Related papers: Bullshark: The Partially Synchronous Version
Agreement among a set of processes and in the presence of partial failures is one of the fundamental problems of distributed systems. In the most general case, many decisions must be agreed upon over the lifetime of a system with…
The goal of counterfactual learning for statistical machine translation (SMT) is to optimize a target SMT system from logged data that consist of user feedback to translations that were predicted by another, historic SMT system. A challenge…
Despite being one of the most widely spoken languages globally, Bangla remains a low-resource language in the field of Natural Language Processing (NLP). Mainstream Automatic Speech Recognition (ASR) and Speaker Diarization systems for…
We develop a novel approach to conformal prediction when the target task has limited data available for training. Conformal prediction identifies a small set of promising output candidates in place of a single prediction, with guarantees…
Federated learning (FL) is an emerging distributed machine learning paradigm that protects privacy and tackles the problem of isolated data islands. At present, there are two main communication strategies of FL: synchronous FL and…
In this paper we briefly report some recent developments on generalized synchronization. We discuss different methods of detecting generalized synchronization. We first consider two unidirectionally coupled systems and then two mutually…
Structural discovery amongst a set of variables is of interest in both static and dynamic settings. In the presence of lead-lag dependencies in the data, the dynamics of the system can be represented through a structural equation model…
Crowdsourcing systems commonly face the problem of aggregating multiple judgments provided by potentially unreliable workers. In addition, several aspects of the design of efficient crowdsourcing processes, such as defining worker's…
We study the problem of reducing test-time acquisition costs in classification systems. Our goal is to learn decision rules that adaptively select sensors for each example as necessary to make a confident prediction. We model our system as…
We present the first parser for UCCA, a cross-linguistically applicable framework for semantic representation, which builds on extensive typological work and supports rapid annotation. UCCA poses a challenge for existing parsing techniques,…
Machine Translation (MT) is usually viewed as a one-shot process that generates the target language equivalent of some source text from scratch. We consider here a more general setting which assumes an initial target sequence, that must be…
This is a complementary document for the paper titled "Asynchronous Distributed Gaussian Process Regression for Online Learning and Dynamical Systems".
The paper introduces the concept of asynchronous pseudo-system. Its purpose is to correct/generalize/continue the study of the asynchronous systems (the models of the asynchronous circuits) that has been started in [1], [2].
Most methods for Byzantine fault tolerance (BFT) in the partial synchrony setting divide the local state of the nodes into views, and the transition from one view to the next dictates a leader change. In order to provide liveness, all…
Real-time data processing applications with low latency requirements have led to the increasing popularity of stream processing systems. While such systems offer convenient APIs that can be used to achieve data parallelism automatically,…
This paper presents a generalized flux-corrected transport (FCT) algorithm, which is shown to be total variation diminishing under some conditions. The new algorithm has improved properties from the standpoint of use and analysis. Results…
Recovering the underlying Directed Acyclic Graph (DAG) structures from observational data presents a formidable challenge, partly due to the combinatorial nature of the DAG-constrained optimization problem. Recently, researchers have…
As an emerging paradigm of federated learning, asynchronous federated learning offers significant speed advantages over traditional synchronous federated learning. Unlike synchronous federated learning, which requires waiting for all…
Consensus protocols for asynchronous networks are usually complex and inefficient, leading practical systems to rely on synchronous protocols. This paper attempts to simplify asynchronous consensus by building atop a novel threshold logical…
Enterprises increasingly need natural language (NL) question answering over hybrid data lakes that combine structured tables and unstructured documents. Current deployed solutions, including RAG-based systems, typically rely on brute-force…