Related papers: Parachute: Single-Pass Bi-Directional Information …
In many prediction problems, we have extra information during training (for example, measurements that are expensive or slow to collect) that will not be available when the model is deployed. A common strategy is to first train a model that…
To train modern large DNN models, pipeline parallelism has recently emerged, which distributes the model across GPUs and enables different devices to process different microbatches in pipeline. Earlier pipeline designs allow multiple…
We propose the Parity Flow formalism, a method for tracking the information flow in quantum circuits. This method adds labels to quantum circuit diagrams such that the action of Clifford gates can be understood as a recoding of quantum…
Extracting the valuable features and information in Big Data has become one of the important research issues in Data Science. In most Internet of Things (IoT) applications, the collected data are uncertain and imprecise due to sensor device…
Due to the scarcity of annotated scene flow data, self-supervised scene flow learning in point clouds has attracted increasing attention. In the self-supervised manner, establishing correspondences between two point clouds to approximate…
Distributed learning platforms for processing large scale data-sets are becoming increasingly prevalent. In typical distributed implementations, a centralized master node breaks the data-set into smaller batches for parallel processing…
Filtering data based on predicates is one of the most fundamental operations for any modern data warehouse. Techniques to accelerate the execution of filter expressions include clustered indexes, specialized sort orders (e.g., Z-order),…
Cross-domain Recommendation (CDR) aims to alleviate the data sparsity and the cold-start problems in traditional recommender systems by leveraging knowledge from an informative source domain. However, previously proposed CDR models pursue…
This study develops a novel class of queueing game to explain a common practice in cargo shipping "Sail Fast, Then Wait" (SFTW), and demonstrates that resolving information asymmetry among ships can deconcentrate port arrival times. We…
We introduce a user mode file system, CannyFS, that hides latency by assuming all I/O operations will succeed. The user mode process will in turn report errors, allowing proper cleanup and a repeated attempt to take place. We demonstrate…
Diamond relay channel model, as a basic transmission model, has recently been attracting considerable attention in wireless Ad Hoc networks. Node cooperation and opportunistic scheduling scheme are two important techniques to improve the…
Advanced Persistent Threats (APTs) are stealthy customized attacks by intelligent adversaries. This paper deals with the detection of APTs that infiltrate cyber systems and compromise specifically targeted data and/or infrastructures.…
Applications are increasingly written as dynamic workflows underpinned by an execution framework that manages asynchronous computations across distributed hardware. However, execution frameworks typically offer one-size-fits-all solutions…
Sparse events, such as malign attacks in real-time network traffic, have caused big organisations an immense hike in revenue loss. This is due to the excessive growth of the network and its exposure to a plethora of people. The standard…
A simple scheme was proposed by Knuth to generate binary balanced codewords from any information word. However, this method is limited in the sense that its redundancy is twice that of the full sets of balanced codes. The gap between…
Metadata hotspots remain one of the key obstacles to scalable Input/Output (I/O) in both High-Performance Computing (HPC) and cloud-scale storage environments. Situations such as job start-ups, checkpoint storms, or heavily skewed namespace…
We study the problem of distributed information bottleneck, in which multiple encoders separately compress their observations in a manner such that, collectively, the compressed signals preserve as much information as possible about another…
This paper considers networks where user traffic is regulated through deterministic traffic profiles, e.g., token buckets, and requires hard delay bounds. The network's goal is to minimize the resources it needs to meet those bounds. The…
We describe a duality mapping between STRIPS planning tasks. By exchanging the initial and goal conditions, taking their respective complements, and swapping for every action its precondition and delete list, one obtains for every STRIPS…
We propose a distributed protocol for a queue, called \textsc{Skueue}, which spreads its data fairly onto multiple processes, avoiding bottlenecks in high throughput scenarios. \textsc{Skueue} can be used in highly dynamic environments,…