Context improves one-class classifiers in dynamic data streams.
problem Improving one-class classification in data streams with limited training data.
method Proposes using context to guide one-class classifier learning in data streams, presenting three frameworks.
result The use of context can improve the performance of streaming one-class classifiers.
Online learning algorithm identifies contextual changes for streaming data.
problem Challenges in identifying and utilizing contextual cues for streaming data.
method Neural network-based autoencoder for identifying contextual changes; comparison to a knowledge base of learned contexts.
result Classifier training benefits from automatically discovered contexts, demonstrating quicker learning convergence during contextual changes.
A deep network learns diverse contexts from multi-modal sensor data.
problem Recognizing diverse contexts and activities from multi-modal sensor data.
method Multi-stream temporal convolutional network with contextualization module.
result Deep network achieves optimal recognition rate.
Data collection at a massive scale is becoming ubiquitous in a wide variety of settings, from vast offline databases to streaming real-time information. Learning algorithms deployed in such contexts must rely on single-pass inference, where the data history is never revisited. In streaming contexts, learning must also …
SDF adapts Deep Forest for evolving data streams with active learning.
problem Adapting Deep Forest for evolving data streams.
method Streaming Deep Forest (SDF) with Augmented Variable Uncertainty (AVU) active learning.
result SDF with AVU outperforms other methods trained with all instances by 70% labeling budget.
This paper analyzes diversity measures for streaming data ensembles.
problem Understanding diversity measures for streaming data ensembles.
method Theoretical analysis of diversity measures for streaming data ensembles.
result Analysis provides deeper understanding of diversity and its impact on online ensemble learning.
Online-iForest detects anomalies in streaming data efficiently.
problem Offline anomaly detection methods are impractical for streaming contexts.
method Online-iForest tracks evolving data processes in real-time without periodic retraining.
result Online-iForest outperforms all competitors in efficiency.
Bayesian nonparametric CMS improves frequency estimation for power-law data.
problem Estimating frequencies of low-frequency tokens in power-law data streams.
method Developed a learning-augmented count-min sketch using a normalized inverse Gaussian process prior.
result The approach achieves remarkable performance in estimating low-frequency tokens.
Signatures simplify analysis of evolving data streams.
problem Understanding and analyzing irregular, non-stationary data streams.
method Mathematical signatures reduce noise and preserve key information.
result Signatures manage the exponential scaling of data complexity.
Large scale, streaming datasets are ubiquitous in modern machine learning. Streaming algorithms must be scalable, amenable to incremental training and robust to the presence of non-stationarity. In this work consider the problem of learning ℓ1 regularized linear models in the context of streaming data. In particu…
The study examines how bias affects hypothesis formation in neural networks.
problem Characterizing the impact of bias on hypothesis formation in neural networks.
method An automated data-driven projection pursuit neural network to extract and select features for binary classification.
result The refinement of a working hypothesis converges to a robust multivariate perception of data.
Develops confidence intervals for unique elements in data streams.
problem Analyzing the number of unique elements in data streams.
method Uses Flajolet-Martin algorithms and Chernoff bounds for statistical analysis.
result Shows deep connections with mathematical special functions and extreme value theory.
New robustness certificates for streaming models with a sliding window.
problem Applying robustness certificates to streaming data with correlated inputs.
method Deriving robustness certificates for models using a sliding window over a sequence of potentially correlated inputs.
result Guarantees hold for the average model performance across the entire stream, independent of stream size.
The aim of process discovery, originating from the area of process mining, is to discover a process model based on business process execution data. A majority of process discovery techniques relies on an event log as an input. An event log is a static source of historical data capturing the execution of a business proc…
StreamEnsemble dynamically selects ML models for ST data streams to improve predictive accuracy.
problem Predictive queries over spatiotemporal data streams are challenging due to varying distributions and patterns.
method Dynamic selection and allocation of ML models based on time series distributions and characteristics.
result Significantly outperforms traditional ensemble and single model approaches, reducing prediction error by over 10 times.
A new platform predicts object movements without needing specific context.
problem Predicting the next position of movable objects.
method λ-Architecture for batch and stream analytics, combining for improved accuracy.
result Combining λ-Architecture parts improves overall accuracy and performance.
Streaming ASR with transformer achieves low WER.
problem Real-time ASR with speech recognition.
method Time-restricted self-attention and triggered attention mechanisms.
result 2.8% and 7.2% WER for LibriSpeech test data.
A new algorithm reduces memory usage for long token attention in streaming applications.
problem Memory inefficiency in computing attention for long documents.
method One-pass streaming algorithm using sublinear space storage.
result Super-efficient memory usage for long token attention.
We bring the theory of rough paths to the study of non-parametric statistics on streamed data. We discuss the problem of regression where the input variable is a stream of information, and the dependent response is also (potentially) a stream. A certain graded feature set of a stream, known in the rough path literature…
New findings show concept drift in data streams implies temporal dependence, affecting model design.
problem Concept drift in data streams challenges existing model design and deployment approaches.
method Developed gradient-descent methods for continuous adaptation without explicit drift detection.
result Gradient-descent methods offer major advantages in accuracy and efficiency for concept-drifting streams.
We adapted the Covertype data set for unsupervised learning.
problem Lack of suitable unsupervised learning data sets.
method Transformed the Covertype data set into the Wilderness Area data set.
result The Wilderness Area data set is more suitable for unsupervised learning.
New analysis for sampling from non-convex distributions with dependent data.
problem Sampling from non-logconcave distributions in stochastic optimization.
method Stochastic Gradient Langevin Dynamics (SGLD) with dependent data streams.
result Sharper and uniform convergence estimates in L1-Wasserstein distance. A number of recent emerging applications call for studying data streams, potentially infinite flows of information updated in real-time. When multiple co-evolving data streams are observed, an important task is to determine how these streams depend on each other, accounting for dynamic dependence patterns without impos…
Novel algorithm SAODE improves high-dimensional stream classification in seasonal data.
problem Handling seasonal concept drift in high-dimensional stream classification.
method SAODE classifier that includes time as a super parent to handle seasonal drift.
result SAODE consistently outperforms other methods in stream and concept drift classification.
In statistical learning for real-world large-scale data problems, one must often resort to "streaming" algorithms which operate sequentially on small batches of data. In this work, we present an analysis of the information-theoretic limits of mini-batch inference in the context of generalized linear models and low-rank…
Tensor decompositions are used in various data mining applications from social network to medical applications and are extremely useful in discovering latent structures or concepts in the data. Many real-world applications are dynamic in nature and so are their data. To deal with this dynamic nature of data, there exis…
METEOR learns efficient representations from multi-modal data streams.
problem Efficiently interpreting multi-modal information in complex environments.
method METEOR learns compact representations by sharing parameters within semantically meaningful groups and preserving domain-agnostic semantics.
result METEOR reduces memory usage by around 80% compared to conventional methods.
We consider a decomposition method for compressive streaming data in the context of online compressive Robust Principle Component Analysis (RPCA). The proposed decomposition solves an n-ℓ1 cluster-weighted minimization to decompose a sequence of frames (or vectors), into sparse and low-rank components, from com…
New algorithms for IV regression with streaming data, avoiding matrix inversions.
problem Instrumental variable regression with streaming data.
method Viewing IV regression as a stochastic optimization problem, developing algorithms that avoid matrix inversions and mini-batches.
result Rates of convergence of order O(logT/T) and O(1/T1−ι) for linear models. New method detects when models influence their own drift in real-time data streams.
problem Models can induce concept drift in real-time data streams.
method CheckerBoard Performative Drift Detection (CB-PDD)
result CB-PDD effectively detects performative drift in real-time data streams.
We present a streaming model for large-scale classification (in the context of ℓ2-SVM) by leveraging connections between learning and computational geometry. The streaming model imposes the constraint that only a single pass over the data is allowed. The ℓ2-SVM is known to have an equivalent formulation in …
Pangloss improves entity linking in noisy text environments.
problem Entity linking in non-grammatical, loosely-structured text.
method Combines probabilistic key phrase identification and semantic similarity engine.
result Better than state-of-the-art results (>5% in F1).
A novel approach for cost-sensitive feature acquisition in data streams.
problem Learning scenarios with feature acquisition at a cost.
method Incremental feature acquisition using a context-aware feature-value function in a reinforcement learning paradigm.
result The proposed method efficiently acquires features and makes accurate predictions.
StreaMRAK improves KRR for streaming data.
problem Streaming data with memory constraints.
method Divides problem into levels of resolution, sub-sampling.
result Efficiently integrates new samples, reduces memory and complexity.
We propose a computationally efficient random walk on a convex body which rapidly mixes and closely tracks a time-varying log-concave distribution. We develop general theoretical guarantees on the required number of steps; this number can be calculated on the fly according to the distance from and the shape of the next…
EMR learns to read and remember from streaming data for QA.
problem Scalable QA from streaming data without knowing questions.
method End-to-end deep network model (EMR) with RL agent for memory management.
result EMR achieves significant improvements over existing methods on synthetic and real-world datasets.
An important metric of users' satisfaction and engagement within on-line streaming services is the user session length, i.e. the amount of time they spend on a service continuously without interruption. Being able to predict this value directly benefits the recommendation and ad pacing contexts in music and video strea…
Two new approaches for point prediction in streaming data, showing consistency and performance.
problem Predicting points in streaming data without a true model.
method Count-Min sketch and Gaussian process priors with random bias.
result CMS-based estimates are consistent under i.i.d. samples assumption.
New estimator uses clustering to improve off-policy evaluation accuracy.
problem Improving off-policy evaluation accuracy when logging and evaluation policies differ.
method Proposes an estimator that shares information across similar contexts using clustering.
result Clustering contexts improves estimation accuracy, especially in deficient information settings.
New insights into how depth and width affect in-context learning in deep models.
problem Understanding how various resources impact in-context learning in deep models.
method Analyzed linear regression in a deep linear self-attention model, varying resources like depth, width, context length, and training steps.
result Increasing depth improves in-context learning even at infinite context length, contrary to previous findings.
A new method detects concept drift without true labels.
problem Detecting concept drift in unsupervised settings.
method Student-teacher learning paradigm for drift detection.
result The method outperforms state-of-the-art approaches in experiments.
Approach to detect and adapt to concept drift in unlabeled streaming data.
problem Detect and adapt to concept drift in high-dimensional, noisy, low-context data.
method Density-based clustering for virtual drift and weak supervision for real drift.
result 90% precision in detecting and adapting to concept drift for 4 years after initial deployment.
Adversarial attacks can fool algorithmic trading systems.
problem Adversarial perturbations can manipulate algorithmic trading models.
method Real-time adversarial attacks on trading algorithms using universal perturbations.
result Perturbations can fool trading algorithms at unseen data points.
Bayesian context trees capture complex dependencies in categorical sequences.
problem Complex, long-range dependencies in categorical sequences are not well captured by simple models.
method Parsimonious Bayesian context trees with model-based agglomerative clustering for efficient inference.
result The proposed framework outperforms existing models on real-world data.
Paper tackles maritime traffic prediction for destinations and times.
problem Predicting destinations and arrival times of ships in real-time.
method Used ensemble learning (RF, GBDT, XGBoost, ERT) for destination prediction and feed-forward neural networks for ETA prediction.
result Achieved 97% accuracy for destination prediction and 90% accuracy for ETA prediction.
We propose scalable methods to execute counting queries in machine learning applications. To achieve memory and computational efficiency, we abstract counting queries and their context such that the counts can be aggregated as a stream. We demonstrate performance and scalability of the resulting approach on random quer…
This paper introduces online algorithms to estimate robust geometric median in large data streams.
problem Detecting outliers in large data sets using robust statistical measures.
method Online stochastic Newton methods for estimating the geometric median.
result Rates of convergence for online estimation of the geometric median.
A neural network learns word-referent associations across various contexts.
problem Learning word-referent associations in different contexts.
method A biologically inspired multi-layered architecture that takes images and phonemes as input, builds representations, and adjusts prototypes based on current context.
result The model achieves up to 78% accuracy in ambiguous situations and mimics human learning patterns.