arXiv subjects

Abhinav Pandey

Publications and source records attributed to Abhinav Pandey.

10 recordsLinked to original sources

arXiv2026

PVF:Understanding AI Vulnerability Against SDCs

Reliability of AI systems is a fundamental concern for the successful deployment and widespread adoption of AI technologies. Unfortunately, the escalating complexity and heterogeneity of AI hardware systems make them increasingly susceptible to hardware faults, e.g., silent data corruptions (SDC), that can potentially corrupt model parameters. When this occurs during AI inference/servicing, it can potentially lead to incorrect or degraded model output for users, ultimately affecting the quality and reliability of AI services. In light of the escalating threat, it is crucial to address key questions: How vulnerable are AI models to parameter corruptions, and how do different components (such as modules, layers) of the models exhibit varying vulnerabilities to parameter corruptions? To systematically address this question, we propose a novel quantitative metric, Parameter Vulnerability Factor (PVF), inspired by architectural vulnerability factor (AVF) in computer architecture community, aiming to standardize the quantification of AI model vulnerability against parameter corruptions. We define a model parameter's PVF as the probability that a corruption in that particular model parameter will result in an incorrect output. In this paper, we present several use cases on applying PVF to three types of tasks/models during inference -- recommendation (DLRM), vision classification (CNN), and text classification (BERT), while presenting an in-depth vulnerability analysis on DLRM. PVF has been a critical metric used for making key error management design decisions in productionizing Meta's in-house AI chip - MTIA.

cs.CR↗

arXiv2026

Variance-Aware LLM Annotation for Strategy Research: Sources, Diagnostics, and a Protocol for Reliable Measurement

Large language models (LLMs) offer strategy researchers powerful tools for annotating text at scale, but treating LLM-generated labels as deterministic overlooks substantial instability. Grounded in content analysis and generalizability theory, we diagnose five variance sources: construct specification, interface effects, model preferences, output extraction, and system-level aggregation. Empirical demonstrations show that minor design choices-prompt phrasing, model selection-can shift outcomes by 12-85 percentage points. Such variance threatens not only reproducibility but econometric identification: annotation errors correlated with covariates bias parameter estimates regardless of average accuracy. We develop a variance-aware protocol specifying sampling budgets, aggregation rules, and reporting standards, and delineate scope conditions where LLM annotation should not be used. These contributions transform LLM-based annotation from ad hoc practice into auditable measurement infrastructure.

cs.CY↗

arXiv2025

Poisson Hierarchical Indian Buffet Processes-With Indications for Microbiome Species Sampling Models

We introduce the Poisson Hierarchical Indian Buffet Process (PHIBP), a new class of species sampling models designed to address the challenges of complex, sparse count data by facilitating information sharing across and within groups. Our theoretical developments enable a tractable Bayesian nonparametric framework with machine learning elements, accommodating a potentially infinite number of species (taxa) whose parameters are learned from data. Focusing on microbiome analysis, we address key gaps by providing a flexible multivariate count model that accounts for overdispersion and robustly handles diverse data types (OTUs, ASVs). We introduce novel parameters reflecting species abundance and diversity. The model borrows strength across groups while explicitly distinguishing between technical and biological zeros to interpret sparse co-occurrence patterns. This results in a framework with tractable posterior inference, exact generative sampling, and a principled solution to the unseen species problem. We describe extensions where domain experts can incorporate knowledge through covariates and structured priors, with potential for strain-level analysis. While motivated by ecology, our work provides a broadly applicable methodology for hierarchical count modeling in genetics, commerce, and text analysis, and has significant implications for the broader theory of species sampling models arising in probability and statistics.

stat.ML↗

arXiv2024

The Llama 3 Herd of Models

Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support multilinguality, coding, reasoning, and tool usage. Our largest model is a dense Transformer with 405B parameters and a context window of up to 128K tokens. This paper presents an extensive empirical evaluation of Llama 3. We find that Llama 3 delivers comparable quality to leading language models such as GPT-4 on a plethora of tasks. We publicly release Llama 3, including pre-trained and post-trained versions of the 405B parameter language model and our Llama Guard 3 model for input and output safety. The paper also presents the results of experiments in which we integrate image, video, and speech capabilities into Llama 3 via a compositional approach. We observe this approach performs competitively with the state-of-the-art on image, video, and speech recognition tasks. The resulting models are not yet being broadly released as they are still under development.

cs.AI↗

arXiv2024

Bayesian Analysis of Generalized Hierarchical Indian Buffet Processes for Within and Across Group Sharing of Latent Features

Bayesian nonparametric hierarchical priors are highly effective in providing flexible models for latent data structures exhibiting sharing of information within and across groups. In this work, we focus on latent feature allocation models, where the data structures correspond to multi-sets or unbounded sparse matrices, which we refer to as generalized hierarchical Indian Buffet processes (HIBP). These are based on hierarchical versions of generalized spike and slab Indian Buffet processes (IBP), where the fundamental development in this regard is the Bernoulli-based HIBP, devised by Thibaux-Jordan (2007), as a hierarchical extension of the IBP devised by Griffiths-Ghahramani (2005). With a focus on Bayesian inference, we provide novel explicit descriptions of the joint, marginal, and posterior distributions of the HIBP, significantly advancing our understanding of these processes. Our results allow for exact sampling for the otherwise complex joint marginal distributions. We provide a general characterization of their posterior distributions as well as highlight bottlenecks for practical implementation. Our main focus then shifts to specific tractable results for the remarkable case of Poisson HIBP, which correspond to generalizations of mixed Poisson random count models arising in genetics, imaging, topic modeling, random occupancy, and species sampling models. We show they also have important relations to Bayesian nonparametric latent class models appearing in the literature. Furthermore, we show that all general HIBP may be coupled to Poisson HIBP, allowing for further analysis of such processes.

math.ST↗

arXiv2024

Modelling financial volume curves with hierarchical Poisson processes

Modeling the trading volume curves of financial instruments throughout the day is of key interest in financial trading applications. Predictions of these so-called volume profiles guide trade execution strategies, for example, a common strategy is to trade a desired quantity across many orders in line with the expected volume curve throughout the day so as not to impact the price of the instrument. The volume curves (for each day) are naturally grouped by stock and can be further gathered into higher-level groupings, such as by industry. In order to model such admixtures of volume curves, we introduce a hierarchical Poisson process model for the intensity functions of admixtures of inhomogenous Poisson processes, which represent the trading times of the stock throughout the day. The model is based on the hierarchical Dirichlet process, and an efficient Markov Chain Monte Carlo (MCMC) algorithm is derived following the slice sampling framework for Bayesian nonparametric mixture models. We demonstrate the method on datasets of different stocks from the Trade and Quote repository maintained by Wharton Research Data Services, including the most liquid stock on the NASDAQ stock exchange, Apple, demonstrating the scalability of the approach.

q-fin.ST↗

arXiv2023

PyPose v0.6: The Imperative Programming Interface for Robotics

PyPose is an open-source library for robot learning. It combines a learning-based approach with physics-based optimization, which enables seamless end-to-end robot learning. It has been used in many tasks due to its meticulously designed application programming interface (API) and efficient implementation. From its initial launch in early 2022, PyPose has experienced significant enhancements, incorporating a wide variety of new features into its platform. To satisfy the growing demand for understanding and utilizing the library and reduce the learning curve of new users, we present the fundamental design principle of the imperative programming interface, and showcase the flexible usage of diverse functionalities and modules using an extremely simple Dubins car example. We also demonstrate that the PyPose can be easily used to navigate a real quadruped robot with a few lines of code.

cs.RO↗

arXiv2023

PyPose: A Library for Robot Learning with Physics-based Optimization

Deep learning has had remarkable success in robotic perception, but its data-centric nature suffers when it comes to generalizing to ever-changing environments. By contrast, physics-based optimization generalizes better, but it does not perform as well in complicated tasks due to the lack of high-level semantic information and reliance on manual parametric tuning. To take advantage of these two complementary worlds, we present PyPose: a robotics-oriented, PyTorch-based library that combines deep perceptual models with physics-based optimization. PyPose's architecture is tidy and well-organized, it has an imperative style interface and is efficient and user-friendly, making it easy to integrate into real-world robotic applications. Besides, it supports parallel computing of any order gradients of Lie groups and Lie algebras and $2^{\text{nd}}$-order optimizers, such as trust region methods. Experiments show that PyPose achieves more than $10\times$ speedup in computation compared to the state-of-the-art libraries. To boost future research, we provide concrete examples for several fields of robot learning, including SLAM, planning, control, and inertial navigation.

cs.RO↗

arXiv2021

Posterior distributions for Hierarchical Spike and Slab Indian Buffet processes

Bayesian nonparametric hierarchical priors are highly effective in providing flexible models for latent data structures exhibiting sharing of information between and across groups. Most prominent is the Hierarchical Dirichlet Process (HDP), and its subsequent variants, which model latent clustering between and across groups. The HDP, may be viewed as a more flexible extension of Latent Dirichlet Allocation models (LDA), and has been applied to, for example, topic modelling, natural language processing, and datasets arising in health-care. We focus on analogous latent feature allocation models, where the data structures correspond to multisets or unbounded sparse matrices. The fundamental development in this regard is the Hierarchical Indian Buffet process (HIBP), which utilizes a hierarchy of Beta processes over J groups, where each group generates binary random matrices, reflecting within group sharing of features, according to beta-Bernoulli IBP priors. To encompass HIBP versions of non-Bernoulli extensions of the IBP, we introduce hierarchical versions of general spike and slab IBP. We provide explicit novel descriptions of the marginal, posterior and predictive distributions of the HIBP and its generalizations which allow for exact sampling and simpler practical implementation. We highlight common structural properties of these processes and establish relationships to existing IBP type and related models arising in the literature. Examples of potential applications may involve topic models, Poisson factorization models, random count matrix priors and neural network models

math.ST↗

arXiv2010

Cloud Computing: Exploring the scope

Cloud computing refers to a paradigm shift to overall IT solutions while raising the accessibility, scalability and effectiveness through its enabling technologies. However, migrated cloud platforms and services cost benefits as well as performances are neither clear nor summarized. Globalization and the recessionary economic times have not only raised the bar of a better IT delivery models but also have given access to technology enabled services via internet. Cloud computing has vast potential in terms of lean Retail methodologies that can minimize the operational cost by using the third party based IT capabilities, as a service. It will not only increase the ROI but will also help in lowering the total cost of ownership. In this paper we have tried to compare the cloud computing cost benefits with the actual premise cost which an organization incurs normally. However, in spite of the cost benefits, many IT professional believe that the latest model i.e. "cloud computing" has risks and security concerns. This report demonstrates how to answer the following questions: (1) Idea behind cloud computing. (2) Monetary cost benefits of using cloud with respect to traditional premise computing. (3) What are the various security issues? We have tried to find out the cost benefit by comparing the Microsoft Azure cloud cost with the prevalent premise cost.

cs.DC↗