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.
The paper proposes a SeqGAN model to generate balanced log messages for anomaly detection.
problem Imbalanced log data makes anomaly detection difficult.
method SeqGAN for generating balanced log messages, Autoencoder for feature extraction, GRU for anomaly detection.
result Oversampling and balancing data improves anomaly detection accuracy.
Paper proposes a log-domain training method to reduce neural network complexity.
problem High computational complexity in training deep neural networks limits real-time training.
method End-to-end training and inference scheme using approximate logarithmic operations in the log-domain.
result 16-bit log-based training achieves within 1% accuracy of floating-point baselines.
EnLSTM network improves log generation from small datasets.
problem Generating well logs from small datasets with high accuracy.
method Combining ENN and C-LSTM networks with perturbation methods.
result 34% reduction in mean-square-error compared to existing models.
Log-Normal Multiplicative Dynamics improves low-precision training of neural networks.
problem Training large neural networks with low precision is unstable.
method Derive a Bayesian learning rule with log-normal posterior distributions and multiplicative updates.
result LMD achieves stable and accurate training for Vision Transformer and GPT-2.
Softmax emerges naturally in neural networks as a measure of conditional mutual information.
problem The artificial nature of softmax in neural networks.
method Information-theoretic perspective to derive log-softmax and evaluate conditional mutual information.
result Training deterministic neural networks through log-softmax maximises conditional mutual information.
Survival regression method improves log-likelihood scores.
problem Improper scoring rules in survival regression models.
method SurvivalMonotonic-net (SuMo-net) with monotonic neural networks.
result SuMo-net achieves state-of-the-art log-likelihood scores.
Paper optimizes deep neural networks for nonparametric estimation without log-sacrifice.
problem Optimizing deep neural networks for nonparametric estimation without redundant log-factors.
method Explicitly constructed network estimator based on tensor product B-splines, derived upper bounds for minimax risk, and asymptotic distributions.
result Upper bounds for the L2 minimax risk become optimal without log-sacrifice. ResNets approximate log-Gaussian at initialization, improving network performance.
problem Understanding the initialization behavior of deep neural networks like ResNets.
method Analyzing ReLU ResNets in the infinite-depth-and-width limit, showing log-Gaussian behavior.
result ResNets at initialization exhibit hypoactivation and interlayer correlations, which are not captured by Gaussian limits.
Corrects pseudo log-likelihood method issues in various applications.
problem Log-likelihood function unbounded issues in pseudo log-likelihood methods.
method Provided a counterexample and corrected algorithms in previous literature.
result Ensured well-definedness of maximum pseudo log-likelihood estimation.
PresGANs improve GANs by mitigating mode collapse and enhancing log-likelihood.
problem GANs struggle with mode collapse and lack a reliable way to evaluate generalization.
method PresGANs add noise to density networks and use entropy regularization to stabilize training and capture all modes.
result PresGANs reduce the gap in predictive log-likelihood between GANs and VAEs.
This work improves neural network calibration using explicit regularization.
problem Improving predictive uncertainty in neural networks.
method Introducing a probabilistic calibration measure and exploring explicit regularization techniques.
result Explicit regularization improves log-likelihood and predictive uncertainty.
The log-likelihood loss in heteroscedastic neural networks can lead to poor parameter estimates.
problem Capturing aleatoric uncertainty in deep learning models.
method Examine the log-likelihood loss in conjunction with gradient-based optimizers and propose an alternative formulation, β-NLL. result Using an appropriate β largely mitigates the issue of poor parameter estimates. 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.
New method identifies drivers from car logs without reverse-engineering CAN protocol.
problem Identifying drivers from in-vehicle network logs without access to exact signal semantics.
method Machine learning techniques applied to off-the-shelf data.
result Driver re-identification accuracy of 75-85% on a dataset of 33 drivers.
A new network log-ARCH model improves stock market volatility forecasting.
problem Improving stock market volatility forecasting accuracy.
method Dynamic network autoregressive conditional heteroscedasticity (ARCH) model integrating lagged and adjacent node volatility information.
result The model shows significant improvements in forecasting accuracy compared to univariate log-ARCH models.
Improves sequence modeling with a flow-based recurrent mixture density network.
problem Sequence modeling and sequence-to-sequence mapping applications.
method Generalized recurrent mixture density networks using normalized flow transformations.
result Significantly improved fit to image sequences measured by log-likelihood.
This paper improves SNN training by using multiple sample compartments.
problem Training SNNs with single-sample estimators leads to inaccurate log-likelihood estimates.
method Proposes a GEM-based online learning algorithm that uses multiple independent spiking signals.
result Significant improvements in log-likelihood, accuracy, and calibration with multiple compartments.
Graph neural networks detect anomalies in object-centric business processes.
problem Detecting anomalies in graph-like business processes.
method Graph convolutional autoencoder architecture for anomaly detection.
result Promising performance in detecting anomalies at the activity type and attributes level.
Residual Flows improve flow-based models for density estimation.
problem Density estimation using flow-based models with biased log-density estimates.
method Proposed a Russian roulette estimator for unbiased log-density estimation and used an alternative infinite series for gradient calculation. Improved invertible residual blocks with activation functions avoiding derivative saturation and generalized Lipschitz condition to induced mixed norms.
result Residual Flows achieve state-of-the-art performance on density estimation and outperform coupling block networks in joint generative and discriminative modeling.
Enhances Cox model for survival analysis with symbolic non-linear log-risk functions.
problem Limited interpretability and non-linearity in traditional Cox models.
method Introduces GCPH model using Kolmogorov-Arnold Networks for symbolic non-linear log-risk functions.
result GCPH achieves competitive performance and superior interpretability.
This paper detects anomalies in cellular network traffic using hybrid methods.
problem Detecting anomalies in network traffic for security and analysis.
method Hybrid method combining GARCH, K-means, and Neural Network.
result Anomaly detection in cellular network traffic successfully achieved.
In deep neural network, the cross-entropy loss function is commonly used for classification. Minimizing cross-entropy is equivalent to maximizing likelihood under assumptions of uniform feature and class distributions. It belongs to generative training criteria which does not directly discriminate correct class from co…
The paper studies recovering hidden nearest neighbor graphs in large networks.
problem Discovering strong ties in social networks and assembling genome subsequences.
method Maximum likelihood estimator for recovering hidden 2k-nearest neighbor graphs. result The maximum likelihood estimator achieves asymptotic recovery guarantees under specific conditions.
Dividing deep learning models for consistent anomaly detection in changing log data.
problem Anomaly detection methods fail when log data types change, leading to false negatives.
method Divide deep learning models based on log data correlation and extract correlations.
result Continues anomaly detection accuracy even when log data changes.
We show that the standard stochastic gradient decent (SGD) algorithm is guaranteed to learn, in polynomial time, a function that is competitive with the best function in the conjugate kernel space of the network, as defined in Daniely, Frostig and Singer. The result holds for log-depth networks from a rich family of ar…
We explore how neural networks train to zero loss, focusing on initial scale.
problem Understanding neural network training dynamics and zero loss.
method Macroscopic limits analysis of gradient descent dynamics.
result Gradient descent can drive deep neural networks to zero loss regardless of initialization.
Deep signature/log-signature FBSDE algorithm improves accuracy and training time.
problem Solving FBSDEs with state and path dependent features.
method Incorporates deep signature/log-signature transformation into RNN model.
result Improves accuracy and training time compared to existing methods.
The main task in oil and gas exploration is to gain an understanding of the distribution and nature of rocks and fluids in the subsurface. Well logs are records of petro-physical data acquired along a borehole, providing direct information about what is in the subsurface. The data collected by logging wells can have si…
A major problem for the learning of Bayesian networks (BNs) is the exponential number of parameters needed for conditional probability tables. Recent research reduces this complexity by modeling local structure in the probability tables. We examine the use of log-linear local models. While log-linear models in this con…
New algorithm reconstructs sparse networks in subquadratic time.
problem Reconstructing sparse networks from limited data.
method Stochastic second neighbor search to bypass quadratic complexity.
result Subquadratic time complexity, up to O(N3/2logN). We study a model of wealth dynamics [Bouchaud and Mézard 2000, \emph{Physica A} \textbf{282}, 536] which mimics transactions among economic agents. The outcomes of the model are shown to depend strongly on the topological properties of the underlying transaction network. The extreme cases of a fully connected and a ful…
Study on the geometric Dyson Brownian motion of non-square matrix products.
problem Understanding the spectrum of a product of non-square random matrices.
method Proportional depth-width limit followed by mean-field limit, solving Burgers equation.
result Free log-normal law is obtained in the identity-start case.
Proposes a deep neural network for multi-dimensional functional data classification.
problem Classifying multi-dimensional functional data with non-Gaussian distributions.
method Trains a deep neural network on the principle components of the training data.
result FDNN achieves minimax optimality when log density ratio has a locally connected modular structure.
New algorithm samples neural network posteriors efficiently.
problem Challenges of sampling multimodal Bayesian posteriors for neural networks.
method Greedy Bayes method using log-concave coupling of posterior and auxiliary random variable.
result Log-concave coupling facilitates efficient sampling of neuron weights.
We propose a DTCWT ScatterNet Convolutional Neural Network (DTSCNN) formed by replacing the first few layers of a CNN network with a parametric log based DTCWT ScatterNet. The ScatterNet extracts edge based invariant representations that are used by the later layers of the CNN to learn high-level features. This improve…
New ANN method for imputing rounded zeros in compositional data.
problem Imputing missing values in compositional data with rounded zeros.
method Artificial Neural Networks (ANNs) for imputation of compositional data.
result ANNs are competitive or better than conventional methods for imputing rounded zeros.
New method uses SBI to infer magnetorotational properties of isolated pulsars.
problem Constrain magnetorotational properties of isolated Galactic radio pulsars.
method Combines population synthesis with SBI to model neutron star birth and evolution.
result Inferred μlogB=13.10−0.10+0.08, σlogB=0.45−0.05+0.05 for lognormal distributions. Proposes a method for training Bayesian neural networks using synthetic data from Raman and CARS spectra.
problem Limited real observations in Raman and CARS spectroscopy.
method Log-Gaussian Gamma Processes and Bayesian Neural Networks.
result Trained Bayesian neural networks provide accurate estimates of Raman and CARS spectra with uncertainty quantification.
Lower bounds on measurements needed for compressive sensing with generative models.
problem Determining the minimum number of measurements required for accurate recovery of signals from generative models.
method Algorithm-independent lower bounds using minimax statistical analysis.
result The necessary number of measurements scales as Ω(klogL) for L-Lipschitz models and Ω(kdlognlogw) for ReLU networks. Deep learning compresses and quantizes log-likelihood ratios for fading channels.
problem Efficiently compress and quantize log-likelihood ratios for fading channels.
method Trains a deep autoencoder network to map log-likelihood ratios to a latent space and reconstruct them.
result Achieves a compression factor of nearly three times with minimal performance loss.
Invertible DenseNets improve model efficiency and performance.
problem Improving model efficiency and performance in neural networks.
method Enforcing invertibility in DenseNets by satisfying the Lipschitz constraint and proposing a learnable concatenation.
result i-DenseNets outperform Residual Flows in negative log-likelihood on various datasets.
Proposes a differentiable LSE-ICNN for modeling multi-well potentials.
problem Modeling multi-well potentials in various scientific domains.
method Log-sum-exponential (LSE) mixture of input convex neural network (ICNN) modes.
result Smooth surrogate that retains convexity within basins and allows gradient-based learning.
VBD improves variational dropout by using a hierarchical prior, enabling better regularization.
problem Improper log-uniform prior in VD causes ill-posed posterior inference.
method Introduces a hierarchical prior with a zero-mean Gaussian distribution and a uniform hyper-prior.
result VBD enables well-posed posterior inference and superior regularization performance.
CANN models improve insurance claim count predictions using telematics data.
problem Improving insurance claim count predictions with telematics data.
method Combining classical actuarial models with neural networks for telematics data.
result CANN models outperform traditional models in predicting insurance claims.
Paper proposes robust estimators for heavy-tailed data with infinite variance.
problem Developing robust estimators for heavy-tailed data with infinite variance.
method Proposes two robust estimators: ridge log-truncated M-estimator and elastic net log-truncated M-estimator.
result Demonstrates robustness of log-truncated estimations over standard estimations through simulations and real data analysis.
Proposes MVG-CRPS for robust multivariate forecasting.
problem Outliers in multivariate forecasting lead to significant errors.
method Integrates CRPS for MVG distributions, optimizing with MVG-CRPS.
result Improves robustness, accuracy, and uncertainty quantification.
Calendar graph neural networks model user behavior with location and time data.
problem Modeling user behavior with location and time information for demographic prediction.
method Graph neural networks with a tripartite network of items, sessions, and locations, and a hierarchical calendar network.
result User embeddings preserve spatial and temporal patterns of various periodicity.