PRETZEL optimizes machine learning prediction serving systems for better performance.
problem Low latency, high throughput, and graceful performance degradation under heavy load in prediction serving systems.
method Introducing a novel white box architecture enabling both end-to-end and multi-model optimizations.
result Average 5.5x reduction in 99th percentile latency, 25x reduction in memory footprint, and 4.7x increase in throughput compared to state-of-the-art approaches.
DeepLight accelerates CTR predictions in ad serving by 46X.
problem Significantly increased serving delay and high memory usage for ad serving.
method Explicitly searching feature interactions, pruning layers, promoting sparsity.
result Accelerates model inference by 46X on Criteo dataset.
HOLMES improves real-time model serving for ICU patients, balancing accuracy and speed.
problem Real-time model serving is crucial in ICU due to urgency and cost.
method Online model ensemble serving framework for healthcare applications.
result HOLMES achieves high accuracy and sub-second latency for model ensemble serving.
Proposes a flexible neural recommendation framework for better prediction performance.
problem Data sparsity, cold start problem, and long-tail distribution in recommendations.
method A modular neural recommendation framework that includes a neural collaborative filtering part and a text processing part as a regularizer.
result Achieves better prediction performance than state-of-the-art text-aware methods using a simple text processing approach.
Random forest model predicts tennis match outcomes with 80% accuracy.
problem Predicting tennis match outcomes before the game starts.
method Used a large database of tennis match information and a random forest model.
result Identified serve strength as a key predictor of match outcome.
The paper introduces uncertainty quantification for NER models.
problem Current NER models lack uncertainty measures, leading to downstream errors.
method Full-Sequence and Subsequence Conformal Prediction framework.
result The method provides formal guarantees about the reliability of model predictions.
A Bayesian agent learns about the structure of a stationary process from ob- serving past outcomes. We prove that his predictions about the near future become ap- proximately those he would have made if he knew the long run empirical frequencies of the process.
This paper improves prediction uncertainty estimation by inferring variation from neuron activation strength.
problem Estimating prediction uncertainty from ensemble methods is expensive and inaccurate.
method Introduced randomness into model training and inferred prediction variation from neuron activation strength.
result Average R squared on MovieLens is 0.56 and on Criteo is 0.81, with strong performance in variation detection.
Empirical analysis serves as an important complement to theoretical analysis for studying practical Bayesian optimization. Often empirical insights expose strengths and weaknesses inaccessible to theoretical analysis. We define two metrics for comparing the performance of Bayesian optimization methods and propose a ran…
The paper proposes a method to create efficient remote monitoring models.
problem Large and complex machine learning models are unsuitable for remote monitoring on edge devices.
method Decompose the model into a simple local monitoring function and a complex correction term evaluated on the server.
result The proposed framework learns monitoring models with significantly reduced complexity that maintain safety.
"How much energy is consumed for an inference made by a convolutional neural network (CNN)?" With the increased popularity of CNNs deployed on the wide-spectrum of platforms (from mobile devices to workstations), the answer to this question has drawn significant attention. From lengthening battery life of mobile device…
Paper measures asymmetric fear network connectedness for risk prediction.
problem Predicting macroeconomic conditions and economic uncertainty.
method Forward-looking measures from bank option prices.
result Asymmetric network structure predicts economic conditions.
BrainSurfCNN predicts task contrasts from resting-state fingerprints, improving accuracy over baseline.
problem Predicting task-evoked activity from resting-state functional connectivity.
method Surface-based convolutional neural network (BrainSurfCNN) with reconstructive-contrastive loss.
result Significantly improved accuracy in predicting task contrasts over baseline.
BusTr predicts bus travel times from real-time traffic forecasts.
problem Improving accuracy of bus travel time predictions.
method Neural sequence model trained on real-time traffic forecasts.
result BusTr outperforms DeepTTE by 30% in Mean Absolute Percentage Error (MAPE).
Deep neural networks reduce weather forecast uncertainty estimation costs.
problem Accurate estimation of weather forecast uncertainty using ensemble prediction systems.
method Modified 3D U-Net architecture and models incorporating temporal data.
result Deep neural networks can estimate weather forecast uncertainty with fewer simulations.
DLHub enables sharing and serving of scientific ML models.
problem Lack of specialized ML systems for scientific applications.
method Self-service model repository and scalable serving capabilities.
result DLHub offers better performance and more capabilities than existing systems.
JD.com uses a new CNN model to improve ad click prediction.
problem Improving CTR prediction for ads with visual content.
method Proposes Category-specific CNN (CSCNN) to incorporate category knowledge early in the feature extraction process.
result CSCNN outperforms existing methods in CTR prediction.
New framework predicts earnings announcements using press release content, surpassing earnings surprises.
problem Predicting stock returns based on earnings press releases.
method Compared traditional and BERT-based embeddings of press releases, finding content as informative as earnings surprises.
result FinBERT yields highest predictive power for earnings announcement returns.
RNNs improve predictive precompute for faster user interface response times.
problem Improving user interface response times in mobile and web applications.
method Application of recurrent neural networks (RNNs) for predictive precompute.
result RNN models improve prediction accuracy and reduce computational cost.
The paper uses XAI to predict RFQ fulfillment accuracy.
problem Improving accuracy in predicting RFQ fulfillment for less liquid asset classes.
method Advanced algorithms like Logistic Regression, Random Forest, XGBoost, and Bayesian Neural Tree.
result Improved accuracy in RFQ fill rate predictions.
The prediction of a stock market direction may serve as an early recommendation system for short-term investors and as an early financial distress warning system for long-term shareholders. Many stock prediction studies focus on using macroeconomic indicators, such as CPI and GDP, to train the prediction model. However…
Deep pNML improves DNN performance and robustness.
problem Improving deep neural network performance and robustness.
method Introduces pNML scheme for DNNs, extending to twice universal solution.
result pNML outperforms ERM and provides robustness against adversarial attacks.
A scalable method for training prediction models in predict-then-optimize
problem Training prediction models in the predict-then-optimize paradigm
method Decision-focused learning pipeline
result Decision quality competitive with state-of-the-art methods while reducing training time
Deep learning models struggle with new data in stock price trend prediction.
problem Stock price trend prediction using Deep Learning models.
method Examination of fifteen state-of-the-art DL models on LOB data, using LOBCAST framework.
result All models show significant performance drop with new data, questioning their market applicability.
FFCP improves FCP's speed without sacrificing accuracy.
problem Inefficient feature transformation in FCP.
method Introduces FFCP using Taylor expansion for faster computation.
result FFCP achieves a 50x speedup with comparable accuracy.
Bayesian method predicts future network configurations from past snapshots.
problem Reconstructing evolving networks from partial observations.
method Bayesian approach using past network snapshots to inform future predictions.
result Method accurately predicts link probabilities and network structure.
New bidirectional model predicts magnetohydrodynamics fields and estimates uncertainty.
problem Predicting multiple fields in magnetohydrodynamics with uncertainty.
method Bidirectional autoregressive latent diffusion approach.
result Model can estimate uncertainty without ground truth using self-supervised consistency.
New approach optimizes sales process for B2B businesses.
problem Optimizing the sales process for B2B businesses.
method Causal Predictive Optimization and Generation with three layers: prediction, optimization, and serving.
result Significant wins over legacy systems in LinkedIn implementation.
The paper uses machine learning to predict cryptocurrency price changes.
problem Predicting significant price changes in cryptocurrency markets.
method Autoencoder-CNN-GANs algorithm for filtering and predicting price fluctuations.
result The model achieves predictive performance in real-time price sequences.
Proposes a probabilistic approach to semi-supervised learning using normalizing flows.
problem Leveraging unlabelled data for semi-supervised learning with limited labelled data.
method Uses a normalizing flow to learn the posterior distribution over predictions for labelled data, serving as a prior for unlabelled data.
result Demonstrates improved performance on various tasks with varying output complexity.
Machine learning improves earnings forecasting accuracy and speed.
problem Improving earnings forecasting accuracy and speed.
method Adopting machine learning models for earnings forecasting.
result Machine learning model outperforms traditional models in accuracy and speed.
Bayesian PINNs solve noisy PDE problems with physics constraints.
problem Uncertainty quantification in noisy PDE problems.
method Bayesian framework combining PINNs and HMC/VI for posterior estimation.
result HMC outperforms VI for noisy data.
DRIFT uses neural flows to replace distributional regression models.
problem Lack of neural network representations for distributional regression models.
method Inverse flow transformations (DRIFT) for distributional regression.
result Neural representations in DRIFT match classical statistical methods in performance.
Conformal Bayes under label shift: post-hoc calibration vs. in-training adaptation
problem Bayesian prediction sets under label shift
method Post-hoc calibration vs. In-training adaptation
result Both strategies achieve valid coverage equally in an unbiased training regime
A new framework for generating predictive features in noisy multivariate time series.
problem Predicting noisy multivariate time series with limited user effort.
method Develops a feature programming framework based on spin-gas dynamical Ising models.
result Validated the method on synthetic and real-world datasets.
We enhance conformal prediction for risk-averse decisions with action-conditional guarantees.
problem Uncertainty quantification and safety guarantees for machine learning decisions.
method Action-conditional conformal prediction, pinball-loss minimization.
result Action-conditional prediction sets optimize risk-averse decision-making.
Paper proposes a new method to evaluate AI model interpretability in bond default prediction.
problem Lack of standardized method to assess inherent interpretability of AI models.
method Uses LIME and SHAP to assess feature contributions in bond default prediction.
result Consistent results with intuitive understanding of model interpretability.
New method attributes feature uncertainty in ML models using cooperative game theory.
problem Lack of feature-level uncertainty attribution in explainable AI.
method Proposes a novel, model-agnostic uncertainty attribution method using cooperative game theory and conformal prediction.
result Demonstrates improved runtime efficiency and practical utility in real-world applications.
Paper uses SSL models' uncertainty to predict audio quality efficiently.
problem Efficiently predicting audio quality in low-resource settings.
method Leverages self-supervised learning models' uncertainty measures.
result Uncertainty measures correlate with MOS scores in SSL models.
The paper critiques existing uncertainty concepts and proposes a new decision-theoretic approach.
problem Incoherence in existing discussions of aleatoric and epistemic uncertainty.
method Decision-theoretic perspective that relates uncertainty, predictive performance, and statistical dispersion.
result Popular information-theoretic quantities can be poor estimators but still useful for guiding data acquisition.
Improved bounds for online prediction with expert advice.
problem Online prediction with expert advice in finite-horizon games.
method Verification arguments from optimal control theory applied to PDEs to find sub- and supersolutions.
result Explicit bounds for any number of experts and horizon, improving upon previous results.
Neural network learns kernel functions for survival analysis and prediction intervals.
problem Predicting survival times for individuals based on similar training subjects.
method Develops a neural network framework to learn kernel functions for kernel survival analysis and uses these to construct valid prediction intervals.
result Neural network survival estimators are competitive with existing methods and provide valid prediction intervals.
The paper introduces a method for creating short proofs of predictions in AI models.
problem Creating reliable and explainable AI predictions.
method Defining robust hollow star numbers and analyzing certificate sizes for various hypothesis classes.
result The certificate coefficient εx precisely controls the sample size needed for predictions. In this paper, we analyze Twitter signals as a medium for user sentiment to predict the price fluctuations of a small-cap alternative cryptocurrency called \emph{ZClassic}. We extracted tweets on an hourly basis for a period of 3.5 weeks, classifying each tweet as positive, neutral, or negative. We then compiled these …
Differentially private conformal prediction improves statistical efficiency.
problem Quantifying uncertainty in private data analysis.
method Introducing differential conformal prediction and developing Differentially Private Conformal Prediction (DPCP).
result DPCP produces tighter prediction sets than existing private split conformal approaches.
CTR prediction in real-world business is a difficult machine learning problem with large scale nonlinear sparse data. In this paper, we introduce an industrial strength solution with model named Large Scale Piece-wise Linear Model (LS-PLM). We formulate the learning problem with L1 and L2,1 regularizers, leadin…
Extends conformal prediction to contrastive learning for better coverage of positive samples.
problem Lack of principled guarantees on coverage in contrastive learning.
method Introduces minimum-volume covering sets with learnable constraints.
result Improves inclusion-exclusion trade-offs in positive and negative samples.
Blockchain data improves asset predictions by 4x compared to LSTM.
problem Improving asset value predictions using blockchain data.
method Modern Deep Learning techniques applied to blockchain account distribution histograms and spatial dataset modeling.
result Error reduction of 4 times with blockchain data compared to LSTM approach.