The growing use of machine learning (ML) has raised concerns that an ML model may reveal private information about an individual who has contributed to the training dataset. To prevent leakage of sensitive data, we consider using differentially- private (DP), synthetic training data instead of real training data to train an ML model. A key desirable property of synthetic data is its ability to preserve the low-order marginals of the original distribution. Our main contribution comprises novel upper and lower bounds on the excess empirical risk of linear models trained on such synthetic data, for continuous and Lipschitz loss functions. We perform extensive experimentation alongside our theoretical results.

The lack of representative, publicly-available cloud services has been a recurring problem in the architecture and systems communities. While open-source benchmarks exist, they do not capture the full complexity of cloud services. Application cloning is a promising way to address this, however, prior work is limited to CPU-/cache-centric, single-node services, operating at user level.

Embedding techniques can be used to represent words using word embedding [1] , images using image-to-vector techniques [2] , [3] and even database queries [4] . As a result, many more real-world objects can be represented by matrices. For example, a matrix can represent a document where each row (i.e., each vector) of the matrix stands for a word in the document. Figure 1 shows the key steps of representing an object (e.g., a document, a video or an audio stream) by a matrix. The intermediate step is to divide the object into small pieces and to convert the small pieces into vectors. The vectors of the object are then put together to form a matrix. These objects represented by matrices require new data management systems to support efficient indexing and retrieval.

Building large AI fleets to support the rapidly growing DL workloads is an active research topic for modern cloud providers. Generating accurate benchmarks plays an essential role in designing the fast-paced software and hardware solutions in this space. Two fundamental challenges to make this scalable are (i) workload representativeness and (ii) the ability to quickly incorporate changes to the fleet into the benchmarks.

DNA methylation plays a crucial role in transcriptional regulation. Reduced representation bisulfite sequencing (RRBS) is a technique of increasing use for analyzing genome-wide methylation profiles. Many computational tools such as Metilene, MethylKit, BiSeq and DMRfinder have been developed to use RRBS data for the detection of the differentially methylated regions (DMRs) potentially involved in epigenetic regulations of gene expression. For DMR detection tools, as for countless other medical applications, P-values and their adjustments are among the most standard reporting statistics used to assess the statistical significance of biological findings. However, P-values are coming under increasing criticism relating to their questionable accuracy and relatively high levels of false positive or negative indications. Here, we propose a method to calculate E-values, as likelihood ratios falling into the null hypothesis over the entire parameter space, for DMR detection in RRBS data. We also provide the R package 'metevalue' as a user-friendly interface to implement E-value calculations into various DMR detection tools. To evaluate the performance of E-values, we generated various RRBS benchmarking datasets using our simulator 'RRBSsim' with eight samples in each experimental group. Our comprehensive benchmarking analyses showed that using E-values not only significantly improved accuracy, area under ROC curve and power, over that of P-values or adjusted P-values, but also reduced false discovery rates and type I errors. In applications using real RRBS data of CRL rats and a clinical trial on low-salt diet, the use of E-values detected biologically more relevant DMRs and also improved the negative association between DNA methylation and gene expression.

With the embedding techniques, many real-world objects can be represented using matrices. For example, a document can be represented by a matrix, where each row of the matrix represents a word. On the other hand, we have witnessed that many applications continuously generate new data represented by matrices and require real-time query answering on the data. These continuously generated matrices need to be well managed for efficient retrieval. In this paper, we propose an index for real-time matrix retrieval. Besides fast query response, the index also supports real-time insertion by exploiting the LSM-tree. Since the index is built for matrices, it consumes much more memory and requires much more time to search than the traditional index for information retrieval. To tackle the challenges, we power our proposed index with precise and fuzzy inverted lists, and propose a series of novel techniques to improve the memory consumption and the search efficiency of the index. The proposed techniques include vector signature, vector residual sorting, hashing based lookup, and dictionary initialization to guarantee the index quality. Comprehensive experimental results show that our proposed index can support real-time search on matrices and is more efficient than the state-of-the-art method.

Cloud applications are increasingly shifting from large monolithic services to complex graphs of loosely-coupled microservices. Despite the advantages of modularity and elasticity microservices offer, they also complicate cluster management and performance debugging, as dependencies between tiers introduce backpressure and cascading QoS violations. Prior work on performance debugging for cloud services either relies on empirical techniques, or uses supervised learning to diagnose the root causes of performance issues, which requires significant application instrumentation, and is difficult to deploy in practice.

This paper demonstrates a real-time search system called Aucher for live audio streams. Audio streaming services (e.g., Mixlr, Ximalaya, Lizhi and Facebook Live Audio) have become increasingly popular with the wide use of smart phones. Because of the popularity of audio broadcasting, the data volume of live audio streams is also ever increasing. Searching and indexing these audio streams is an important and challenging problem. Aucher is a system prototype which can support both voice search and keyword search on audio streams. We achieve the real-time response for queries by our novel index which exploits log structured merge-trees and supports multi-modal search. Moreover, our system can handle insertion about four times faster and more memory efficient than the state-of-the-art solution. We plan to demonstrate searching live audio streams by keywords and voice, illustrate the trade-off of freshness, popularity and relevance on query results, perform searching hot terms, and show the ability of searching live audio streams in real-time.

The state-of-the-art techniques on data center peak power management are too optimistic; they overestimate their benefits in a potentially insecure operating environment. Especially in data centers that oversubscribe power infrastructure, it is likely that unexpected traffics can violate power budget before an effective network DoS attack is observed. In this work, we take the first to investigate the joint effect of power throttling and traffic flooding. We characterize a special operating region in which DoS attacks can provoke undesirable power peaks without exhibiting network traffic anomalies. In this region, an attacker can trigger power emergency by sending normal traffics throughout the Internet. We term this new type of threat as DOPE (Denial of Power and Energy). We show that existing technologies are insufficient for eliminating DOPE without negative performance effects on legitimate users. To enhance data center resiliency, we propose a request-aware power management framework called Anti-DOPE. The key feature of Anti-DOPE is bridging the gap between network traffic controlling and server power management. Specifically, it pre-processes of incoming requests to isolate malicious power attacks on the network load balancer side and then post-processes of compute node performance to minimize the collateral damage it may cause. Anti-DOPE is orthogonal to prior power management schemes and requires minute system modification. Using Alibaba container trace we show that Anti-DOPE allows 44% shorter average response time. It also improves the 90th percentile tail latency by 68.1% compared to the other power controlling methods.

Motivation: The rapid development of next-generation sequencing technology provides an opportunity to study genome-wide DNA methylation at single-base resolution. However, depletion of unmethylated cytosines brings challenges for aligning bisulfite-converted sequencing reads to a large reference. Software tools for aligning methylation reads have not yet been comprehensively evaluated, especially for the widely used reduced representation bisulfite sequencing (RRBS) that involves enrichment for CpG islands (CGIs). Results: We specially developed a simulator, RRBSsim, for benchmarking analysis of RRBS data. We performed extensive comparison of seven mapping algorithms for methylation analysis in both real and simulated RRBS data. Eighteen lung tumors and matched adjacent tissues were sequenced by the RRBS protocols. Our empirical evaluation found that methylation results were less consistent between software tools for CpG sites with low sequencing depth, medium methylation level, on CGI shores or gene body. These observations were further confirmed by simulations that indicated software tools generally had lower recall of detecting these vulnerable CpG sites and lower precision of estimating methylation levels in these CpG sites. Among the software tools tested, bwa-meth and BS-Seeker2 (bowtie2) are currently our preferred aligners for RRBS data in terms of recall, precision and speed. Existing aligners cannot efficiently handle moderately methylated CpG sites and those CpG sites on CGI shores or gene body. Interpretation of methylation results from these vulnerable CpG sites should be treated with caution. Our study reveals several important features inherent in methylation data, and RRBSsim provides guidance to advance sequence-based methylation data analysis and methodological development. Availability and implementation: RRBSsim is a simulator for benchmarking analysis of RRBS data and its source code is available at https://github.com/xwBio/RRBSsim or https://github.com/xwBio/Docker-RRBSsim. Supplementary information: Supplementary data are available at Bioinformatics online.

MOTIVATION: RNA-Seq (also called whole-transcriptome sequencing) is an emerging technology that uses the capabilities of next-generation sequencing to detect and quantify entire transcripts. One of its important applications is the improvement of existing genome annotations. RNA-Seq provides rapid, comprehensive and cost-effective tools for the discovery of novel genes and transcripts compared with expressed sequence tag (EST), which is instrumental in gene discovery and gene sequence determination. The rat is widely used as a laboratory disease model, but has a less well-annotated genome as compared with humans and mice. In this study, we incorporated deep RNA-Seq data from three rat tissues-bone marrow, brain and kidney-with EST data to improve the annotation of the rat genome. RESULTS: Our analysis identified 32 197 transcripts, including 13 461 known transcripts, 13 934 novel isoforms and 4802 new genes, which almost doubled the numbers of transcripts in the current public rat genome database (rn5). Comparisons of our predicted protein-coding gene sets with those in public datasets suggest that RNA-Seq significantly improves genome annotation and identifies novel genes and isoforms in the rat. Importantly, the large majority of novel genes and isoforms are supported by direct evidence of RNA-Seq experiments. These predicted genes were integrated into the Rat Genome Database (RGD) and can serve as an important resource for functional studies in the research community. AVAILABILITY AND IMPLEMENTATION: The predicted genes are available at http://rgd.mcw.edu.