scholarly journals Less Is Better: Unweighted Data Subsampling via Influence Function

2020 ◽  
Vol 34 (04) ◽  
pp. 6340-6347
Author(s):  
Zifeng Wang ◽  
Hong Zhu ◽  
Zhenhua Dong ◽  
Xiuqiang He ◽  
Shao-Lun Huang
Keyword(s):  
Large Scale ◽  
Empirical Distribution ◽  
Data Sets ◽  
Worst Case ◽  
Classification Image ◽  
Probabilistic Sampling ◽  
Out Of Sample ◽  
Sample Test ◽  
Data Volume ◽  
Complex Models

In the time of Big Data, training complex models on large-scale data sets is challenging, making it appealing to reduce data volume for saving computation resources by subsampling. Most previous works in subsampling are weighted methods designed to help the performance of subset-model approach the full-set-model, hence the weighted methods have no chance to acquire a subset-model that is better than the full-set-model. However, we question that how can we achieve better model with less data? In this work, we propose a novel Unweighted Influence Data Subsampling (UIDS) method, and prove that the subset-model acquired through our method can outperform the full-set-model. Besides, we show that overly confident on a given test set for sampling is common in Influence-based subsampling methods, which can eventually cause our subset-model's failure in out-of-sample test. To mitigate it, we develop a probabilistic sampling scheme to control the worst-case risk over all distributions close to the empirical distribution. The experiment results demonstrate our methods superiority over existed subsampling methods in diverse tasks, such as text classification, image classification, click-through prediction, etc.

scholarly journals Predicting the Replicability of Social Science Lab Experiments

2019 ◽  
Author(s):  
Adam Altmejd ◽  
Anna Dreber ◽  
Eskil Forsell ◽  
Teck Hua Ho ◽  
Juergen Huber ◽  
...  
Keyword(s):  
Effect Size ◽  
Large Scale ◽  
Relative Effect ◽  
New Findings ◽  
Psychology And Economics ◽  
Out Of Sample ◽  
Sample Test ◽  
Successful Replication ◽  
Basic Features ◽  
Main Effects

We measure how accurately replication of experimental results can be predicted by a black-box statistical model. With data from four large- scale replication projects in experimental psychology and economics, and techniques from machine learning, we train a predictive model and study which variables drive predictable replication.The model predicts binary replication with a cross validated accuracy rate of 70% (AUC of 0.79) and relative effect size with a Spearman ρ of 0.38. The accuracy level is similar to the market-aggregated beliefs of peer scientists (Camerer et al., 2016; Dreber et al., 2015). The predictive power is validated in a pre-registered out of sample test of the outcome of Camerer et al. (2018b), where 71% (AUC of 0.73) of replications are predicted correctly and effect size correlations amount to ρ = 0.25.Basic features such as the sample and effect sizes in original papers, and whether reported effects are single-variable main effects or two- variable interactions, are predictive of successful replication. The models presented in this paper are simple tools to produce cheap, prognostic replicability metrics. These models could be useful in institutionalizing the process of evaluation of new findings and guiding resources to those direct replications that are likely to be most informative.

scholarly journals AstroCatR: a mechanism and tool for efficient time series reconstruction of large-scale astronomical catalogues

2020 ◽  
Vol 496 (1) ◽  
pp. 629-637
Author(s):  
Ce Yu ◽  
Kun Li ◽  
Shanjiang Tang ◽  
Chao Sun ◽  
Bin Ma ◽  
...  
Keyword(s):  
Time Series ◽  
High Performance ◽  
Large Scale ◽  
Extrasolar Planets ◽  
Time Series Data ◽  
Series Data ◽  
Data Sets ◽  
Observation Data ◽  
Data Volume ◽  
And Performance

ABSTRACT Time series data of celestial objects are commonly used to study valuable and unexpected objects such as extrasolar planets and supernova in time domain astronomy. Due to the rapid growth of data volume, traditional manual methods are becoming extremely hard and infeasible for continuously analysing accumulated observation data. To meet such demands, we designed and implemented a special tool named AstroCatR that can efficiently and flexibly reconstruct time series data from large-scale astronomical catalogues. AstroCatR can load original catalogue data from Flexible Image Transport System (FITS) files or data bases, match each item to determine which object it belongs to, and finally produce time series data sets. To support the high-performance parallel processing of large-scale data sets, AstroCatR uses the extract-transform-load (ETL) pre-processing module to create sky zone files and balance the workload. The matching module uses the overlapped indexing method and an in-memory reference table to improve accuracy and performance. The output of AstroCatR can be stored in CSV files or be transformed other into formats as needed. Simultaneously, the module-based software architecture ensures the flexibility and scalability of AstroCatR. We evaluated AstroCatR with actual observation data from The three Antarctic Survey Telescopes (AST3). The experiments demonstrate that AstroCatR can efficiently and flexibly reconstruct all time series data by setting relevant parameters and configuration files. Furthermore, the tool is approximately 3× faster than methods using relational data base management systems at matching massive catalogues.

CMIP model evaluation with the ESMValTool v2.0

2020 ◽  
Author(s):  
Axel Lauer ◽  
Fernando Iglesias-Suarez ◽  
Veronika Eyring ◽  
the ESMValTool development team
Keyword(s):  
Model Evaluation ◽  
Large Scale ◽  
Performance Metrics ◽  
Comprehensive Evaluation ◽  
Coupled Model ◽  
Data Sets ◽  
Evaluation Tool ◽  
Emergent Constraints ◽  
Data Volume ◽  
And Performance

<p>The Earth System Model Evaluation Tool (ESMValTool) has been developed with the aim of taking model evaluation to the next level by facilitating analysis of many different ESM components, providing well-documented source code and scientific background of implemented diagnostics and metrics and allowing for traceability and reproducibility of results (provenance). This has been made possible by a lively and growing development community continuously improving the tool supported by multiple national and European projects. The latest version (2.0) of the ESMValTool has been developed as a large community effort to specifically target the increased data volume of the Coupled Model Intercomparison Project Phase 6 (CMIP6) and the related challenges posed by analysis and evaluation of output from multiple high-resolution and complex ESMs. For this, the core functionalities have been completely rewritten in order to take advantage of state-of-the-art computational libraries and methods to allow for efficient and user-friendly data processing. Common operations on the input data such as regridding or computation of multi-model statistics are now centralized in a highly optimized preprocessor written in Python. The diagnostic part of the ESMValTool includes a large collection of standard recipes for reproducing peer-reviewed analyses of many variables across atmosphere, ocean, and land domains, with diagnostics and performance metrics focusing on the mean-state, trends, variability and important processes, phenomena, as well as emergent constraints. While most of the diagnostics use observational data sets (in particular satellite and ground-based observations) or reanalysis products for model evaluation some are also based on model-to-model comparisons. This presentation introduces the diagnostics newly implemented into ESMValTool v2.0 including an extended set of large-scale diagnostics for quasi-operational and comprehensive evaluation of ESMs, new diagnostics for extreme events, regional model and impact evaluation and analysis of ESMs, as well as diagnostics for emergent constraints and analysis of future projections from ESMs. The new diagnostics are illustrated with examples using results from the well-established CMIP5 and the newly available CMIP6 data sets.</p>

scholarly journals Polynomial-Time Algorithms for Multiple-Arm Identification with Full-Bandit Feedback

2020 ◽  
Vol 32 (9) ◽  
pp. 1733-1773
Author(s):  
Yuko Kuroki ◽  
Liyuan Xu ◽  
Atsushi Miyauchi ◽  
Junya Honda ◽  
Masashi Sugiyama
Keyword(s):  
Approximation Algorithm ◽  
Polynomial Time ◽  
Large Scale ◽  
Computation Time ◽  
Data Sets ◽  
Sample Complexity ◽  
Worst Case ◽  
Large Scale Data ◽  
Polynomial Time Approximation Algorithm ◽  
Noisy Observation

We study the problem of stochastic multiple-arm identification, where an agent sequentially explores a size-[Formula: see text] subset of arms (also known as a super arm) from given [Formula: see text] arms and tries to identify the best super arm. Most work so far has considered the semi-bandit setting, where the agent can observe the reward of each pulled arm or assumed each arm can be queried at each round. However, in real-world applications, it is costly or sometimes impossible to observe a reward of individual arms. In this study, we tackle the full-bandit setting, where only a noisy observation of the total sum of a super arm is given at each pull. Although our problem can be regarded as an instance of the best arm identification in linear bandits, a naive approach based on linear bandits is computationally infeasible since the number of super arms [Formula: see text] is exponential. To cope with this problem, we first design a polynomial-time approximation algorithm for a 0-1 quadratic programming problem arising in confidence ellipsoid maximization. Based on our approximation algorithm, we propose a bandit algorithm whose computation time is [Formula: see text](log [Formula: see text]), thereby achieving an exponential speedup over linear bandit algorithms. We provide a sample complexity upper bound that is still worst-case optimal. Finally, we conduct experiments on large-scale data sets with more than 10[Formula: see text] super arms, demonstrating the superiority of our algorithms in terms of both the computation time and the sample complexity.

scholarly journals Galaxy spin direction distribution in HST and SDSS show similar large-scale asymmetry

2020 ◽  
Vol 37 ◽  
Author(s):  
Lior Shamir
Keyword(s):  
Large Scale ◽  
Spiral Galaxies ◽  
Hubble Space Telescope ◽  
Gravitational Interaction ◽  
Large Data ◽  
Sloan Digital Sky Survey ◽  
Data Sets ◽  
Dipole Axis ◽  
Data Set ◽  
The Asymmetry

Abstract Several recent observations using large data sets of galaxies showed non-random distribution of the spin directions of spiral galaxies, even when the galaxies are too far from each other to have gravitational interaction. Here, a data set of $\sim8.7\cdot10^3$ spiral galaxies imaged by Hubble Space Telescope (HST) is used to test and profile a possible asymmetry between galaxy spin directions. The asymmetry between galaxies with opposite spin directions is compared to the asymmetry of galaxies from the Sloan Digital Sky Survey. The two data sets contain different galaxies at different redshift ranges, and each data set was annotated using a different annotation method. The results show that both data sets show a similar asymmetry in the COSMOS field, which is covered by both telescopes. Fitting the asymmetry of the galaxies to cosine dependence shows a dipole axis with probabilities of $\sim2.8\sigma$ and $\sim7.38\sigma$ in HST and SDSS, respectively. The most likely dipole axis identified in the HST galaxies is at $(\alpha=78^{\rm o},\delta=47^{\rm o})$ and is well within the $1\sigma$ error range compared to the location of the most likely dipole axis in the SDSS galaxies with $z>0.15$ , identified at $(\alpha=71^{\rm o},\delta=61^{\rm o})$ .

scholarly journals Fast and robust identity-by-descent inference with the templated positional Burrows-Wheeler transform

2020 ◽  
Author(s):  
William A Freyman ◽  
Kimberly F McManus ◽  
Suyash S Shringarpure ◽  
Ethan M Jewett ◽  
Katarzyna Bryc ◽  
...  
Keyword(s):  
Isolation By Distance ◽  
False Negative ◽  
Segment Length ◽  
Data Sets ◽  
Haplotype Sharing ◽  
Binary File ◽  
Inference Algorithms ◽  
Out Of Sample ◽  
Massive Scale ◽  
Burrows Wheeler Transform

Abstract Estimating the genomic location and length of identical-by-descent (IBD) segments among individuals is a crucial step in many genetic analyses. However, the exponential growth in the size of biobank and direct-to-consumer (DTC) genetic data sets makes accurate IBD inference a significant computational challenge. Here we present the templated positional Burrows-Wheeler transform (TPBWT) to make fast IBD estimates robust to genotype and phasing errors. Using haplotype data simulated over pedigrees with realistic genotyping and phasing errors we show that the TPBWT outperforms other state-of-the-art IBD inference algorithms in terms of speed and accuracy. For each phase-aware method, we explore the false positive and false negative rates of inferring IBD by segment length and characterize the types of error commonly found. Our results highlight the fragility of most phased IBD inference methods; the accuracy of IBD estimates can be highly sensitive to the quality of haplotype phasing. Additionally we compare the performance of the TPBWT against a widely used phase-free IBD inference approach that is robust to phasing errors. We introduce both in-sample and out-of-sample TPBWT-based IBD inference algorithms and demonstrate their computational efficiency on massive-scale datasets with millions of samples. Furthermore we describe the binary file format for TPBWT-compressed haplotypes that results in fast and efficient out-of-sample IBD computes against very large cohort panels. Finally, we demonstrate the utility of the TPBWT in a brief empirical analysis exploring geographic patterns of haplotype sharing within Mexico. Hierarchical clustering of IBD shared across regions within Mexico reveals geographically structured haplotype sharing and a strong signal of isolation by distance. Our software implementation of the TPBWT is freely available for non-commercial use in the code repository https://github.com/23andMe/phasedibd.

scholarly journals Accelerating In-Transit Co-Processing for Scientific Simulations Using Region-Based Data-Driven Analysis

Algorithms ◽  
2021 ◽  
Vol 14 (5) ◽  
pp. 154
Author(s):  
Marcus Walldén ◽  
Masao Okita ◽  
Fumihiko Ino ◽  
Dimitris Drikakis ◽  
Ioannis Kokkinakis
Keyword(s):  
Large Scale ◽  
Data Driven ◽  
Data Sets ◽  
Output Constraints ◽  
Data Driven Approach ◽  
Scientific Simulations ◽  
Multiple Metrics ◽  
In Transit ◽  
Multiple Compression ◽  
Large Scale Simulations

Increasing processing capabilities and input/output constraints of supercomputers have increased the use of co-processing approaches, i.e., visualizing and analyzing data sets of simulations on the fly. We present a method that evaluates the importance of different regions of simulation data and a data-driven approach that uses the proposed method to accelerate in-transit co-processing of large-scale simulations. We use the importance metrics to simultaneously employ multiple compression methods on different data regions to accelerate the in-transit co-processing. Our approach strives to adaptively compress data on the fly and uses load balancing to counteract memory imbalances. We demonstrate the method’s efficiency through a fluid mechanics application, a Richtmyer–Meshkov instability simulation, showing how to accelerate the in-transit co-processing of simulations. The results show that the proposed method expeditiously can identify regions of interest, even when using multiple metrics. Our approach achieved a speedup of 1.29× in a lossless scenario. The data decompression time was sped up by 2× compared to using a single compression method uniformly.

scholarly journals A Hypothesis Test for the Goodness-of-Fit of the Marginal Distribution of a Time Series with Application to Stablecoin Data

2021 ◽  
Vol 5 (1) ◽  
pp. 10
Author(s):  
Mark Levene
Keyword(s):  
Time Series ◽  
Goodness Of Fit ◽  
Marginal Distribution ◽  
Hypothesis Test ◽  
Data Sets ◽  
Test Statistic ◽  
Sample Test ◽  
Kolmogorov Smirnov ◽  
Heavy Tailed ◽  
Jensen Shannon Divergence

A bootstrap-based hypothesis test of the goodness-of-fit for the marginal distribution of a time series is presented. Two metrics, the empirical survival Jensen–Shannon divergence (ESJS) and the Kolmogorov–Smirnov two-sample test statistic (KS2), are compared on four data sets—three stablecoin time series and a Bitcoin time series. We demonstrate that, after applying first-order differencing, all the data sets fit heavy-tailed α-stable distributions with 1<α<2 at the 95% confidence level. Moreover, ESJS is more powerful than KS2 on these data sets, since the widths of the derived confidence intervals for KS2 are, proportionately, much larger than those of ESJS.

scholarly journals Compartment and hub definitions tune metabolic networks for metabolomic interpretations

GigaScience ◽  
2020 ◽  
Vol 9 (1) ◽  
Author(s):  
T Cameron Waller ◽  
Jordan A Berg ◽  
Alexander Lex ◽  
Brian E Chapman ◽  
Jared Rutter
Keyword(s):  
Large Scale ◽  
Metabolic Networks ◽  
Shortest Paths ◽  
Large Data ◽  
Differential Regulation ◽  
Large Data Sets ◽  
Data Sets ◽  
Human Metabolism ◽  
Experimental Conditions ◽  
Systemic Model

Abstract Background Metabolic networks represent all chemical reactions that occur between molecular metabolites in an organism’s cells. They offer biological context in which to integrate, analyze, and interpret omic measurements, but their large scale and extensive connectivity present unique challenges. While it is practical to simplify these networks by placing constraints on compartments and hubs, it is unclear how these simplifications alter the structure of metabolic networks and the interpretation of metabolomic experiments. Results We curated and adapted the latest systemic model of human metabolism and developed customizable tools to define metabolic networks with and without compartmentalization in subcellular organelles and with or without inclusion of prolific metabolite hubs. Compartmentalization made networks larger, less dense, and more modular, whereas hubs made networks larger, more dense, and less modular. When present, these hubs also dominated shortest paths in the network, yet their exclusion exposed the subtler prominence of other metabolites that are typically more relevant to metabolomic experiments. We applied the non-compartmental network without metabolite hubs in a retrospective, exploratory analysis of metabolomic measurements from 5 studies on human tissues. Network clusters identified individual reactions that might experience differential regulation between experimental conditions, several of which were not apparent in the original publications. Conclusions Exclusion of specific metabolite hubs exposes modularity in both compartmental and non-compartmental metabolic networks, improving detection of relevant clusters in omic measurements. Better computational detection of metabolic network clusters in large data sets has potential to identify differential regulation of individual genes, transcripts, and proteins.

Sign in / Sign up

Export Citation Format

Share Document