Papers for

online machine learning engineers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Bayesian neural networks learn better online with full covariance tracking

Full-Covariance Smoothing of Bayesian Neural Networks for Online Adaptation

Abstract: A neural network's layers can be treated as time steps of a state-space model, turning Bayesian training into a smoothing problem: a forward pass propagates Gaussian moments through the network, and a backward Rauch--Tung--Striebel pass updates the weight posteriors in closed form. Such methods learn from each observation in a single pass, in an uncertainty-aware manner, and without gradient-based iterations or replay, which makes them well suited for online adaptation and data-efficient learning. Existing smoothing-based methods, however, are restricted to diagonal covariances across activations, discarding correlations between neurons. We overcome this limitation via a cross-covariance identity that enables full-covariance propagation through a network's nonlinear activations. We derive a one-step-per-layer smoother that approximates as Gaussian only each layer's affine output, and that applies both to deterministic systems with noisy observations and to stochastic systems described by output statistics. We demonstrate this method in non-stationary classification, online dynamics learning, and policy adaptation of a vision-language-action model, and find that it is generally more accurate than other smoothing-based methods.

Wed 23 SeptMachine Learning
The gist
Neural networks can learn from data arriving over time, but usually, they treat each part of the network independently, missing how parts relate to each other. This paper presents a method that keeps track of how different neurons depend on one another during learning, improving the network’s ability to adapt quickly and accurately. The authors show this approach works well on tasks like changing classifications, learning dynamics, and adapting policies for vision-language models. Their method updates knowledge efficiently without many repeated training steps.
Open → 2609.27244v1

Stream cruise control method improves online regression with adaptive drift detection

SCCM : Stream Cruise Control Method for Automated Drift Detection and Adaptation

Abstract: Real-world datasets often exhibit evolving distributions, known as concept drift. Ignoring drift degrades predictive performance, while reliance on fixed hyperparameters further limits model adaptability under changing conditions. Adaptive learning addresses this challenge by continuously updating models online, allowing them to incrementally adjust and remain effective as data distributions evolve. This paper presents the Stream Cruise Control Method (SCCM), a comprehensive framework for drift detection and adaptation in online regression. SCCM enables automated adaptation through early-response, pre-update drift detection, drift magnitude quantification, KPI-window-based thresholding for local false-alarm mitigation, dynamic hyperparameter tuning, and model recalibration. SCCM also adopts an in-memory design for real-time adaptability, unlike purely reactive methods that typically activate adaptation only after performance degradation is observed. By using dynamic thresholding and remaining agnostic to data distributions, SCCM supports KPI-based monitoring across varying data streams, including high-dimensional and large-scale settings. SCCM is integrated with four online regression models and evaluated on 18 synthetic datasets covering abrupt, incremental, and alternating gradual drift, together with eight real-world datasets. The evaluation uses both R2 and MSE and compares against eight detector--adaptation baselines. Results show improved predictive performance and effective drift handling across the evaluated online regression settings.

Tue 8 SeptMachine LearningArtificial Intelligence
The gist
Data used in many applications can change over time, making prediction models less accurate. The authors present the Stream Cruise Control Method (SCCM), which detects when these changes happen early and adjusts the models automatically before performance drops. This method monitors changes continuously and adapts the models dynamically, even when data characteristics vary widely. SCCM was tested on a variety of synthetic and real datasets and showed better prediction accuracy compared to existing methods.
Open → 2609.09432v1