Related papers: 2P-BFT-Log: 2-Phase Single-Author Append-Only Log …
We apply diffusion strategies to develop a fully-distributed cooperative reinforcement learning algorithm in which agents in a network communicate only with their immediate neighbors to improve predictions about their environment. The…
Data reconciliation in general, and filesystem synchronization in particular, lacks rigorous theoretical foundation. This paper presents, for the first time, a complete analysis of synchronization for two replicas of a theoretical…
Trees are fundamental data structure for many areas of computer science and system engineering. In this report, we show how to ensure eventual consistency of optimistically replicated trees. In optimistic replication, the different replicas…
In this paper we propose a double-linked blockchain data structure that greatly improves blockchain performance and guarantees single chain with no forks. Additionally, with the proposed proof-of-refundable-tax (PoRT) consensus algorithm,…
Backdoor attacks involve the injection of a limited quantity of poisoned examples containing triggers into the training dataset. During the inference stage, backdoor attacks can uphold a high level of accuracy for normal examples, yet when…
Federated learning protocols require repeated synchronization between clients and a central server, with convergence rates depending on learning rates, data heterogeneity, and client sampling. This paper asks whether iterative communication…
Distributed in-memory datastores underpin cloud applications that run within a datacenter and demand high performance, strong consistency, and availability. A key feature of datastores is data replication. The data are replicated across…
A protocol involving the repetitive (twofold, to be precise) application of PBT protocol to the same resource is studied. The quantities characterizing the resulting protocol, so-called \textit{two-step PBT}, namely \textit{enatnglement…
By the CAP Theorem, a distributed data storage system can ensure either Consistency under Partition (CP) or Availability under Partition (AP), but not both. This has led to a split between CP databases, in which updates are synchronous, and…
Subjective evaluation of LLM behavior -- empathy, restraint, calibrated emotional tone -- is hard. Human inter-rater agreement on such qualities saturates near rho ~ 0.45, and an LLM-as-judge proxy alone risks circularity: a judge sharing…
In this paper, we present BunchBFT Byzantine fault-tolerant state-machine replication for high performance and scalability. At the heart of BunchBFT is a novel design called the cluster-based approach that divides the replicas into clusters…
Byzantine Fault-Tolerant (BFT) protocols have been proposed to tolerate malicious behaviors in state machine replications. With classic BFT protocols, the total number of replicas is known and fixed a priori. The resilience of BFT…
We describe an efficient and fault-tolerant algorithm for distributed cyclic garbage collection. The algorithm imposes few requirements on the local machines and allows for flexibility in the choice of local collector and distributed…
LLM post-training typically propagates task gradients through the full depth of the model. Although this end-to-end structure is simple and general, it couples task adaptation to full-depth activation storage, long-range backward…
We present ezBFT, a novel leaderless, distributed consensus protocol capable of tolerating byzantine faults. ezBFT's main goal is to minimize the client-side latency in WAN deployments. It achieves this by (i) having no designated primary…
We study large-scale distributed cooperative systems that use optimistic replication. We represent a system as a graph of actions (operations) connected by edges that reify semantic constraints between actions. Constraint types include…
In federated learning (FL), a set of participants share updates computed on their local data with an aggregator server that combines updates into a global model. However, reconciling accuracy with privacy and security is a challenge to FL.…
Data management systems have traditionally been designed to support either long-running analytics queries or short-lived transactions, but an increasing number of applications need both. For example, online games, socio-mobile apps, and…
Efficiently aggregating trained neural networks from local clients into a global model on a server is a widely researched topic in federated learning. Recently, motivated by diminishing privacy concerns, mitigating potential attacks, and…
GUI task automation streamlines repetitive tasks, but existing LLM or VLM-based planner-executor agents suffer from brittle generalization, high latency, and limited long-horizon coherence. Their reliance on single-shot reasoning or static…