MLDemon monitors ML systems post-deployment, improving reliability with real-time performance estimates and expert labels.
problem Ensuring reliability of machine learning systems post-deployment, especially when user inputs differ from training data.
method Integrates unlabeled and on-demand labeled data to monitor ML model performance in real-time, deciding when to acquire expert labels.
result Outperforms existing approaches in temporal datasets with diverse distribution drifts, providing theoretical optimality for distribution drifts.
Operations is a key challenge in the domain of machine learning pipeline deployments involving monitoring and management of real-time prediction quality. Typically, metrics like accuracy, RMSE etc., are used to track the performance of models in deployment. However, these metrics cannot be calculated in production due …
Deployment of machine learning (ML) algorithms in production for extended periods of time has uncovered new challenges such as monitoring and management of real-time prediction quality of a model in the absence of labels. However, such tracking is imperative to prevent catastrophic business outcomes resulting from inco…
Amazon SageMaker Model Monitor detects drift in deployed ML models.
problem Ensuring high performance of ML models in production environments.
method Automatically detects data, concept, bias, and feature attribution drift in real-time.
result Maintains high quality models by providing alerts and corrective actions.
DUPLE tackles cross-deployment recognition in fiber-optic perimeter security with meta-learning.
problem Cross-deployment recognition challenges in fiber-optic perimeter security due to label scarcity and distribution shifts.
method DUPLE employs statistically guided meta-learning to enhance recognition robustness across unseen deployments.
result DUPLE consistently outperforms traditional and meta-learning baselines in cross-deployment DFOS benchmarks.
Infrastructure monitors AI/ML radiology models across multiple sites.
problem Monitoring and improving AI/ML radiology models across multiple sites.
method Interactive radiology reporting, centralized cloud system, post-marketing surveillance.
result Efficient monitoring and iterative development of AI/ML models without radiologist burden.
Simple online monitor detects unsafe LLM outputs.
problem LLMs generate unsafe outputs despite training.
method Thresholding external verifier signal to decide alarms.
result Simple design competitive with advanced methods.
Focuses on monitoring and explaining models in real-world applications.
problem Ensuring high quality machine learning services in production environments.
method Statistical techniques for model performance and data monitoring, explanations of predictions.
result Challenges and solutions for implementing monitoring and explanation in production models.
Adaptive monitoring for AI systems detects and diagnoses shifts in data distribution.
problem Continuous monitoring of AI systems to detect and address unsafe behavior.
method Weighted-conformal martingales (WCTMs) for online monitoring of AI systems.
result Improved performance over state-of-the-art baselines on real-world datasets.
This research tackles monitoring machine learning algorithms post-deployment, addressing performativity issues.
problem Monitoring machine learning algorithms after deployment, especially when they affect their own data-generating process.
method Uses causal inference techniques to navigate performativity and compares different monitoring criteria and data sources.
result Different monitoring systems have varying operating characteristics and implications for ML monitoring design.
Work addresses long-term accuracy issues in IoT air quality sensors.
problem Limited accuracy of IoT air quality sensors in long-term field deployments.
method Adaptive machine learning strategies for network calibration.
result Prolongs the validity of multisensor calibration models for continuous learning.
Proposes real-time risk monitoring for machine learning systems under unknown shifts.
problem Dynamic distribution shifts challenge real-world machine learning systems' risk assurances.
method Sequential hypothesis testing with 'testing by betting' to detect risk violations.
result Effective real-time risk monitoring under various unknown shifts.
The significance of air pollution and the problems associated with it are fueling deployments of air quality monitoring stations worldwide. The most common approach for air quality monitoring is to rely on environmental monitoring stations, which unfortunately are very expensive both to acquire and to maintain. Hence e…
The paper develops methods to reduce deployment risk under dynamic covariate shifts.
problem Reduction of deployment risk under dynamic covariate shifts.
method Time-domain Poincare inequality and Jacobian-velocity theorem to identify and control directional tangent energy.
result Drift-aligned tangent regularization (DTR) reduces risk volatility and directional gain in low-rank drift regimes.
Since 2006, deep learning (DL) has become a rapidly growing research direction, redefining state-of-the-art performances in a wide range of areas such as object recognition, image segmentation, speech recognition and machine translation. In modern manufacturing systems, data-driven machine health monitoring is gaining …
This thesis tackles NILM challenges with a new dataset and efficient edge deployment techniques.
problem Limited datasets and high computational power for NILM deployment.
method Developed an interoperable data collection framework and introduced model compression techniques.
result Efficient edge deployment of NILM models for global scalability and sustainability.
RESPIRE calibrates low-cost air-quality sensors for CO levels, resistant to outliers.
problem Calibrating LCAQ sensors against regulatory-grade monitors is expensive and time-consuming.
method PROvably outlier-resistant semi-parametric regression technique.
result RESPIRE offers improved prediction in cross-site, cross-season, and cross-sensor settings.
The paper monitors artificial neural networks using embeddings and multivariate control charts.
problem Ensuring the stability of artificial neural networks during deployment.
method Monitoring the latent feature representation (embedding) of ANN outputs using multivariate control charts based on data depth and ranks.
result The proposed method effectively detects nonstationary data streams in ANN outputs.
The paper monitors model deterioration using uncertainty estimation.
problem Challenges in monitoring deployed machine learning models.
method Non-parametric bootstrapped uncertainty estimates and SHAP values.
result The approach detects model deterioration and uncertainty effectively.
There is a need for affordable, widely deployable maternal-fetal ECG monitors to improve maternal and fetal health during pregnancy and delivery. Based on the diffusion-based channel selection, here we present the mathematical formalism and clinical validation of an algorithm capable of accurate separation of maternal …
VarDetect monitors API queries to detect model extraction attacks.
problem Attackers can extract ML models through API queries.
method VarDetect uses a modified variational autoencoder to track and detect attacker samples.
result VarDetect successfully detects and raises alarms for model extraction attacks.
Across numerous applications, forecasting relies on numerical solvers for partial differential equations (PDEs). Although the use of deep-learning techniques has been proposed, actual applications have been restricted by the fact the training data are obtained using traditional PDE solvers. Thereby, the uses of deep-le…
Novel method detects faults in helicopter transmissions using healthy data only.
problem Detecting faults in rare events in helicopter transmissions.
method Probabilistic anomaly detection using Bayesian measures.
result Method achieves competitive detection performance in real-world and benchmark applications.
Geometric stability predicts steerability and detects drift in language models.
problem Predicting steerability and detecting drift in language models.
method Supervised and unsupervised geometric stability measures.
result Supervised geometric stability predicts steerability with high accuracy and detects drift earlier.
AnomalyCD discovers anomaly causes in large systems with binary flags, reducing computational burden.
problem Learning graphical causal models from large-scale binary anomaly data is computationally expensive.
method AnomalyCD uses anomaly data-aware causality testing, sparse data compression, and edge pruning.
result AnomalyCD reduces computation overhead and improves accuracy on binary anomaly datasets.
With the deployment of online monitoring systems in distribution networks, massive amounts of data collected through them contains rich information on the operating states of the networks. By leveraging the data, an unsupervised approach based on bidirectional generative adversarial networks (BiGANs) is proposed for op…
Biodiversity monitoring using audio recordings is achievable at a truly global scale via large-scale deployment of inexpensive, unattended recording stations or by large-scale crowdsourcing using recording and species recognition on mobile devices. The ability, however, to reliably identify vocalising animal species is…
AM-PPI uses multiple predictors to reduce label cost in healthcare AI.
problem Reduces label cost in post-deployment monitoring of healthcare AI.
method Combines model predictions with a small labeled sample, routing each instance to a cost-appropriate subset of predictors.
result Produces narrower confidence intervals than single-predictor methods.
RSI uses Bayesian inference to monitor compliance in rule-governed domains.
problem Structural obstacles in compliance monitoring, including unlabeled outcomes and selective withholding of evidence.
method Rule-State Inference (RSI) treats formalized rules as Bayesian priors and infers compliance states through mean-field variational inference.
result RSI delivers formal guarantees of adaptability, consistency, and convergence, validated on a synthetic enterprise benchmark.
Paper presents UrbanFM and UrbanPy models for inferring fine-grained urban flows.
problem Reduce cost of urban flow monitoring while maintaining data accuracy and granularity.
method Develops UrbanFM and UrbanPy models to infer fine-grained urban flows from coarse-grained observations.
result UrbanPy model demonstrates favorable performance for larger-scale inference tasks.
DGPs improve air quality inference from sparse data.
problem Accurate air quality monitoring in unmonitored areas.
method Deep Gaussian Processes with Doubly Stochastic Variational Inference.
result DGPs outperform state-of-the-art models in AQ inference.
VSCOUT detects anomalies in high-dimensional data using a hybrid VAE approach.
problem Challenges in classical SPC for high-dimensional, non-Gaussian data.
method Hybrid VAE architecture with ARD prior, ensemble filtering, and changepoint detection.
result VSCOUT achieves superior sensitivity to special-cause structure and controlled false alarms.
The paper develops a new framework for detecting distributional drifts conditioned on context.
problem Detecting distributional drifts in machine learning systems when context changes.
method Develops a framework using two-sample tests for conditional distributional treatment effects.
result Demonstrates effectiveness for detecting drift in subpopulations of data.
Optimal sensor placement minimizes information loss from simulations.
problem Designing efficient sensor networks for spatiotemporal processes.
method Model-based sensor placement criterion with sparse variational inference and Gauss-Markov priors.
result Our method identifies sensor networks that minimize information loss from simulated data.
This paper tackles AI model governance challenges in financial services.
problem Challenges in current AI model governance practices in financial services.
method Proposes a system-level framework for increased self-regulation.
result Enhanced model governance and risk management capabilities.
CMCO provides robust uncertainty estimates for neural operators without retraining.
problem Uncertainty quantification in deep learning for real-time virtual sensing.
method Unified Monte Carlo dropout and split conformal prediction in DeepONet.
result Near-nominal empirical coverage in diverse applications.
This paper presents a solution for persistent monitoring of real-world stochastic phenomena, where the underlying covariance structure changes sharply across time, using a small number of mobile robot sensors. We propose an adaptive solution for the problem where stochastic real-world dynamics are modeled as a Gaussian…
As video camera deployments continue to grow, the need to process large volumes of real-time data strains wide area network infrastructure. When per-camera bandwidth is limited, it is infeasible for applications such as traffic monitoring and pedestrian tracking to offload high-quality video streams to a datacenter. Th…
Contemporary power grids are being challenged by rapid voltage fluctuations that are caused by large-scale deployment of renewable generation, electric vehicles, and demand response programs. In this context, monitoring the grid's operating conditions in real time becomes increasingly critical. With the emergent large …
This study benchmarks anomaly detection methods in a functional setup.
problem Efficient anomaly detection in high-frequency sensor data.
method Functional analysis approach for multivariate data.
result Comparison of anomaly detection methods on real datasets.
Deployment-complete benchmarking assesses if evidence leads to consistent deployment actions.
problem Lack of clear evidence leading to consistent deployment actions.
method Introduces deployment-complete benchmarking to test if benchmark evidence determines deployment actions.
result Benchmark evidence must be complete for a claim to lead to a consistent deployment action.
A new method for releasing AI workflows to avoid premature incorrect results.
problem Statistical challenges in releasing AI workflows with adaptive scoring.
method Wrapper that calibrates and accumulates evidence from high-scoring failures.
result Reduces premature incorrect release while still releasing on moderate evidence.
The preponderance of connected devices provides unprecedented opportunities for fine-grained monitoring of the public infrastructure. However while classical models expect high quality application-specific data streams, the promise of the Internet of Things (IoT) is that of an abundance of disparate and noisy datasets …
Paper establishes lower bounds and optimal algorithms for deployment-efficient RL.
problem Deployment efficiency in reinforcement learning.
method Optimization with constraints, lower bounds, algorithms.
result Established optimal algorithms for deployment-efficient RL.
CoinTossX is a low-latency, open-source matching engine for financial trading.
problem Efficiently matching orders in financial markets with low latency and high throughput.
method Developed in Java, orders submitted via UDP SBE, low-latency message transport (Aeron Media Driver). Separates order generation and matching.
result Demonstrated low-latency, high-throughput performance in various deployment scenarios.
AI systems that explain their decisions can be monitored for harmful intentions.
problem Monitoring AI systems' decision-making processes for harmful intentions is imperfect and can miss some misbehavior.
method Monitoring the chain of thought (CoT) of AI systems that communicate in human language.
result CoT monitoring is a promising but fragile approach to AI safety.
Machine learning (ML), especially deep learning is made possible by the availability of big data, enormous compute power and, often overlooked, development tools or frameworks. As the algorithms become mature and efficient, more and more ML inference is moving out of datacenters/cloud and deployed on edge devices. This…
Paper addresses theoretical risks in neural MCCFR, proposing Robust Deep MCCFR for improved performance.
problem Theoretical risks in neural MCCFR, especially in large games.
method Adaptive framework with selective component deployment, including target networks, exploration, and variance-aware training.
result Robust Deep MCCFR achieves significant exploitability improvements in both Kuhn and Leduc Poker.