This paper uses unsupervised learning and dimensionality reduction to optimize sewer system control.
problem Challenges in controlling large sewer systems efficiently.
method Divide sewer system into subcatchments, collect factors, cluster, apply PCA, simulate control scenarios.
result Priority control measures applied to clusters with similar hydraulic characteristics yield the best overflow reduction.
DeepCSO model forecasts CSO events from multiple sewer structures in near real-time.
problem Forecasting Combined Sewer Overflow (CSO) events at a citywide level.
method Multi-task deep learning model combining data-driven and deterministic methods.
result Deep learning model outperforms traditional methods in CSO event forecasting.
Paper proposes ICWT method to balance sewer flow and WWTP capacity.
problem Balancing spatial mismatch of sewer flow and WWTP capacity.
method Hydraulic model and LSTM for multi-step ahead water level prediction.
result LSTM outperforms other models in predicting water levels.
Random forest model predicts sewer pipe deterioration with high accuracy.
problem Challenges in predicting and scheduling sewer pipe inspections.
method Random forest classification model for sewer pipe condition prediction.
result Model achieved excellent AUC of 0.81 in a case study for City of LA.
New model shows most users on Q&A site Stack Overflow ignore badges.
problem Understanding user behavior in Q&A websites with badges.
method Probabilistic model applied to Stack Overflow data.
result Majority of users remain apathetic to badges but still contribute.
Stack Overflow is the most popular Q&A website among software developers. As a platform for knowledge sharing and acquisition, the questions posted in Stack Overflow usually contain a code snippet. Stack Overflow relies on users to properly tag the programming language of a question and it simply assumes that the progr…
Deep neural network predicts semantic labels for source code.
problem Difficulty in labeling and understanding new programming languages and functionalities.
method Language-agnostic deep convolutional neural network trained on Stack Overflow code snippets.
result Mean area under ROC of 0.957 and top-1 accuracy of 86.6% on Github code documents.
Study investigates micro-event detection on FLOSS version releases from Stack Overflow.
problem Detecting micro-events in FLOSS version release events from textual messages.
method Developed pipelines using LDA topic modeling, hSBM topics, and sentiment analysis; optimized feature spaces with RFECV; evaluated models with statistical analysis.
result Found characteristic changes in topics or sentiment features before or after FLOSS version releases.
WrapNet optimizes inference for low-resolution neural networks by using 8-bit additions.
problem Reducing multiplication complexity in low-resolution neural networks.
method Adapting neural networks to use low-resolution (8-bit) additions in accumulators, with a cyclic activation layer and overflow penalty regularizer.
result Achieves comparable classification accuracy to 32-bit counterparts using low-resolution additions.
CoNCRA uses CNN to find code snippets matching developer intent.
problem Finding relevant code snippets using general search engines.
method Convolutional Neural Network approach to code retrieval.
result Improved code retrieval by 5% on average, top 3 positions 80% of the time.
LiteMORT reduces memory usage for GBDT models by 30% with improved accuracy.
problem Memory inefficiency in GBDT models, especially with adaptive compact distributions.
method Share memory, implicit merging, adaptive histogram resizing.
result Significant reduction in memory usage with improved accuracy.
Determining the programming language of a source code file has been considered in the research community; it has been shown that Machine Learning (ML) and Natural Language Processing (NLP) algorithms can be effective in identifying the programming language of source code files. However, determining the programming lang…
Deep autoencoder detects anomalies in wastewater sensor data.
problem Anomaly detection in in-situ wastewater sensor data.
method 1D Convolutional Neural Network (CNN) autoencoder for anomaly detection.
result Validation on in-sewer process monitoring data shows effective anomaly detection.
New algorithm reduces costs and latency for large language model inference.
problem Optimizing inference costs and latency for large language models with GPU constraints.
method Formulated as an online scheduling problem with endogenous memory growth, introduced fluid model and WAIT algorithms.
result Reduced costs and latency, especially in near-overloaded and overloaded regimes.
We present a semi-supervised learning algorithm for learning discrete factor analysis models with arbitrary structure on the latent variables. Our algorithm assumes that every latent variable has an "anchor", an observed variable with only that latent variable as its parent. Given such anchors, we show that it is possi…
People are increasingly relying on the Web and social media to find solutions to their problems in a wide range of domains. In this online setting, closely related problems often lead to the same characteristic learning pattern, in which people sharing these problems visit related pieces of information, perform almost …
In this study, we investigate the limits of the current state of the art AI system for detecting buffer overflows and compare it with current static analysis tools. To do so, we developed a code generator, s-bAbI, capable of producing an arbitrarily large number of code samples of controlled complexity. We found that t…
New method reduces SBL complexity from cubic to linear, improving scalability.
problem Sparse Bayesian Learning's high computational complexity for large feature spaces.
method DQN-SBL, a diagonal Quasi-Newton method for SBL.
result DQN-SBL achieves competitive generalization with sparse models, scaling well to large-scale problems.
Online knowledge repositories typically rely on their users or dedicated editors to evaluate the reliability of their content. These evaluations can be viewed as noisy measurements of both information reliability and information source trustworthiness. Can we leverage these noisy evaluations, often biased, to distill a…
A new method for estimating probabilities and risks using Markov processes.
problem Computational difficulties in classical importance sampling for latent Markov models.
method Proposes a new importance sampling framework that minimizes estimator variance.
result Shows logarithmic efficiency of the proposed estimator.
This paper considers a transmission control problem in network-coded two-way relay channels (NC-TWRC), where the relay buffers random symbol arrivals from two users, and the channels are assumed to be fading. The problem is modeled by a discounted infinite horizon Markov decision process (MDP). The objective is to find…
Deep neural networks are commonly developed and trained in 32-bit floating point format. Significant gains in performance and energy efficiency could be realized by training and inference in numerical formats optimized for deep learning. Despite advances in limited precision inference in recent years, training of neura…
Intelligent AQM uses ECN to predict and control network congestion.
problem Challenges in finding optimal AQM parameters due to network complexity.
method Machine Learning (Neural Network for prediction, Reinforcement Learning for parameter tuning).
result Enhanced performance of AQM using ECN and existing TCP congestion control.
Modeling time series with jumps using neural networks and stochastic processes.
problem Capturing the dynamics of time series with both continuous flows and discrete jumps.
method Introducing Neural Jump Stochastic Differential Equations (Neural JSDEs) that extend Neural Ordinary Differential Equations (Neural ODEs) with a stochastic process term.
result Demonstrated the model's predictive capabilities on various datasets, including Hawkes processes, Stack Overflow awards, medical records, and earthquake monitoring.
Research improves federated text models for next word prediction.
problem Training models on distributed devices efficiently and effectively.
method Employ transfer learning in federated learning for next word prediction.
result Enhancements to current baselines with pretrained embeddings and whole model pretraining.
Optimizes communication in federated learning using rate-distortion theory.
problem Reduces communication cost in federated learning while maintaining model accuracy.
method Applies rate-distortion theory to model updates, proposing distortion as a proxy for accuracy.
result Near-optimal communication reduction, outperforming other methods on a FL benchmark.
Learning from the crowd has become increasingly popular in the Web and social media. There is a wide variety of crowdlearning sites in which, on the one hand, users learn from the knowledge that other users contribute to the site, and, on the other hand, knowledge is reviewed and curated by the same users using assessm…
XLA compiler extension improves memory efficiency for machine learning.
problem Memory constraints limit the scalability of memory-intensive machine learning algorithms.
method Developed an XLA compiler extension that adjusts algorithm data-flow representation to fit memory limits.
result k-nearest neighbour and sparse Gaussian process regression can be run at larger scales.
A framework to compare federated learning algorithms in high-dimensional settings.
problem Comparing the performance of federated learning algorithms in high-dimensional settings.
method Formulating federated learning as a multi-criterion objective and analyzing a linear regression model.
result Federated Averaging with simple client fine-tuning achieves the same asymptotic risk as more intricate approaches and outperforms without personalization.
Deep learning methods are useful for high-dimensional data and are becoming widely used in many areas of software engineering. Deep learners utilizes extensive computational power and can take a long time to train-- making it difficult to widely validate and repeat and improve their results. Further, they are not the b…
This paper explains adversarial examples as feature redundancy abuse.
problem Understanding and mitigating adversarial examples in machine learning.
method Information-theoretic model to explain adversarial attacks.
result Feature redundancy is necessary for adversarial examples.
The fast demographic growth, together with the concentration of the population in cities and the increasing amount of daily waste, are factors that push to the limit the ability of waste assimilation by Nature. Therefore, we need technological means to make an optimal management of the waste collection process, which r…
Score-fPINN tackles high-dimensional FPL equations using fractional score functions.
problem High-dimensional Fokker-Planck-Lévy equations with non-Brownian processes.
method Fractional score function and Physics-informed neural networks (PINN) to solve CoD and numerical overflow.
result Effective solution to high-dimensional FPL equations without fractional Laplacian.
Deep learning detects cyber-attacks in smart grid systems.
problem Cyber-attacks on smart grid systems.
method Deep learning-based intrusion detection system trained on industrial dataset.
result Proposed system outperforms Naive Bayes, SVM, and Random Forest.
The paper proposes a method to create robust neural networks for automated driving.
problem Creating neural networks that can accurately predict road conditions and distances.
method The method introduces a non-standard loss function with tolerance to account for label variability and allows for deviations from labels.
result The proposed method results in a neural network that can robustly predict road conditions and distances, even with small label variations.
This paper considers a cross-layer adaptive modulation system that is modeled as a Markov decision process (MDP). We study how to utilize the monotonicity of the optimal transmission policy to relieve the computational complexity of dynamic programming (DP). In this system, a scheduler controls the bit rate of the m-qu…
Improves matrix multiplication throughput for asymmetric bit-width operands.
problem Matrix multiplications between asymmetric bit-width operands, especially 8- and 4-bit, are not efficiently handled by existing SIMD instructions.
method Proposes a new SIMD matrix multiplication instruction that uses mixed precision on inputs (8- and 4-bit) and accumulates into 16-bit output, improving throughput.
result Offers 2x improvement in throughput compared to existing symmetric-operand-size instructions, with negligible overflow.
Novel algorithm for privacy-preserving distributed learning in analog domain.
problem Privacy-preserving distributed learning over analog data.
method Proposes a novel algorithm for analog data, leveraging real/complex number representation and information-theoretic security metrics.
result Demonstrates a fundamental trade-off between privacy and accuracy in analog domain distributed learning.