arXiv subjects

Priyam Das

Publications and source records attributed to Priyam Das.

At least 19 recordsLinked to original sources

arXiv2026

Ejecta clumps revealed by study of reverse-shocked ejecta through MUSE integral field spectroscopy of SNR 0509-67.5

We report the discovery of a spatially resolved clumpy ejecta structure in the reverse-shocked ejecta of SNR 0509-67.5, revealed through multiple faint and broad forbidden coronal emission lines in deep MUSE observations. We also identify two new broad coronal emission lines not reported before in this remnant, [Fe xi] 7894 A and [Fe x] 6374.5 A , which extend the set of previously reported [Fe xv] 7059.59 A, [Fe xiv] 5302.86 A , [Fe ix] 8236.55 A , [Ca xv] 5695 A, and [S xii] 7611.0 A. Near-continuous ionisation states of Fe allow us to follow the ionisation progression behind the reverse shock. We use a 1D analytical model to evolve Fe charge states following reverse shock interaction to compare with observations, indicating the need for preshock clumping or over-density in order to reproduce the observed surface brightness of the [Fe xiv] line. Additionally, we report the spatially resolved distribution of ejecta clumps and show that reverse-shock interaction drives their compression and fragmentation. We also find a clear trend of decreasing velocity width with increasing Fe ionisation state, from the broadest [Fe ix] emission to the narrowest [Fe xv], with intermediate-ionisation species ([Fe x], [Fe xi], [Fe xiv]) showing intermediate widths. Finally, we compare our observations to a dynamically driven double-degenerate double detonation (D6) 3D remnant model at similar Fe and S ionisation states and conclude that the observed clumps are predominantly due to Rayleigh-Taylor instabilities.

astro-ph.SR↗

arXiv2026

Deep MUSE observations of SNR 0509-67.5 reveal a double degenerate merger progenitor

Deep MUSE observations of SNR 0509-67.5 reveal that the coronal [Fe\,\textsc{xiv}] $\mathrm{\lambda}$5303 emission line appears with either one or two velocity components across the entire remnant, arising from reverse-shocked ejecta moving toward and away from the observer. A supervised dense neural network classifies each spaxel and fits Gaussian profiles plus a linear function to the observed line emission. We measure a bulk Doppler velocity of $-1000\pm60~~\mathrm{km~s^{-1}}$, interpreted as the line-of-sight component of the primary white dwarf's orbital velocity in a double-degenerate merger. The red- and blue-shifted ejecta map shows a flattened edge along the north-eastern rim, consistent with the companion's shadow, indicating a binary companion was present at explosion. Modelling this feature as a cone anchored at the explosion centre and applying Bayesian inference, we recover the cone's orientation and half-opening angle. We then use the Eggleton Roche-lobe relation to infer properties of the companion. The companion was likely a ${\sim}0.6~\mathrm{M_\odot}$ white dwarf with radius ${\sim}9800$~km and orbital velocity ${\sim}1700~\mathrm{km~s^{-1}}$ at the time of explosion. Together, these results provide a complete dynamical picture of a Type Ia supernova progenitor system whose maximum-light spectrum is independently constrained by light echo observations.

astro-ph.SR↗

arXiv2026

MAPLE: Mapper Based Localized Prediction with Data Driven Cover Selection for High dimensional Data

High dimensional biomedical data often exhibit nonlinear, heterogeneous, and manifold driven structures that challenge global parametric and tree-based models. We propose MAPLE (mapper-based Adaptive Prediction via Local Estimation), a localized prediction framework grounded in topological data analysis. The method is formulated as a nonparametric estimator of conditional class probabilities that adapts to the intrinsic geometry of the predictor space. Neighborhoods are defined through connectivity in a data-adaptive Mapper graph, enabling localized averaging within graph induced regions that capture complex structures such as branching and multi-scale heterogeneity. We introduce a statistically principled, data driven procedure for cover selection based on a bias-variance trade off, yielding optimal asymptotic scaling for interval widths and overlaps. The framework accommodates binary, nominal, and ordinal outcomes and incorporates a permutation-based variable importance measure to quantify covariate contributions in prediction. We establish theoretical guarantees, including pointwise consistency and Bayes risk consistency under standard regularity conditions. Simulations show that MAPLE consistently outperforms or matches multinomial regression, ordinal regression, and random forest, with the largest gains observed under heterogeneous and high-noise settings. Applications to Parkinson's disease progression (PPMI) and glioma classification (TCGA RNA sequencing) demonstrate strong predictive accuracy and interpretable, topology-aware summaries of underlying data structure.

stat.ME↗

arXiv2026

Supervised Low-Rank Structure Discovery for Developmental Epigenetic Aging in Ultra-High-Dimensional DNA Methylation Data

Ultra-high-dimensional array-based CpG methylation studies require statistical frameworks that simultaneously provide supervised structure discovery, interpretability, scalable latent-dimension identification, and computational feasibility. We propose SOLAR (Supervised Orthogonal Low-rank Adaptive Regression), a supervised low-rank latent-factor framework for identifying CpG-level methylation structure associated with residualized DNAm age. SOLAR combines orthogonal low-rank regression with a penalized maximum a posteriori formulation, dimension-adaptive BIC-type penalization, and a trans-dimensional simulated-annealing strategy for automatic latent-rank selection, together with theoretical guarantees including identifiability, fixed-rank recovery, and rank-selection consistency under suitable regularity conditions. The framework additionally incorporates computationally and memory-efficient optimization strategies demonstrating scalability up to $p=10^7$, while analyses at $p=10^6$ remain feasible on standard desktop computing environments. Simulation studies demonstrate stable rank recovery, competitive supervised signal recovery, and strong scalability across moderate-, high-, and ultra-high-dimensional regimes. Using longitudinal EPIC-array CpG methylation data from the GUSTO birth cohort, comprising $n=1051$ methylation profiles collected across infancy and early childhood with approximately 860,000 assayed CpGs per sample, SOLAR identifies heterogeneous supervised methylation structure associated with residualized DNAm age beyond chronological age alone, together with biologically coherent CpG signatures and enrichment patterns.

stat.ME↗

arXiv2026

Helium emission from Balmer-dominated shocks in Type Ia supernova remnants provides constraints to their progenitor systems

Balmer-dominated shocks in Type Ia supernova remnants offer powerful probes into collisionless shock physics and hints towards supernova progenitor environments. Prior studies focused on the hydrogen Balmer lines, which manifest as a superposition of broad and narrow emission lines. Using integral-field spectroscopy with MUSE, we discovered broad and narrow helium emission lines from Balmer-dominated filaments of three Type Ia supernovae remnants in the Large Magellanic Cloud: SNR 0509-67.5, SNR 0519-69.0 and N103B. We detect broad and narrow He~\textsc{i} 5876~\AA~,7065~\AA\ emission in SNR 0519 and N103B and He \textsc{ii} 8236~\AA\ in SNR 0519. In SNR 0509 we detect narrow He~\textsc{i} 5015~\AA, 6678~\AA, 7065~\AA\ and 7281~\AA, with only 7065~\AA~ exhibiting a broad component. The detection of narrow He\,\textsc{ii} challenges existing shock models, where such emission is not expected, and may indicate either incomplete ion-ion equilibration behind the shock or an origin in shock precursors. For SNR 0509 and N103B, the neutral He/H line ratios indicate enhanced helium abundances, whereas SNR 0519 is consistent with the primordial He/H value. We therefore propose helium emission in Balmer-dominated shocks as a new diagnostic of shock physics and Type Ia supernova circumstellar environments. Although our modeling is primarily a proof of concept, it demonstrates the possibility to infer the total He-to-H abundance ratio, with dominant uncertainties arising from the assumed initial ionization fractions. Despite the uncertainties, we demonstrate that narrow helium lines can serve as effective probes of circumstellar conditions and progenitor evolution when analysed alongside reliable constraints on the preshock neutral H/He abundance ratio.

astro-ph.SR↗

arXiv2026

BOOOM: Loss-Function-Agnostic Black-Box Optimization over Orthonormal Manifolds for Machine Learning and Statistical Inference

Optimization over the Stiefel manifold $\mathrm{St}(p,d)$, the set of $p \times d$ column-orthonormal matrices, is fundamental in statistics, machine learning, and scientific computing, yet remains challenging in the presence of non-convex, non-smooth, or black-box objectives. Existing methods largely rely on either convex relaxations or gradient-based Riemannian optimization, limiting applicability in derivative-free and highly multimodal settings. We propose \textsc{BOOOM} (Black-box Optimization Over Orthonormal Manifolds), a general-purpose framework for loss-function-agnostic optimization on $\mathrm{St}(p,d)$. The key idea is a global Givens rotation-based parametrization that maps the manifold to an unconstrained Euclidean angle space while preserving feasibility exactly. Building on this representation, BOOOM employs a structured, parallelizable, derivative-free search based on Recursive Modified Pattern Search, enabling systematic exploration through plane-wise rotations without requiring gradient information and facilitating escape from poor local optima. We establish a unified theoretical framework showing equivalence between angle-space and manifold optimization, transfer of stationarity, and global convergence in probability under mild conditions. Empirical results across diverse problems, including heterogeneous quadratic optimization, low-rank and sparse matrix decomposition, independent component analysis, and orthogonal joint diagonalization, among other widely studied settings, demonstrate strong performance relative to state-of-the-art methods, particularly in non-smooth and highly multimodal regimes. We further illustrate its practical utility through a novel supervised PCA formulation applied to metabolomics data in colorectal cancer.

math.OC↗

arXiv2026

Bayesian Global-Local Shrinkage with Univariate Guidance for Ultra-High-Dimensional Regression

We propose Bayesian Univariate-Guided Sparse Regression (BUGS), a novel global-local shrinkage framework that incorporates marginal association information directly into the prior through a continuous modulation of shrinkage. Unlike existing approaches that treat predictors symmetrically or rely on post hoc screening, BUGS embeds univariate guidance within the nonlinear variance structure of a regularized horseshoe prior, inducing adaptive shrinkage that enhances signal-noise separation. We establish theoretical guarantees including prior concentration, posterior contraction, and guidance-induced shrinkage separation, while demonstrating robustness under uninformative guidance. To enable scalability in ultra-high dimensions, we develop BUGS-Active, an active-set MCMC approximation that restricts local updates to a data-adaptive subset A_n, reducing per-iteration complexity from O(p) to O(|A_n|) while preserving key theoretical properties such as sure screening and contraction. Empirically, the proposed framework achieves strong signal recovery together with substantially improved control of false discovery rates relative to existing methods. BUGS-Active scales to dimensions up to p = 1,000,000, and is applied to a DNA methylation study with n=1051 subjects and approximately 850,000 CpG sites, yielding accurate prediction and interpretable sparse selection. These results establish marginally guided shrinkage as a powerful and scalable paradigm for high-dimensional Bayesian inference.

stat.ME↗

arXiv2026

BLOC: A Global Optimization Framework for Sparse Covariance Estimation with Non-Convex Penalties

We introduce BLOC (Black-box Optimization over Correlation matrices), a general framework for sparse covariance estimation with non-convex penalties. BLOC operates on the manifold of correlation matrices and reparameterizes it via an angular Cholesky mapping, transforming the positive-definite, unit-diagonal constraint into an unconstrained search over a Euclidean hyperrectangle. This enables gradient-free global optimization of diverse objectives, including non-differentiable or black-box losses, using a pattern search routine with adaptive coordinate polling, run-wise restarts to escape local minima, and leveraging up to $d(d-1)$ parallel threads when optimizing a $d$-dimensional correlation matrix. The method is penalty-agnostic and ensures that every iterate is a valid correlation matrix, from which covariance estimates are obtained. We establish convergence guarantees, including stationarity, probabilistic escape from poor local minima, and sublinear rates under smooth convex losses. From a statistical perspective, we prove consistency, convergence rates, and sparsistency for penalized correlation estimators under general conditions, extending sparse covariance theory beyond the Gaussian setting. Empirically, BLOC with nonconvex penalties such as SCAD and MCP outperforms leading estimators in both low- and high-dimensional regimes, achieving lower estimation error and improved sparsity recovery. A parallel implementation enhances scalability, and a proteomic network application demonstrates robust, positive-definite sparse covariance estimation.

stat.ME↗

arXiv2025

Deciphering the explosion mechanism of Type Ia SNe using their remnants II: a deep dive into double detonations with SNR 0509-67.5

Type Ia supernovae (SNe) occur when a white dwarf (WD) explodes via runaway thermonuclear burning. Till date, major uncertainties remain regarding the nature of the explosion mechanism and its observable signatures. In this work, we study how the double detonation explosion mechanism, or a helium shell detonation in a sub-Chandrasekhar WD followed by a core detonation, shapes supernova remnants (SNRs) and encodes information about the WD progenitor. We evolve a suite of double-detonation SN models to the remnant phase, up to several centuries after explosion, and measure the characteristic sizes of substructures formed in the SNR due to turbulent mixing. By comparing our models to high-resolution optical observations of the young Type Ia SNR 0509-67.5, we find that the size distribution of its small-scale substructures is consistent with a double detonation explosion mechanism and further places constraints on the carbon-oxygen core mass and helium shell mass of the WD progenitor. The observed sizes of iron-dominated and sulfur-dominated substructures in SNR 0509-67.5 indicate a progenitor core mass and a shell mass of 1 solar mass and greater than 0.05 solar mass, respectively.

astro-ph.HE↗

arXiv2025

GLASD: A Loss-Function-Agnostic Global Optimizer for Robust Correlation Estimation under Data Contamination and Heavy Tails

Robust correlation estimation is essential in high-dimensional settings, particularly when data are contaminated by outliers or exhibit heavy-tailed behavior. Many robust loss functions of practical interest-such as those involving truncation or redescending M-estimators-lead to objective functions that are inherently non-convex and non-differentiable. Traditional methods typically focus on a single loss function tailored to a specific contamination model and develop custom algorithms tightly coupled with that loss, limiting generality and adaptability. We introduce GLASD (Global Adaptive Stochastic Descent), a general-purpose black-box optimization algorithm designed to operate over the manifold of positive definite correlation matrices. Unlike conventional solvers, GLASD requires no gradient information and imposes no assumptions of convexity or smoothness, making it ideally suited for optimizing a wide class of loss functions-including non-convex, non-differentiable, or discontinuous objectives. This flexibility allows GLASD to serve as a unified framework for robust estimation under arbitrary user-defined criteria. We demonstrate its effectiveness through extensive simulations involving contaminated and heavy-tailed distributions, as well as a real-data application to breast cancer proteomic network inference, where GLASD successfully identifies biologically plausible interactions despite the presence of outliers. The proposed method is scalable, constraint-aware, and available as open-source software at GitHub.

stat.AP↗

arXiv2025

pared: Model selection using multi-objective optimization

Motivation: Model selection is a ubiquitous challenge in statistics. For penalized models, model selection typically entails tuning hyperparameters to maximize a measure of fit or minimize out-of-sample prediction error. However, these criteria fail to reflect other desirable characteristics, such as model sparsity, interpretability, or smoothness. Results: We present the R package pared to enable the use of multi-objective optimization for model selection. Our approach entails the use of Gaussian process-based optimization to efficiently identify solutions that represent desirable trade-offs. Our implementation includes popular models with multiple objectives including the elastic net, fused lasso, fused graphical lasso, and group graphical lasso. Our R package generates interactive graphics that allow the user to identify hyperparameter values that result in fitted models which lie on the Pareto frontier. Availability: We provide the R package pared and vignettes illustrating its application to both simulated and real data at https://github.com/priyamdas2/pared.

stat.ME↗

arXiv2024

B-MASTER: Scalable Bayesian Multivariate Regression for Master Predictor Discovery in Colorectal Cancer Microbiome-Metabolite Profiles

Motivation: The gut microbiome shapes cancer therapy response through its influence on host metabolism. While prior studies examine pairwise associations between individual genera and metabolites, there is limited methodology for identifying microbial genera that systematically regulate the overall metabolome. Scalable statistical tools are needed to uncover such system-level 'master predictors' in high-dimensional microbiome-metabolome data. Results: We introduce B-MASTER, a scalable Bayesian multivariate regression framework combining L1 sparsity and L2 group shrinkage to identify essential cross-metabolite regulators. A Gibbs sampler enables near-linear computational scaling, supporting models with millions of parameters. The method is supported by theoretical guarantees, including posterior contraction and selection consistency. Analysis of colorectal cancer microbiome-metabolome data reveals key microbial genera that govern global and cancer-associated metabolite patterns, highlighting system-level regulatory structure. Availability: The B-MASTER code, including demonstration scripts, is available at https://github.com/priyamdas2/B-MASTER. An archived snapshot of the code corresponding to this manuscript is available on Zenodo with DOI: 10.5281/zenodo.20484958.

stat.ME↗

arXiv2024

SMART-MC: Characterizing the Dynamics of Multiple Sclerosis Therapy Transitions Using a Covariate-Based Markov Model

Treatment switching is a common occurrence in the management of Multiple Sclerosis (MS), where patients transition across various disease-modifying therapies (DMTs) due to heterogeneous treatment responses, differences in disease progression, patient characteristics, and therapy-associated adverse effects. To investigate how patient-level covariates influence the likelihood of treatment transitions among DMTs, we adopt a Markovian framework, Sparse Matrix Estimation with Covariate-Based Transitions in Markov Chain Modeling (SMART-MC), in which the transition probabilities are modeled as functions of these covariates. Modeling real-world treatment transitions under this framework presents several challenges, including ensuring parameter identifiability and handling sparse transitions without overfitting. To address identifiability, we constrain each transition-specific covariate coefficient vectors to have a fixed L2 norm. Furthermore, our method automatically estimates transition probabilities for sparsely observed transitions as constants and enforces zero transition probabilities for transitions that are empirically unobserved. This approach mitigates the need for additional model complexity to handle sparsity while maintaining interpretability and efficiency. To optimize the multi-modal likelihood function, we develop a scalable, parallelized global optimization routine, which is validated through benchmark comparisons and supported by key theoretical properties. Our analysis uncovers meaningful patterns in DMT transitions, revealing variations across MS patient subgroups defined by age, race, and other clinical factors.

stat.ME↗

arXiv2023

Revisiting the two-sample location shift model with a log-concavity assumption

In this paper, we consider the two-sample location shift model, a classic semiparametric model introduced by Stein (1956). This model is known for its adaptive nature, enabling nonparametric estimation with full parametric efficiency. Existing nonparametric estimators of the location shift often depend on external tuning parameters, which restricts their practical applicability (Van der Vaart and Wellner, 2021). We demonstrate that introducing an additional assumption of log-concavity on the underlying density can alleviate the need for tuning parameters. We propose a one step estimator for location shift estimation, utilizing log-concave density estimation techniques to facilitate tuning-free estimation of the efficient influence function. While we employ a truncated version of the one step estimator for theoretical adaptivity, our simulations indicate that the one step estimators perform best with zero truncation, eliminating the need for tuning during practical implementation.

math.ST↗

arXiv2023

Black-box optimization on hyper-rectangle using Recursive Modified Pattern Search and application to ROC-based Classification Problem

In statistics, it is common to encounter multi-modal and non-smooth likelihood (or objective function) maximization problems, where the parameters have known upper and lower bounds. This paper proposes a novel derivative-free global optimization technique that can be used to solve those problems even when the objective function is not known explicitly or its derivatives are difficult or expensive to obtain. The technique is based on the pattern search algorithm, which has been shown to be effective for black-box optimization problems. The proposed algorithm works by iteratively generating new solutions from the current solution. The new solutions are generated by making movements along the coordinate axes of the constrained sample space. Before making a jump from the current solution to a new solution, the objective function is evaluated at several neighborhood points around the current solution. The best solution point is then chosen based on the objective function values at those points. Parallel threading can be used to make the algorithm more scalable. The performance of the proposed method is evaluated by optimizing up to 5000-dimensional multi-modal benchmark functions. The proposed algorithm is shown to be up to 40 and 368 times faster than genetic algorithm (GA) and simulated annealing (SA), respectively. The proposed method is also used to estimate the optimal biomarker combination from Alzheimer's disease data by maximizing the empirical estimates of the area under the receiver operating characteristic curve (AUC), outperforming the contextual popular alternative, known as step-down algorithm.

math.OC↗

arXiv2022

On-demand continuous-variable quantum entanglement source for integrated circuits

Integration of devices generating nonclassical states~(such as entanglement) into photonic circuits is one of the major goals in achieving integrated quantum circuits~(IQCs). This is demonstrated successfully in recent decades. Controlling the nonclassicality generation in these micron-scale devices is also crucial for the robust operation of the IQCs. Here, we propose a micron-scale quantum entanglement device whose nonlinearity (so the generated nonclassicality) can be tuned by several orders of magnitude via an \textit{applied voltage} without altering the linear response. Quantum emitters~(QEs), whose level-spacing can be tuned by voltage, are embedded into the hotspot of a metal nanostructure~(MNS). QE-MNS coupling introduces a Fano resonance in the ``nonlinear response''. Nonlinearity, already enhanced extremely due to localization, can be controlled by the QEs' level-spacing. Nonlinearity can either be suppressed (also when the probe is on the device) or be further enhanced by several orders. Fano resonance takes place in a relatively narrow frequency window so that $\sim$meV voltage-tunability for QEs becomes sufficient for a \textit{continuous} turning on/off of the nonclassicality. This provides as much as 5 orders of magnitude modulation depths.

physics.optics↗

arXiv2020

Formation of Solitonic Bound State via Light-Matter Interaction

Exchange of energy by means of light-matter interaction provides a new dimension to various nonlinear dynamical systems. Here, the effects of light-matter interaction are investigated for a situation, where two counter-propagating, orthogonally polarized laser pulses are incident on the atomic condensate. It's observed that a localized laser pulse profile can induce localized modes in Bose-Einstein condensate. A stability analysis performed using Vakhitov-Kolokolov-like criterion has established that these localized modes are stable, when the atom-atom interaction is repulsive. The cooperative effects of light-matter interactions and atom-atom interactions on the Lieb-mode have been studied in the stable region through atomic dispersion, revealing the signature of bound state formation when the optical potential is Pöschl-Teller type. The energy diagram also indicates a continuous transfer of energy from the laser pulses to the atoms as the light-matter interaction changes its sign.

cond-mat.quant-gas↗

arXiv2020

On Second order correctness of Bootstrap in Logistic Regression

In the fields of clinical trials, biomedical surveys, marketing, banking, with dichotomous response variable, the logistic regression is considered as an alternative convenient approach to linear regression. In this paper, we develop a novel bootstrap technique based on perturbation resampling method for approximating the distribution of the maximum likelihood estimator (MLE) of the regression parameter vector. We establish second order correctness of the proposed bootstrap method after proper studentization and smoothing. It is shown that inferences drawn based on the proposed bootstrap method are more accurate compared to that based on asymptotic normality. The main challenge in establishing second order correctness remains in the fact that the response variable being binary, the resulting MLE has a lattice structure. We show the direct bootstrapping approach fails even after studentization. We adopt smoothing technique developed in Lahiri (1993) to ensure that the smoothed studentized version of the MLE has a density. Similar smoothing strategy is employed to the bootstrap version also to achieve second order correct approximation.

math.ST↗