Related papers: Benchmarking JSON BinPack
Batch normalization (BN) allows training very deep networks by normalizing activations by mini-batch sample statistics which renders BN unstable for small batch sizes. Current small-batch solutions such as Instance Norm, Layer Norm, and…
Temporal Neural Networks (TNNs), inspired from the mammalian neocortex, exhibit energy-efficient online sensory processing capabilities. Recent works have proposed a microarchitecture framework for implementing TNNs and demonstrated…
Large language models (LLMs) have revolutionized numerous applications, yet their deployment remains challenged by memory constraints on local devices. While scaling laws have enhanced LLM capabilities, the primary bottleneck has shifted…
We consider algorithms to schedule packets with values and deadlines in a size-bounded buffer. At any time, the buffer can store at most B packets. Packets arrive over time. Each packet has a non-negative value and an integer deadline. In…
A prescription to calculate the minimum number of bits needed for binary strip detector readout is presented. This permits a systematic analysis of the readout efficiency relative to this theoretical minimum number of bits. Different level…
Modern data stream applications demand memory-efficient solutions for accurately tracking frequent items, such as heavy hitters and heavy changers, under strict resource constraints. Traditional sketches face inherent accuracy-memory…
In this research we use a data stream approach to mining data and construct Decision Tree models that predict software build outcomes in terms of software metrics that are derived from source code used in the software construction process.…
The main advantage of Constraint Programming (CP) approaches for sequential pattern mining (SPM) is their modularity, which includes the ability to add new constraints (regular expressions, length restrictions, etc). The current best CP…
The challenge of estimating similarity between sets has been a significant concern in data science, finding diverse applications across various domains. However, previous approaches, such as MinHash, have predominantly centered around…
The Java Stream API aims at increasing developer productivity thanks to an easy-to-read declarative syntax to express computations. It also simplifies parallel computing, providing a high-level abstraction on top of common parallelization…
In the scenario-based evaluation of machine learning models, a key problem is how to construct test datasets that represent various scenarios. The methodology proposed in this paper is to construct a benchmark and attach metadata to each…
We present a new streaming algorithm to validate JSON documents against a set of constraints given as a JSON schema. Among the possible values a JSON document can hold, objects are unordered collections of key-value pairs while arrays are…
Decentralized resource markets are Web 3.0 applications that build open-access platforms for trading digital resources among users without any central management. They promise cost reduction, transparency, and flexible service provision.…
In modern computing systems, jobs' resource requirements often vary over time. Accounting for this temporal variability during job scheduling is essential for meeting performance goals. However, theoretical understanding on how to schedule…
In many real-world computer vision applications, including medical imaging and industrial inspection, binary classification tasks are characterized by a severe scarcity of positive samples. A widely adopted solution is to generate synthetic…
We study the online bin packing problem under two stochastic settings. In the bin packing problem, we are given n items with sizes in (0,1] and the goal is to pack them into the minimum number of unit-sized bins. First, we study bin packing…
Most sentence embedding techniques heavily rely on expensive human-annotated sentence pairs as the supervised signals. Despite the use of large-scale unlabeled data, the performance of unsupervised methods typically lags far behind that of…
Software effort estimation models are typically developed based on an underlying assumption that all data points are equally relevant to the prediction of effort for future projects. The dynamic nature of several aspects of the software…
In the burgeoning realm of Internet of Things (IoT) applications on edge devices, data stream compression has become increasingly pertinent. The integration of added compression overhead and limited hardware resources on these devices calls…
Bayesian neural networks offer better estimates of model uncertainty compared to frequentist networks. However, inference involving Bayesian models requires multiple instantiations or sampling of the network parameters, requiring…