Searcharxiv⌕ Search

arXiv subjects

Peter Kraft

Publications and source records attributed to Peter Kraft.

13 recordsLinked to original sources
arXiv2024

FastImpute: A Baseline for Open-source, Reference-Free Genotype Imputation Methods -- A Case Study in PRS313

Genotype imputation enhances genetic data by predicting missing SNPs using reference haplotype information. Traditional methods leverage linkage disequilibrium (LD) to infer untyped SNP genotypes, relying on the similarity of LD structures between genotyped target sets and fully sequenced reference panels. Recently, reference-free deep learning-based methods have emerged, offering a promising alternative by predicting missing genotypes without external databases, thereby enhancing privacy and accessibility. However, these methods often produce models with tens of millions of parameters, leading to challenges such as the need for substantial computational resources to train and inefficiency for client-sided deployment. Our study addresses these limitations by introducing a baseline for a novel genotype imputation pipeline that supports client-sided imputation models generalizable across any genotyping chip and genomic region. This approach enhances patient privacy by performing imputation directly on edge devices. As a case study, we focus on PRS313, a polygenic risk score comprising 313 SNPs used for breast cancer risk prediction. Utilizing consumer genetic panels such as 23andMe, our model democratizes access to personalized genetic insights by allowing 23andMe users to obtain their PRS313 score. We demonstrate that simple linear regression can significantly improve the accuracy of PRS313 scores when calculated using SNPs imputed from consumer gene panels, such as 23andMe. Our linear regression model achieved an R^2 of 0.86, compared to 0.33 without imputation and 0.28 with simple imputation (substituting missing SNPs with the minor allele frequency). These findings suggest that popular SNP analysis libraries could benefit from integrating linear regression models for genotype imputation, providing a viable and light-weight alternative to reference based imputation.

q-bio.GN↗
arXiv2024

ACORN: Performant and Predicate-Agnostic Search Over Vector Embeddings and Structured Data

Applications increasingly leverage mixed-modality data, and must jointly search over vector data, such as embedded images, text and video, as well as structured data, such as attributes and keywords. Proposed methods for this hybrid search setting either suffer from poor performance or support a severely restricted set of search predicates (e.g., only small sets of equality predicates), making them impractical for many applications. To address this, we present ACORN, an approach for performant and predicate-agnostic hybrid search. ACORN builds on Hierarchical Navigable Small Worlds (HNSW), a state-of-the-art graph-based approximate nearest neighbor index, and can be implemented efficiently by extending existing HNSW libraries. ACORN introduces the idea of predicate subgraph traversal to emulate a theoretically ideal, but impractical, hybrid search strategy. ACORN's predicate-agnostic construction algorithm is designed to enable this effective search strategy, while supporting a wide array of predicate sets and query semantics. We systematically evaluate ACORN on both prior benchmark datasets, with simple, low-cardinality predicate sets, and complex multi-modal datasets not supported by prior methods. We show that ACORN achieves state-of-the-art performance on all datasets, outperforming prior methods with 2-1,000x higher throughput at a fixed recall.

cs.IR↗
arXiv2023

Apiary: A DBMS-Integrated Transactional Function-as-a-Service Framework

Developers increasingly use function-as-a-service (FaaS) platforms for data-centric applications that perform low-latency and transactional operations on data, such as for microservices or web serving. Unfortunately, existing FaaS platforms support these applications poorly because they physically and logically separate application logic, executed in cloud functions, from data management, done in interactive transactions accessing remote storage. Physical separation harms performance while logical separation complicates efficiently providing transactional guarantees and fault tolerance. This paper introduces Apiary, a novel DBMS-integrated FaaS platform for deploying and composing fault-tolerant transactional functions. Apiary physically co-locates and logically integrates function execution and data management by wrapping a distributed DBMS engine and using it as a unified runtime for function execution, data management, and operational logging, thus providing similar or stronger transactional guarantees as comparable systems while greatly improving performance and observability. To allow developers to write complex stateful programs, we leverage this integration to enable efficient and fault-tolerant function composition, building a frontend for orchestrating workflows of functions with the guarantees that each workflow runs to completion and each function in a workflow executes exactly once. We evaluate Apiary against research and production FaaS platforms and show it outperforms them by 2--68x on microservice workloads by reducing communication overhead.

cs.DB↗
arXiv2022

Transactions Make Debugging Easy

We propose TROD, a novel transaction-oriented framework for debugging modern distributed web applications and online services. Our critical insight is that if applications store all state in databases and only access state transactionally, TROD can use lightweight always-on tracing to track the history of application state changes and data provenance, and then leverage the captured traces and transaction logs to faithfully replay or even test modified code retroactively on any past event. We demonstrate how TROD can simplify programming and debugging in production applications, list several research challenges and directions, and encourage the database and systems communities to drastically rethink the synergy between the way people develop and debug applications.

cs.DB↗
arXiv2022

Machine Learning with DBOS

We recently proposed a new cluster operating system stack, DBOS, centered on a DBMS. DBOS enables unique support for ML applications by encapsulating ML code within stored procedures, centralizing ancillary ML data, providing security built into the underlying DBMS, co-locating ML code and data, and tracking data and workflow provenance. Here we demonstrate a subset of these benefits around two ML applications. We first show that image classification and object detection models using GPUs can be served as DBOS stored procedures with performance competitive to existing systems. We then present a 1D CNN trained to detect anomalies in HTTP requests on DBOS-backed web services, achieving SOTA results. We use this model to develop an interactive anomaly detection system and evaluate it through qualitative user feedback, demonstrating its usefulness as a proof of concept for future work to develop learned real-time security services on top of DBOS.

cs.CR↗
arXiv2021

Solving Large-Scale Granular Resource Allocation Problems Efficiently with POP

Resource allocation problems in many computer systems can be formulated as mathematical optimization problems. However, finding exact solutions to these problems using off-the-shelf solvers is often intractable for large problem sizes with tight SLAs, leading system designers to rely on cheap, heuristic algorithms. We observe, however, that many allocation problems are granular: they consist of a large number of clients and resources, each client requests a small fraction of the total number of resources, and clients can interchangeably use different resources. For these problems, we propose an alternative approach that reuses the original optimization problem formulation and leads to better allocations than domain-specific heuristics. Our technique, Partitioned Optimization Problems (POP), randomly splits the problem into smaller problems (with a subset of the clients and resources in the system) and coalesces the resulting sub-allocations into a global allocation for all clients. We provide theoretical and empirical evidence as to why random partitioning works well. In our experiments, POP achieves allocations within 1.5% of the optimal with orders-of-magnitude improvements in runtime compared to existing systems for cluster scheduling, traffic engineering, and load balancing.

cs.DC↗
arXiv2021

Don't Give Up on Large Optimization Problems; POP Them!

Resource allocation problems in many computer systems can be formulated as mathematical optimization problems. However, finding exact solutions to these problems using off-the-shelf solvers in an online setting is often intractable for "hyper-scale" system sizes with tight SLAs, leading system designers to rely on cheap, heuristic algorithms. In this work, we explore an alternative approach that reuses the original optimization problem formulation. By splitting the original problem into smaller, more tractable problems for subsets of the system and then coalescing resulting sub-allocations into a global solution, we achieve empirically quasi-optimal (within 1.5%) performance for multiple domains with several orders-of-magnitude improvement in runtime. Deciding how to split a large problem into smaller sub-problems, and how to coalesce split allocations into a unified allocation, needs to be performed carefully in a domain-aware way. We show common principles for splitting problems effectively across a variety of tasks, including cluster scheduling, traffic engineering, and load balancing.

cs.DC↗
arXiv2020

Willump: A Statistically-Aware End-to-end Optimizer for Machine Learning Inference

Systems for ML inference are widely deployed today, but they typically optimize ML inference workloads using techniques designed for conventional data serving workloads and miss critical opportunities to leverage the statistical nature of ML. In this paper, we present Willump, an optimizer for ML inference that introduces two statistically-motivated optimizations targeting ML applications whose performance bottleneck is feature computation. First, Willump automatically cascades feature computation for classification queries: Willump classifies most data inputs using only high-value, low-cost features selected through empirical observations of ML model performance, improving query performance by up to 5x without statistically significant accuracy loss. Second, Willump accurately approximates ML top-K queries, discarding low-scoring inputs with an automatically constructed approximate model and then ranking the remainder with a more powerful model, improving query performance by up to 10x with minimal accuracy loss. Willump automatically tunes these optimizations' parameters to maximize query performance while meeting an accuracy target. Moreover, Willump complements these statistical optimizations with compiler optimizations to automatically generate fast inference code for ML applications. We show that Willump improves the end-to-end performance of real-world ML inference pipelines curated from major data science competitions by up to 16x without statistically significant loss of accuracy.

cs.DB↗
arXiv2018

Automatic Parallelization of Sequential Programs

Prior work on Automatically Scalable Computation (ASC) suggests that it is possible to parallelize sequential computation by building a model of whole-program execution, using that model to predict future computations, and then speculatively executing those future computations. Although that prior work demonstrated scaling, it did not demonstrate speedup, because it ran entirely in emulation. We took this as a challenge to construct a hardware prototype that embodies the ideas of ASC, but works on a broader range of programs and runs natively on hardware. The resulting system is similar in spirit to the original work, but differs in practically every respect. We present an implementation of the ASC architecture that runs natively on x86 hardware and achieves near-linear speedup up to 44-cores (the size of our test platform) for several classes of programs, such as computational kernels, map-style programs, and matrix operations. We observe that programs are either completely predictable, achieving near-perfect predictive accuracy, or totally unpredictable, and therefore not amenable to scaling via ASC-like techniques. We also find that in most cases, speedup is limited only by implementation details: the overhead of our dependency tracking infrastructure and the manipulation of large state spaces. We are able to automatically parallelize programs with linked data structures that are not amenable to other forms of automatic parallelization.

cs.DC↗
arXiv2014

Control Function Assisted IPW Estimation with a Secondary Outcome in Case-Control Studies

Case-control studies are designed towards studying associations between risk factors and a single, primary outcome. Information about additional, secondary outcomes is also collected, but association studies targeting such secondary outcomes should account for the case-control sampling scheme, or otherwise results may be biased. Often, one uses inverse probability weighted (IPW) estimators to estimate population effects in such studies. However, these estimators are inefficient relative to estimators that make additional assumptions about the data generating mechanism. We propose a class of estimators for the effect of risk factors on a secondary outcome in case-control studies, when the mean is modeled using either the identity or the log link. The proposed estimator combines IPW with a mean zero control function that depends explicitly on a model for the primary disease outcome. The efficient estimator in our class of estimators reduces to standard IPW when the model for the primary disease outcome is unrestricted, and is more efficient than standard IPW when the model is either parametric or semiparametric.

stat.ME↗
arXiv2013

Maximizing the Power of Principal Components Analysis of Correlated Phenotypes in Genome-wide Association Studies

Principal Component analysis (PCA) is a useful statistical technique that is commonly used for multivariate analysis of correlated variables. It is usually applied as a dimension reduction method: the top principal components (PCs) explaining most of total variance are tested for association with a predictor of interest, and the remaining PCs are ignored. This strategy has been widely applied in genetic epidemiology, however some of its aspects are not well appreciated in the context of single nucleotide polymorphisms (SNPs) association testing. In this study, we review the theoretical basis of PCA and its behavior when testing for association between a SNP and two correlated traits under various scenarios. We then evaluate with simulations the power of several different PCA-based strategies when analyzing up to 100 correlated traits. We show that contrary to widespread practice that testing the top PCs only can be dramatically underpowered since PCs explaining a low amount of the total phenotypic variance can harbor substantial genetic associations. Furthermore, we demonstrate that PC-based strategies that use all PCs have great potential to detect negatively pleiotropic genetic variants (e.g. variants with opposite effects on positively correlated traits) and genetic variants that are exclusively associated with a single trait, but only achieve a moderate gain in power to detect positive pleiotropic genetic loci. Finally, the genome-wide association study of five correlated coagulation traits in 685 subjects from the MARTHA study confirms these results. The joint analysis of the five PCs from the coagulation traits identified two new candidate SNPs, which were most strongly associated with the 5th PC that explained the smallest amount of phenotypic variance.

stat.ME↗
arXiv2010

Replication in Genome-Wide Association Studies

Replication helps ensure that a genotype-phenotype association observed in a genome-wide association (GWA) study represents a credible association and is not a chance finding or an artifact due to uncontrolled biases. We discuss prerequisites for exact replication, issues of heterogeneity, advantages and disadvantages of different methods of data synthesis across multiple studies, frequentist vs. Bayesian inferences for replication, and challenges that arise from multi-team collaborations. While consistent replication can greatly improve the credibility of a genotype-phenotype association, it may not eliminate spurious associations due to biases shared by many studies. Conversely, lack of replication in well-powered follow-up studies usually invalidates the initially proposed association, although occasionally it may point to differences in linkage disequilibrium or effect modifiers across studies.

stat.ME↗