Classical Machine Learning (ML) pipelines often comprise of multiple ML models where models, within a pipeline, are trained in isolation. Conversely, when training neural network models, layers composing the neural models are simultaneously trained using backpropagation. We argue that the isolated training scheme of ML…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “ML pipeline”
AVATAR uses a surrogate model to quickly evaluate ML pipelines, saving time and resources.
problem Time-consuming evaluation of ML pipelines limits exploration of complex models.
method AVATAR employs a surrogate model to assess pipeline validity without execution.
result AVATAR accelerates ML pipeline evaluation, improving efficiency in complex scenarios.
A rigorous ML pipeline for binary classification in biomedical studies, focusing on pancreatic cancer.
problem Handling bias in ML models for complex biomedical data.
method Customizable ML analysis pipeline with 9 algorithms, hyperparameter optimization, and thorough evaluation.
result Comparison of ML algorithms to ExSTraCS, highlighting interpretability and bias handling.
Modyn automates continuous ML model training on growing datasets.
problem Continuous model retraining is costly and impractical.
method Data-centric ML platform with policies for continuous training.
result Modyn enables high throughput training with sample-level data selection.
The paper proposes a ML workflow for B2B sales prediction.
problem Predicting business to business sales outcomes using subjective human evaluations.
method A two-pipeline ML approach on Azure ML, including data enrichment and model training.
result ML predictions improve accuracy and increase sales value.
Underspecified ML models can behave unpredictably in real-world use.
problem ML models can fail in real-world deployment due to ambiguous predictors.
method Identified underspecification as the cause, showing it affects various ML domains.
result Underspecified models can behave differently in deployment domains.
DeepLine automates ML pipeline generation using reinforcement learning.
problem Automatic generation of end-to-end ML pipelines combining multiple algorithms.
method Deep Reinforcement Learning with hierarchical actions filtering.
result DeepLine outperforms state-of-the-art approaches in accuracy and computational cost.
As machine learning is applied more widely, data scientists often struggle to find or create end-to-end machine learning systems for specific tasks. The proliferation of libraries and frameworks and the complexity of the tasks have led to the emergence of "pipeline jungles" - brittle, ad hoc ML systems. To address thes…
DC-Check: A Data-Centric AI checklist to guide the development of reliable machine learning systemscs.LG
DC-Check helps guide ML development by considering data-centric aspects.
problem Lack of standardized framework for data-centric considerations in ML.
method DC-Check is a checklist-style framework for data-centric AI at ML pipeline stages.
result Promotes thoughtfulness and transparency in ML development.
The paper aims to improve reproducibility of machine learning experiments.
problem Lack of reproducibility in machine learning experiments.
method Investigates factors affecting reproducibility and proposes FAIR data practices.
result Preliminary results show the role of ProvBook in capturing and comparing provenance.
In this demo paper, we introduce the DARPA D3M program for automatic machine learning (ML) and JPL's MARVIN tool that provides an environment to locate, annotate, and execute machine learning primitives for use in ML pipelines. MARVIN is a web-based application and associated back-end interface written in Python that e…
Proposes VEESA pipeline for interpreting ML models with functional data.
problem Interpreting ML models with functional data inputs for high-consequence applications.
method VEESA pipeline using efPCA and PFI.
result Provides explanation of model's use of functional data variability for prediction.
RankML predicts machine learning pipeline performance quickly and accurately.
problem Lack of machine learning experts and high computational costs.
method Meta-learning approach to predict pipeline performance.
result RankML outperforms or matches state-of-the-art approaches with less time and resources.
Paper introduces probabilistic approach to CO layers in ML.
problem Challenges in training CO layers with stochastic gradient descent.
method Probabilistic perspective, approximate differentiation, structured losses.
result InferOpt.jl package for training CO layers.
Hyperparameter tuning of multi-stage pipelines introduces a significant computational burden. Motivated by the observation that work can be reused across pipelines if the intermediate computations are the same, we propose a pipeline-aware approach to hyperparameter tuning. Our approach optimizes both the design and exe…
Much of the work in metalearning has focused on classifier selection, combined more recently with hyperparameter optimization, with little concern for data preprocessing. Yet, it is generally well accepted that machine learning applications require not only model building, but also data preprocessing. In other words, p…
TIER uses extended strain data to improve gravitational wave detection sensitivity.
problem Improving gravitational wave detection sensitivity using extended strain data.
method TIER framework using machine learning to capture extended strain data features.
result Up to 20% improvement in sensitive volume time in LIGO-Virgo-Kagra O3 data.
Study on AutoML robustness with dirty data.
problem Robustness of AutoML-generated pipelines with noisy data.
method Investigated TPOT, H2O, and AutoKeras systems; analyzed accuracy and pipeline structure.
result Dirty data can improve robustness of AutoML solutions.
Develops a machine learning pipeline for learning causal structure in time-series data.
problem Current ML algorithms fail to learn causal structure in time-series data due to lack of temporal order consideration.
method Integrates machine learning with chaos theory using ChaosFEX feature extractor to learn generalized causal structure.
result Successfully learns generalized causal structure in time-series data.
Generating labeled training datasets has become a major bottleneck in Machine Learning (ML) pipelines. Active ML aims to address this issue by designing learning algorithms that automatically and adaptively select the most informative examples for labeling so that human time is not wasted labeling irrelevant, redundant…
There has been considerable growth and interest in industrial applications of machine learning (ML) in recent years. ML engineers, as a consequence, are in high demand across the industry, yet improving the efficiency of ML engineers remains a fundamental challenge. Automated machine learning (AutoML) has emerged as a …
Connected and autonomous vehicles (CAVs) will form the backbone of future next-generation intelligent transportation systems (ITS) providing travel comfort, road safety, along with a number of value-added services. Such a transformation---which will be fuelled by concomitant advances in technologies for machine learnin…
This paper tackles hidden technical debts in fair ML systems for Fintech.
problem Building fair machine learning systems in financial services.
method Examining key stages of ML system development and deployment.
result Technical debts exist in deploying fair ML systems in Fintech.
Rubin LSST DESC uses AI/ML for dark energy research.
problem Challenges in uncertainty quantification and model robustness for AI/ML in DESC.
method Bayesian inference, physics-informed methods, validation frameworks, active learning.
result AI/ML methods are essential but require rigorous evaluation and governance.
fintech-kMC simulates financial platforms for AI/ML model validation.
problem Validation of AI/ML models in real-world financial applications.
method Agent-based model with kinetic Monte Carlo engine.
result Generates realistic synthetic data for testing AI/ML models.
Operations is a key challenge in the domain of machine learning pipeline deployments involving monitoring and management of real-time prediction quality. Typically, metrics like accuracy, RMSE etc., are used to track the performance of models in deployment. However, these metrics cannot be calculated in production due …
Clinical prognostic models derived from largescale healthcare data can inform critical diagnostic and therapeutic decisions. To enable off-theshelf usage of machine learning (ML) in prognostic research, we developed AUTOPROGNOSIS: a system for automating the design of predictive modeling pipelines tailored for clinical…
Shai-am simplifies ML for finance, solving code structure and scalability issues.
problem Challenges in integrating ML for investment strategies, including code structure and scalability.
method Integrates a Python framework with modern open-source technologies to manage containerized pipelines and unified interfaces.
result Facilitates collaborative work in quantitative finance by enhancing reusability and readability.
Adversarial attacks can manipulate ML-aided visualizations, tricking analysts.
problem Adversarial attacks on ML-aided visualizations.
method Identifying attack surface and exemplifying five adversarial attacks.
result Adversaries can induce various attacks, like creating arbitrary and deceptive visualizations.
Paper proposes EEIPU, a memoization-aware BO algorithm to reduce hyperparameter tuning costs.
problem High costs in GPU-days for training and fine-tuning language models.
method Memoization-aware Bayesian Optimization (EEIPU) algorithm in tandem with pipeline caching.
result EEIPU produces 103% more hyperparameter candidates and 108% more validation metric improvement.
Large scale machine learning (ML) systems such as the Alexa automatic speech recognition (ASR) system continue to improve with increasing amounts of manually transcribed training data. Instead of scaling manual transcription to impractical levels, we utilize semi-supervised learning (SSL) to learn acoustic models (AM) …
Machine Learning is transitioning from an art and science into a technology available to every developer. In the near future, every application on every platform will incorporate trained models to encode data-based decisions that would be impossible for developers to author. This presents a significant engineering chal…
RFX-Fuse combines Breiman and Cutler's Random Forest with modern ML capabilities.
problem Lack of a unified ML engine with diverse capabilities.
method Unified ML engine with native GPU/CPU support, delivering 5+ functionalities in one model.
result Native explainable similarity and imputation validation.
PipeDream-2BW accelerates large model training by 20x with minimal memory usage.
problem Training large models requires memory beyond single accelerator capacity.
method Pipeline parallelism, weight gradient coalescing, double buffering.
result Accelerates large model training by up to 20x.
We introduce vine computational graphs for efficient ML integration of vine copulas.
problem Integrating vine copulas into modern machine learning pipelines.
method Developed vine computational graphs and algorithms for conditional sampling, scheduling, and structure construction.
result Gradient flow through vine copulas improves performance in machine learning models.
The paper proposes a method to evaluate ML models for subjective inference, focusing on sentence toxicity.
problem Bias in ML models for subjective inference, especially in real-life applications.
method Proposes a list of specifications to evaluate ML models for subjective inference, illustrated with a sentence toxicity example.
result Demonstrates the importance of considering subjectivity and bias in evaluating ML models.
RODMAN improves ML-based disk failure prediction accuracy in cloud environments.
problem Imperfect data quality in real-world cloud environments degrades ML-based disk failure prediction accuracy.
method RODMAN uses three data preprocessing techniques: failure-type filtering, spline-based data filling, and automated pre-failure backtracking.
result RODMAN significantly improves prediction accuracy compared to no preprocessing.
MLModelScope streamlines ML/DL model evaluation and benchmarking.
problem Challenges in evaluating and benchmarking ML/DL models.
method Open-source, framework/hardware agnostic platform with distributed design.
result Demonstrates the impact of model evaluation pipelines and HW/SW choices.
There has been a rapid proliferation of machine learning/deep learning (ML) models and wide adoption of them in many application domains. This has made profiling and characterization of ML model performance an increasingly pressing task for both hardware designers and system providers, as they would like to offer the b…
This dissertation automates deep learning pipelines and uses meta-learning for better model selection and data augmentation.
problem Challenges in selecting and fine-tuning deep learning pipelines for new datasets.
method Meta-learning for DL pipeline selection and data augmentation, using synthetic data.
result Meta-learned approaches outperform traditional methods in automated DL pipeline selection and data augmentation.
Framework improves ML performance by identifying high-quality data.
problem Poor data quality hampers ML performance.
method Intelligent data-centric evaluation framework combining quality measurements and unsupervised learning.
result Framework improves ML system performance in real-world use case.
Machine learning (ML) has become a vital part in many aspects of our daily life. However, building well performing machine learning applications requires highly specialized data scientists and domain experts. Automated machine learning (AutoML) aims to reduce the demand for data scientists by enabling domain experts to…
The study examines backward compatibility issues in ML systems, especially with noisy data.
problem Backward compatibility challenges in ML systems, especially with noisy data.
method Empirical analysis of ML systems across different architectures and datasets, focusing on data shifts and noise.
result Backward compatibility issues arise even without data shift due to optimization stochasticity and training on large-scale noisy datasets can significantly decrease compatibility.
Machine learning (ML) methods have been developing rapidly, but configuring and selecting proper methods to achieve a desired performance is increasingly difficult and tedious. To address this challenge, automated machine learning (AutoML) has emerged, which aims to generate satisfactory ML configurations for given tas…
Tribuo integrates ML models with provenance in Java.
problem Tracking and ensuring ML models behave appropriately as they grow in number and complexity.
method Integrates model training, inference, type-safety, runtime checking, and automatic provenance recording into a single Java library.
result Automatic recording of full processing pipeline and training details inside the model object.
We study the AutoML problem of automatically configuring machine learning pipelines by jointly selecting algorithms and their appropriate hyper-parameters for all steps in supervised learning pipelines. This black-box (gradient-free) optimization with mixed integer & continuous variables is a challenging problem. We pr…
New algorithm learns and unlearns from streaming data efficiently.
problem Continuous learning and unlearning from production data streams.
method Translated batch unlearning techniques to online setting using regret, sample complexity, and deletion capacity.
result Achieved logarithmic regret bound of for online unlearning.
In this paper, a Wide Learning architecture is proposed that attempts to automate the feature engineering portion of the machine learning (ML) pipeline. Feature engineering is widely considered as the most time consuming and expert knowledge demanding portion of any ML task. The proposed feature recommendation approach…