Related papers: OLC-WA: Drift Aware Tuning-Free Online Classificat…

Training a classifier on web-crawled data demands learning algorithms that are robust to annotation errors and irrelevant examples. This paper builds upon the recent empirical observation that applying unsupervised contrastive learning to…

In scenarios where obtaining real-time labels proves challenging, conventional approaches may result in sub-optimal performance. This paper presents an optimal strategy for streaming contexts with limited labeled data, introducing an…

Urban time series data forecasting featuring significant contributions to sustainable development is widely studied as an essential task of the smart city. However, with the dramatic and rapid changes in the world environment, the…

Classical optimization theory deals with fixed, time-invariant objective functions. However, time-varying optimization has emerged as an important subject for decision-making in dynamic environments. In this work, we study the problem of…

It is a well-known fact that the performance of deep learning models deteriorates when they encounter a distribution shift at test time. Test-time adaptation (TTA) algorithms have been proposed to adapt the model online while inferring test…

Control tuning and adaptation present a significant challenge to the usage of robots in diverse environments. It is often nontrivial to find a single set of control parameters by hand that work well across the broad array of environments…

Data in the real world often has an evolving distribution. Thus, machine learning models trained on such data get outdated over time. This phenomenon is called model drift. Knowledge of this drift serves two purposes: (i) Retain an accurate…

The growth of network-connected devices has led to an exponential increase in data generation, creating significant challenges for efficient data analysis. This data is generated continuously, creating a dynamic flow known as a data stream.…

We present a real-time multivariate anomaly detection algorithm for data streams based on the Probabilistic Exponentially Weighted Moving Average (PEWMA). Our formulation is resilient to (abrupt transient, abrupt distributional, and gradual…

In contrast to offline working fashions, two research paradigms are devised for online learning: (1) Online Meta Learning (OML) learns good priors over model parameters (or learning to learn) in a sequential setting where tasks are revealed…

LLMs operating in dynamic real-world contexts often encounter knowledge that evolves continuously or emerges incrementally. To remain accurate and effective, models must adapt to newly arriving information on the fly. We introduce Online…

Continual Test-Time Adaptation (CTTA) involves adapting a pre-trained source model to continually changing unsupervised target domains. In this paper, we systematically analyze the challenges of this task: online environment, unsupervised…

Test-time adaptation (TTA) is a technique used to reduce distribution gaps between the training and testing sets by leveraging unlabeled test data during inference. In this work, we expand TTA to a more practical scenario, where the test…

We consider the problem of detecting abrupt changes in the distribution of a multi-dimensional time series, with limited computing power and memory. In this paper, we propose a new, simple method for model-free online change-point detection…

Addressing sensor drift is essential in industrial measurement systems, where precise data output is necessary for maintaining accuracy and reliability in monitoring processes, as it progressively degrades the performance of machine…

Modern clinical decision support systems can concurrently serve multiple, independent medical imaging institutions, but their predictive performance may degrade across sites due to variations in patient populations, imaging hardware, and…

Machine learning approaches for image classification have led to impressive advances in that field. For example, convolutional neural networks are able to achieve remarkable image classification accuracy across a wide range of applications…

Continuous machine learning pipelines are common in industrial settings where models are periodically trained on data streams. Unfortunately, concept drifts may occur in data streams where the joint distribution of the data X and label y,…

Over-the-air (OTA) federated learning (FL) has been well recognized as a scalable paradigm that exploits the waveform superposition of the wireless multiple-access channel to aggregate model updates in a single use. Existing OTA-FL designs…

Open-world learning (OWL) requires models that can adapt to evolving environments while reliably detecting out-of-distribution (OOD) inputs. Existing approaches, such as SCONE, achieve robustness to covariate and semantic shifts but assume…