Paper combines RNN and signatures for learning functions on streamed multimodal data.
problem Learning functions on streamed multimodal data.
method Hybrid Logsig-RNN algorithm combining signatures and RNN.
result Hybrid algorithm achieves outstanding accuracy with superior efficiency and robustness.
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…
Paper introduces fast botnet detection from web server logs.
problem Botnets cause various malicious activities; fast detection is needed.
method Inspired by PCA, uses Lanczos method to improve detection speed.
result Lanczos method significantly reduces time complexity for botnet detection.
Improved single-pass streaming MAB regret bound to O(K^1/3T^2/3).
problem Minimize regret in single-pass streaming multi-armed bandits with sublinear memory.
method Improved regret lower bound to Ω(K^1/3T^2/3) and upper bound to O(K^1/3T^2/3).
result Achieved tight regret bound of O(K^1/3T^2/3) for algorithms with o(K) memory.
We study the statistical and computational aspects of kernel principal component analysis using random Fourier features and show that under mild assumptions, O ( n log n ) O(\sqrt{n} \log n) O ( n log n ) features suffices to achieve O ( 1 / ε 2 ) O(1/ε^2) O ( 1/ ε 2 ) sample complexity. Furthermore, we give a memory efficient streaming algorithm based on classical Oja…
Improved Clipped-SGD achieves near-optimal heavy-tailed statistical estimation in streaming settings.
problem High-dimensional heavy-tailed statistical estimation in streaming with memory constraints.
method Stochastic convex optimization with Clipped-SGD, proving near-optimal sub-Gaussian statistical rates.
result Clipped-SGD achieves an error of T r ( Σ ) + T r ( Σ ) ∥ Σ ∥ 2 log ( log ( T ) δ ) T \sqrt{\frac{\mathsf{Tr}(Σ)+\sqrt{\mathsf{Tr}(Σ)\|Σ\|_2}\log(\frac{\log(T)}δ)}{T}} T Tr ( Σ ) + Tr ( Σ ) ∥Σ ∥ 2 l o g ( δ l o g ( T ) ) with probability 1 − δ 1-δ 1 − δ . MaxSketch improves distinct counting in high-dimensional, noisy data streams.
problem Estimating distinct elements in high-dimensional, noisy data streams.
method MaxSketch uses random Gaussian projections to estimate distinct counts.
result MaxSketch achieves ( 1 + ε ) (1+\varepsilon) ( 1 + ε ) factor estimation with m = O ~ ( log n / ε 2 ) m = \widetilde{O} (\log n/\varepsilon^2) m = O ( log n / ε 2 ) random projections. A new data-oblivious sketch for logistic regression reduces data size while maintaining approximation accuracy.
problem Efficiently solving logistic regression in one pass over a data stream.
method Data-oblivious sketching approach that reduces data size to poly(μdlog n) weighted points.
result Sketching reduces data size significantly and provides approximation guarantees.
Paper improves submodular streaming with better approximation, less memory, and lower complexity.
problem Maximizing submodular functions in streaming with a cardinality constraint.
method Sieve-Streaming++ with one pass, O ( k ) O(k) O ( k ) memory, and ( 1 / 2 ) (1/2) ( 1/2 ) -approximation; adaptive complexity reduction. result Achieves ( 1 / 2 ) (1/2) ( 1/2 ) -approximation with O ( k ) O(k) O ( k ) memory and low adaptive complexity. Anomaly detection system for network logs using ELK, Spark, and Hadoop.
problem Detecting anomalies in network connection logs.
method Streaming architecture, ELK, Spark, Hadoop for data collection and analysis; unsupervised learning with clustering and classification algorithms.
result Identifies subtle variances in log data, highlighting outliers.
In this paper, we study the problem of learning a mixture of Gaussians with streaming data: given a stream of N N N points in d d d dimensions generated by an unknown mixture of k k k spherical Gaussians, the goal is to estimate the model parameters using a single pass over the data stream. We analyze a streaming version of …
New algorithm detects and handles concept drift in data streams.
problem Handling concept drift in data streams for timely predictions.
method Hybrid Forest algorithm combining Hoeffding Trees and fast startup.
result The algorithm outperforms other methods in classification and regression tasks.
A flexible nonparametric online changepoint detection algorithm for high-frequency data.
problem Detecting changes in real-time in high-frequency data streams with limited computational resources.
method NP-FOCuS, a sequential likelihood ratio test for a change in the empirical cumulative density function, using functional pruning.
result NP-FOCuS outperforms current nonparametric online changepoint techniques in various settings.
TDX predicts evolving distributions from streaming data.
problem Predicting density at future time points in evolving data.
method Dynamic basis expansion with isometric log-ratio transformation.
result TDX accurately captures monotonous drift patterns.
Combines offline causal inference and online bandit learning for better decision-making.
problem Making adaptive decisions using both logged and streaming data to avoid user harm.
method Unified offline causal inference and online learning algorithms, deriving bounds on decision accuracy.
result First upper regret bound for forest-based online bandit algorithms.
Sublinear memory sketch finds nearest neighbors in streaming data.
problem Finding nearest neighbors in large datasets with limited memory.
method Combines LSH, online kernel density estimation, and compressed sensing to achieve sublinear memory.
result Achieves sublinear memory performance on stable queries, reporting nearest neighbors efficiently.
New algorithm reduces memory usage for multi-pass bandit problems.
problem Memory-efficient multi-pass bandit algorithms for large action spaces.
method Develops a B B B -pass algorithm with O ( 1 ) O(1) O ( 1 ) memory that achieves optimal regret. result Sharp memory-regret trade-off: O ( 1 ) O(1) O ( 1 ) memory suffices for Θ ( T 1 / 2 ) Θ(T^{1/2}) Θ ( T 1/2 ) regret in B B B passes. Efficiently trains GMMs for streaming data with SGD, addressing local optima and numerical instabilities.
problem Local optima and numerical instabilities in training GMMs for high-dimensional streaming data.
method Stochastic Gradient Descent (SGD) with adaptive annealing and exponential-free approximation.
result SGD approach trains GMMs without k-means initialization and outperforms sEM for high-dimensional data.
The paper tackles robust submodular maximization under matroid constraints, providing approximation algorithms for summary extraction.
problem Maximizing submodular functions while ensuring high value even after deletions.
method Constant-factor approximation algorithms for centralized and streaming settings, considering both non-monotone and monotone objectives.
result Approximation algorithms with space complexity depending on matroid rank and deleted elements, achieving improved factors in monotone cases.
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 ( log T / T ) \mathcal{O}(\log T/T) O ( log T / T ) and O ( 1 / T 1 − ι ) \mathcal{O}(1/T^{1-ι}) O ( 1/ T 1 − ι ) for linear models. Automated process discovery is a class of process mining methods that allow analysts to extract business process models from event logs. Traditional process discovery methods extract process models from a snapshot of an event log stored in its entirety. In some scenarios, however, events keep coming with a high arrival…
New methods improve anomaly detection from large streaming data.
problem Anomaly detection in large streaming data fails with current methods.
method Two novel randomized algorithms (rPS and gPS) for better detection of correlated anomalies.
result High and balanced recall and estimated accuracy for anomaly detection.
We present a sparse analogue to stochastic gradient descent that is guaranteed to perform well under similar conditions to the lasso. In the linear regression setup with irrepresentable noise features, our algorithm recovers the support set of the optimal parameter vector with high probability, and achieves a statistic…
The paper develops algorithms to find a robust summary of data under deletion, achieving good approximation guarantees.
problem Finding a summary of data that remains valuable even after some elements are deleted.
method Constant-factor approximation algorithms for deletion robust submodular maximization under matroid constraints.
result The algorithms provide good approximation guarantees for both centralized and streaming settings.
Analysis of an organization's computer network activity is a key component of early detection and mitigation of insider threat, a growing concern for many organizations. Raw system logs are a prototypical example of streaming data that can quickly scale beyond the cognitive power of a human analyst. As a prospective fi…
Federated online learning for streaming data with privacy and efficiency.
problem Analyzing continuous, heterogeneous data streams in a privacy-preserving manner.
method Personalized models for each data source, subgroup assumption, penalized renewable estimation, proximal gradient descent.
result Effective model for distributed multi-source streaming data analysis with privacy and efficiency.
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…
A federated model predicts failures using multi-stream incomplete data.
problem Insufficient data for reliable prognostic models in multi-stream applications.
method Federated data fusion, multivariate functional principal component analysis, (log)-location-scale regression model, federated algorithm.
result Performance is as good as classic non-federated models and better than individual models.
New method for estimating quantiles in streams of data.
problem Estimating quantiles in real-time data streams.
method Confidence sequences for quantiles based on i.i.d. observations.
result Explicit expressions for intervals with fast shrinking widths.
We consider the problem of learning convex aggregation of models, that is as good as the best convex aggregation, for the binary classification problem. Working in the stream based active learning setting, where the active learner has to make a decision on-the-fly, if it wants to query for the label of the point curren…
M-FISHER detects and adapts to streaming data shifts with statistical validity and stability.
problem Detecting and adapting to distributional shifts in streaming data.
method Constructs an exponential martingale from non-conformity scores and applies Ville's inequality for detection. Fisher-preconditioned updates for adaptation.
result Establishes M-FISHER as a principled approach for robust, anytime-valid detection and geometrically stable adaptation.
New method detects anomalies in computing centers' logs.
problem Anomaly detection in continuously changing log data for predictive maintenance.
method Evolving granular classifiers using Fuzzy-set-Based evolving Modeling and evolving Granular Neural Network.
result Classification model prioritizes maintenance based on anomaly severity.
Improved online changepoint detection for autocorrelated data.
problem Changepoint detection in autocorrelated data with false positives or delays.
method Generalized Likelihood Ratio (GLR) statistic for AR(p) processes, online focus algorithm.
result AR(p)-focus algorithm achieves high detection power in correlated data.
Investor optimizes wealth in a market with non-traded endowment, deriving expansions up to second order.
problem Optimizing wealth in an incomplete financial market with a non-traded endowment.
method Duality techniques and Kunita-Watanabe projections for deriving expansions up to second order.
result Derives expansions of the primal value function and optimal wealth process up to second order with respect to the non-traded endowment units.
Semi-supervised GANs with log-signatures improve credit card fraud detection.
problem Detecting fraud in large, complex financial transaction data streams.
method Conditional GANs with Bayesian inference and log-signatures for robust feature encoding.
result Consistent improvements over benchmarks in global and domain-specific metrics.
SGMM clusters data in one pass, reducing dimensionality.
problem Clustering high-dimensional data efficiently.
method One-pass sparsification of Gaussian mixture model.
result SGMM achieves clustering accuracy with reduced computational cost.
New sublinear sketches improve ANN and KDE for massive data streams.
problem Efficiently approximate nearest neighbors and kernel density estimation in large datasets.
method Developed sublinear space and query time algorithms for ANN and A-KDE in streaming and sliding-window models.
result Achieved near-optimal trade-offs between memory size and approximation error for ANN.
New method for evaluating sequential recommendations with lower variance.
problem Evaluating good sequences of music, video, news, and e-commerce recommendations.
method Proposes a new counterfactual estimator for sequential reward interactions with lower variance and asymptotic unbiasedness.
result Our method outperforms existing methods in bias and data efficiency for sequential track recommendations.
A new method classifies multiple correlated data streams simultaneously.
problem Classifying multiple correlated data streams in practical scenarios.
method Double-Coupling Support Vector Machines (DC-SVM) considers both internal and external correlations.
result The proposed method outperforms traditional methods on artificial and real-world data streams.
New algorithms minimize regret in streaming MAB with memory constraints.
problem Minimizing regret in single-pass streaming MAB with limited memory.
method Developed two algorithms with tight regret bounds for different memory sizes.
result Established tight gap-dependent regret bounds for streaming MAB.
A new method for estimating SW from streaming data.
problem Estimating Wasserstein distance from sample streams.
method Introducing a streaming estimator of the 1DW and applying it to all projections.
result Stream-SW achieves more accurate approximation of SW than random subsampling.
A new method detects sparse changes in high-dimensional data streams using tailored PCA projections.
problem Detecting sparse changes in high-dimensional data streams.
method Tailored PCA projections for online change detection.
result High efficiency in detecting even very sparse changes in mean, variance, and correlation.
Online PCA phase transition depends on n / d log ( d ) n/d\log(d) n / d log ( d ) , not just n / d n/d n / d .
problem Understanding the phase transition in online PCA.
method Study of Oja's algorithm for online PCA.
result Phase transition in correlation between estimated and true eigenvector.
We create coresets for Gaussian Mixture Models of any shape.
problem Approximating the negative log-likelihood of Gaussian Mixture Models with arbitrary shapes.
method Reduction to projective clustering problems, maintaining coresets for streaming and dynamic data.
result The coreset size is ( log n ) O ( 1 ) / ε 2 (\log n)^{O(1)}/\varepsilon^2 ( log n ) O ( 1 ) / ε 2 , and can be computed in near-linear time. We study streaming principal component analysis (PCA), that is to find, in O ( d k ) O(dk) O ( d k ) space, the top k k k eigenvectors of a d × d d\times d d × d hidden matrix Σ \bf Σ Σ with online vectors drawn from covariance matrix Σ \bf Σ Σ . We provide global \textit{global} global convergence for Oja's algorithm which is popularly used in practice but lacks t…
A new model detects financial bubbles with high accuracy.
problem Quantifying and detecting financial bubbles.
method Hyped Log-Periodic Power Law Model (HLPPL) with sentiment scores and hype index.
result Achieved an average annualized return of 34.13% during backtesting.
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.
Data stream clustering tackles real-time data processing challenges.
problem Real-time processing of data streams with less prior information.
method Review of data stream clustering algorithms and their characteristics.
result Comparison and analysis of data stream clustering algorithms.