Related papers: Training Through Failure: Effects of Data Consiste…

State-of-the-art stream processing platforms make use of checkpointing to support fault tolerance, where a "checkpoint tuple" flows through the topology to all operators, indicating a checkpoint and triggering a checkpoint operation. The…

This paper investigates dual sourcing problems with supply mode dependent failure rates, particularly relevant in managing spare parts for downtime-critical assets. To enhance resilience, businesses increasingly adopt dual sourcing…

Using neural networks in practical settings would benefit from the ability of the networks to learn new tasks throughout their lifetimes without forgetting the previous tasks. This ability is limited in the current deep neural networks by a…

Continual learning is a promising machine learning paradigm to learn new tasks while retaining previously learned knowledge over streaming training data. Till now, rehearsal-based methods, keeping a small part of data from old tasks as a…

Fault-tolerance techniques for stream processing engines can be categorized into passive and active approaches. A typical passive approach periodically checkpoints a processing task's runtime states and can recover a failed task by…

Averaging checkpoints along the training trajectory is a simple yet powerful approach to improve the generalization performance of Machine Learning models and reduce training time. Motivated by these potential gains, and in an effort to…

Machine learning (ML) techniques are increasingly applied to decision-making and control problems in Cyber-Physical Systems among which many are safety-critical, e.g., chemical plants, robotics, autonomous vehicles. Despite the significant…

Recent developments in large language models (LLMs) have introduced new requirements for efficient and robust training. As LLM clusters scale, node failures, lengthy recoveries, and bulky checkpoints erode efficiency. Infrequent…

Federated learning is used to train a shared model in a decentralized way without clients sharing private data with each other. Federated learning systems are susceptible to poisoning attacks when malicious clients send false updates to the…

Continual learning (CL) studies how models acquire tasks sequentially while retaining previously learned knowledge. Despite substantial progress in benchmarking CL methods, comparative evaluations typically keep the fine-tuning regime…

Parallel computing is very important to accelerate the performance of software systems. Additionally, considering that a recurring challenge is to process high data volumes continuously, stream processing emerged as a paradigm and software…

Machine unlearning, an emerging research topic focusing on compliance with data privacy regulations, enables trained models to remove the information learned from specific data. While many existing methods indirectly address this issue by…

In the present era of deep learning, continual learning research is mainly focused on mitigating forgetting when training a neural network with stochastic gradient descent on a non-stationary stream of data. On the other hand, in the more…

Federated Learning (FL) is a machine learning paradigm that enables the training of a shared global model across distributed clients while keeping the training data local. While most prior work on designing systems for FL has focused on…

Railway points are among the key components of railway infrastructure. As a part of signal equipment, points control the routes of trains at railway junctions, having a significant impact on the reliability, capacity, and punctuality of…

State-machine replication, a fundamental approach to designing fault-tolerant services, requires commands to be executed in the same order by all replicas. Moreover, command execution must be deterministic: each replica must produce the…

The performance of modern machine learning methods highly depends on their hyperparameter configurations. One simple way of selecting a configuration is to use default settings, often proposed along with the publication and implementation…

This paper tackles the problem of making complex resource-constrained cyber-physical systems (CPS) resilient to sensor anomalies. In particular, we present a framework for checkpointing and roll-forward recovery of state-estimates in…

Modern language models are powerful, but typically static after deployment. A major obstacle to building models that continually learn over time is catastrophic forgetting, where updating on new data erases previously acquired capabilities.…

We explore a data-driven approach for learning to optimize neural networks. We construct a dataset of neural network checkpoints and train a generative model on the parameters. In particular, our model is a conditional diffusion transformer…