detection, most approaches rely on coarse, video-level annotations that overlook the temporal granularity of hateful content. This introduces substantial label noise, as videos annotated as hateful often contain long non-hateful segments. In this paper, we investigate the impact of such label ambiguity through a fine-grained approach. Specifically, we trim hateful videos from the HateMM and MultiHateClip English datasets using annotated timestamps to isolate explicitly hateful segments. We then conduct an exploratory analysis of these trimmed segments to examine the distribution and characteristics of both hateful and non-hateful content. This analysis highlights the degree of semantic overlap and the confusion introduced by coarse, video-level annotations. Finally, controlled experiments demonstrated that time-stamp noise fundamentally alters model decision boundaries and weakens classification confidence, highlighting the inherent context dependency and temporal continuity of hate speech expression. Our findings provide new insights into the temporal dynamics of multimodal hateful videos and highlight the need for temporally aware models and benchmarks for improved robustness and interpretability. Code and data are available at https://github.com/Multimodal-Intelligence-Lab-MIL/HatefulVideoLabelNoise.

cs.CV↗

arXiv2025

Provably Adaptive Average Reward Reinforcement Learning for Metric Spaces

We study infinite-horizon average-reward reinforcement learning (RL) for Lipschitz MDPs, a broad class that subsumes several important classes such as linear and RKHS MDPs, function approximation frameworks, and develop an adaptive algorithm $\text{ZoRL}$ with regret bounded as $\mathcal{O}\big(T^{1 - d_{\text{eff.}}^{-1}}\big)$, where $d_{\text{eff.}}= 2d_\mathcal{S} + d_z + 3$, $d_\mathcal{S}$ is the dimension of the state space and $d_z$ is the zooming dimension. In contrast, algorithms with fixed discretization yield $d_{\text{eff.}} = 2(d_\mathcal{S} + d_\mathcal{A}) + 2$, $d_\mathcal{A}$ being the dimension of action space. $\text{ZoRL}$ achieves this by discretizing the state-action space adaptively and zooming into ''promising regions'' of the state-action space. $d_z$, a problem-dependent quantity bounded by the state-action space's dimension, allows us to conclude that if an MDP is benign, then the regret of $\text{ZoRL}$ will be small. The zooming dimension and $\text{ZoRL}$ are truly adaptive, i.e., the current work shows how to capture adaptivity gains for infinite-horizon average-reward RL. $\text{ZoRL}$ outperforms other state-of-the-art algorithms in experiments, thereby demonstrating the gains arising due to adaptivity.

cs.LG↗

arXiv2025

RCA Copilot: Transforming Network Data into Actionable Insights via Large Language Models

Ensuring the reliability and availability of complex networked services demands effective root cause analysis (RCA) across cloud environments, data centers, and on-premises networks. Traditional RCA methods, which involve manual inspection of data sources such as logs and telemetry data, are often time-consuming and challenging for on-call engineers. While statistical inference methods have been employed to estimate the causality of network events, these approaches alone are similarly challenging and suffer from a lack of interpretability, making it difficult for engineers to understand the predictions made by black-box models. In this paper, we present RCACopilot, an advanced on-call system that combines statistical tests and large language model (LLM) reasoning to automate RCA across various network environments. RCACopilot gathers and synthesizes critical runtime diagnostic information, predicts the root cause of incidents, provides a clear explanatory narrative, and offers targeted action steps for engineers to resolve the issues. By utilizing LLM reasoning techniques and retrieval, RCACopilot delivers accurate and practical support for operators.

cs.NI↗

arXiv2025

Computer Vision based Automated Quantification of Agricultural Sprayers Boom Displacement

Application rate errors when using self-propelled agricultural sprayers for agricultural production remain a concern. Among other factors, spray boom instability is one of the major contributors to application errors. Spray booms' width of 38m, combined with 30 kph driving speeds, varying terrain, and machine dynamics when maneuvering complex field boundaries, make controls of these booms very complex. However, there is no quantitative knowledge on the extent of boom movement to systematically develop a solution that might include boom designs and responsive boom control systems. Therefore, this study was conducted to develop an automated computer vision system to quantify the boom movement of various agricultural sprayers. A computer vision system was developed to track a target on the edge of the sprayer boom in real time. YOLO V7, V8, and V11 neural network models were trained to track the boom's movements in field operations to quantify effective displacement in the vertical and transverse directions. An inclinometer sensor was mounted on the boom to capture boom angles and validate the neural network model output. The results showed that the model could detect the target with more than 90 percent accuracy, and distance estimates of the target on the boom were within 0.026 m of the inclinometer sensor data. This system can quantify the boom movement on the current sprayer and potentially on any other sprayer with minor modifications. The data can be used to make design improvements to make sprayer booms more stable and achieve greater application accuracy.

cs.CV↗

arXiv2025

SlepNet: Spectral Subgraph Representation Learning for Neural Dynamics

Graph neural networks have been useful in machine learning on graph-structured data, particularly for node classification and some types of graph classification tasks. However, they have had limited use in representing patterning of signals over graphs. Patterning of signals over graphs and in subgraphs carries important information in many domains including neuroscience. Neural signals are spatiotemporally patterned, high dimensional and difficult to decode. Graph signal processing and associated GCN models utilize the graph Fourier transform and are unable to efficiently represent spatially or spectrally localized signal patterning on graphs. Wavelet transforms have shown promise here, but offer non-canonical representations and cannot be tightly confined to subgraphs. Here we propose SlepNet, a novel GCN architecture that uses Slepian bases rather than graph Fourier harmonics. In SlepNet, the Slepian harmonics optimally concentrate signal energy on specifically relevant subgraphs that are automatically learned with a mask. Thus, they can produce canonical and highly resolved representations of neural activity, focusing energy of harmonics on areas of the brain which are activated. We evaluated SlepNet across three fMRI datasets, spanning cognitive and visual tasks, and two traffic dynamics datasets, comparing its performance against conventional GNNs and graph signal processing constructs. SlepNet outperforms the baselines in all datasets. Moreover, the extracted representations of signal patterns from SlepNet offers more resolution in distinguishing between similar patterns, and thus represent brain signaling transients as informative trajectories. Here we have shown that these extracted trajectory representations can be used for other downstream untrained tasks. Thus we establish that SlepNet is useful both for prediction and representation learning in spatiotemporal data.

cs.LG↗

arXiv2025

Nested Nonparametric Instrumental Variable Regression

Several causal parameters in short panel data models are functionals of a nested nonparametric instrumental variable regression (nested NPIV). Recent examples include mediated, time varying, and long term treatment effects identified using proxy variables. In econometrics, examples arise in triangular simultaneous equations and hedonic price systems. However, it appears that explicit mean square convergence rates for nested NPIV are unknown, preventing inference on some of these parameters with generic machine learning. A major challenge is compounding ill posedness due to the nested inverse problems. To limit how ill posedness compounds, we introduce two techniques: relative well posedness, and multiple robustness to ill posedness. With these techniques, we provide explicit mean square rates for nested NPIV and efficient inference for recently identified causal parameters. Our nonasymptotic analysis accommodates neural networks, random forests, and reproducing kernel Hilbert spaces. It extends to causal functions, e.g. heterogeneous long term treatment effects.

stat.ML↗

arXiv2025

Least squares for cardinal paired comparisons data

Least square estimators for graphical models for cardinal paired comparison data with and without covariates are rigorously analyzed. Novel, graph--based, necessary and sufficient conditions that guarantee strong consistency, asymptotic normality and the exponential convergence of the estimated ranks are emphasized. A complete theory for models with covariates is laid out. In particular, conditions under which covariates can be safely omitted from the model are provided. The methodology is employed in the analysis of both finite and infinite sets of ranked items where the case of large sparse comparison graphs is addressed. The proposed methods are explored by simulation and applied to the ranking of teams in the National Basketball Association (NBA).

stat.ME↗

arXiv2025

Hybrid SiO2/Si Pillar-Based Optomechanical Crystals for On-Chip Photonic Integration

One-dimensional photonic crystal (1D-PhC) pillar cavities allow transducing mechanical pillar vibrations to the optical domain, thereby relaxing the requirements typically associated with mechanical motion detection. In this study, we integrate these geometries into a silicon-on-insulator photonics platform and explore their optical and mechanical properties. The 1D-PhC structures consist of a linear array of high aspect ratio nanopillars with nanometer-sized diameters, designed to enhance the interaction between transverse-magnetic (TM) polarized optical fields and mechanical vibrations and to minimize optical leaking to the substrate. Integrated waveguides are engineered to support TM-like modes, which enable optimized coupling to the 1D-PhC optical cavity modes via evanescent wave interaction. Finite element method simulations and experimental analyses reveal that these cavities achieve relatively high optical quality factors (Q = 4x10^3). In addition, both simulated and experimentally measured mechanical vibrational frequencies show large optomechanical coupling rates exceeding 1 MHz for the fundamental cantilever-like modes. By tuning the separation between the 1D-PhC and the waveguide, we achieve optimal optical coupling conditions that enable the transduction of thermally activated mechanical modes across a broad frequency range (from tens to several hundreds of MHz). This enhanced accessibility and efficiency in mechanical motion transduction significantly strengthens the viability of established microelectromechanical (MEMS) and nanoelectromechanical systems (NEMS) technologies based on nanowires, nanorods, and related structures, particularly in applications such as force sensing and biosensing.

physics.optics↗

arXiv2025

GVPT -- A software for guided visual pitch tracking

GVPT (Guided visual pitch tracking) is a publicly available, real-time pitch tracking software designed to guide and evaluate vocal pitch control using visual feedback. Developed for clinical and research applications, the system presents various visual target pitch contour and overlays the subject's pitch in real-time to promote accurate vocal reproduction. GVPT supports difficulty modification, session logging, and precise pitch tracking. The software enables voice pitch control exercise in both experimental and therapeutic settings.

cs.SD↗

arXiv2025

An Empirical Study on Common Defects in Modern Web Browsers Using Knowledge Embedding in GPT-4o

Technology is advancing at an unprecedented pace. With the advent of cutting-edge technologies, keeping up with rapid changes are becoming increasingly challenging. In addition to that, increasing dependencies on the cloud technologies have imposed enormous pressure on modern web browsers leading to adapting new technologies faster and making them more susceptible to defects/bugs. Although, many studies have explored browser bugs, a comparative study among the modern browsers generalizing the bug categories and their nature was still lacking. To fill this gap, we undertook an empirical investigation aimed at gaining insights into the prevalent bugs in Google Chromium and Mozilla Firefox as the representatives of modern web browsers. We used GPT-4.o to identify the defect (bugs) categories and analyze the clusters of the most commonly appeared bugs in the two prominent web browsers. Additionally, we compared our LLM based bug categorization with the traditional NLP based approach using TF-IDF and K-Means clustering. We found that although Google Chromium and Firefox have evolved together since almost around the same time (2006-2008), Firefox suffers from high number of bugs having extremely high defect-prone components compared to Chromium. This exploratory study offers valuable insights on the browser bugs and defect-prone components to the developers, enabling them to craft web browsers and web-applications with enhanced resilience and reduced errors.

cs.SE↗

arXiv2025

$QQ$-systems and tropical geometry

We investigate the system of polynomial equations, known as $QQ$-systems, which are closely related to the so-called Bethe ansatz equations of the XXZ spin chain, using the methods of tropical geometry.

math.AG↗

arXiv2025

Counting Parabolic Principal G-bundles with Nilpotent Sections over $\mathbb{P}^{1}$

Let $G$ be a split connected reductive group over $\mathbb{F}_q$ and let $\mathbb{P}^1$ be the projective line over $\mathbb{F}_q$. Firstly, we give an explicit formula for the number of $\mathbb{F}_{q}$-rational points of generalized Steinberg varieties of $G$. Secondly, for each principal $G$-bundle over $\mathbb{P}^1$, we give an explicit formula counting the number of triples consisting of parabolic structures at $0$ and $\infty$ and a compatible nilpotent section of the associated adjoint bundle. In the case of $GL_{n}$ we calculate a generating function of such volumes re-deriving a result of Mellit.

math.AG↗