Transfer Neural AutoML speeds up deep learning architecture design.
problem High computational cost in Neural AutoML.
method Transfer learning to speed up architecture design.
result Reduces convergence time by over an order of magnitude.
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.
169,291 papers · 148 categories
Trend · papers per month
48 results for “Neural AutoML”
AutoML uses dataset and algorithm descriptions to improve performance.
problem Improving automated machine learning performance.
method Uses language embeddings to augment AutoML recommendations.
result Zero-shot AutoML system provides good solutions in under a second.
Survey of AutoML methods and their performance.
problem Building high-quality DL systems requires human expertise.
method Reviews AutoML methods including data preparation, feature engineering, hyperparameter optimization, and neural architecture search.
result Summarizes the performance of NAS algorithms on CIFAR-10 and ImageNet datasets.
NASirt automates CNN architecture design for spectral data.
problem Designing optimal neural architectures for complex data.
method Neural Architecture Search (NAS) with Item Response Theory (IRT) for instance-level complexity.
result NASirt achieves high accuracy (97.40%) on spectral datasets.
AutoML discovers complete machine learning algorithms from basic operations.
problem Automating the discovery of machine learning algorithms from scratch.
method Evolutionary search on a generic search space of basic mathematical operations.
result Simple neural networks can be surpassed by evolving directly on tasks of interest.
Auto-PyTorch automates deep learning by optimizing neural architectures and hyperparameters.
problem Automated deep learning for tabular data with robust and efficient optimization.
method Combines multi-fidelity optimization, portfolio construction, and warmstarting with ensembling.
result Achieves state-of-the-art performance on tabular benchmarks.
Improved AutoML performance with a pipeline grammar and pre-trained model.
problem Automatic machine learning by pipeline synthesis.
method Model-based reinforcement learning and pipeline grammar.
result Improved performance on AutoML benchmark datasets.
RandomNet uses random search to design neural architectures without much human intervention.
problem Designing neural architectures without excessive human intervention.
method Random search strategy for multimodal neural architecture design.
result RandomNet performs close to state-of-the-art on AV-MNIST with minimal human supervision.
This paper compares machine learning models for pricing European options.
problem Pricing European options using traditional methods like Black Scholes Model.
method Google AutoML Regressor, TensorFlow Neural Networks, and XGBoost Gradient Boosting Decision Trees.
result All models outperformed the Black Scholes Model in terms of mean absolute error.
AgEBO-Tabular combines NAS and hyperparameter tuning for fast, high-performing tabular models.
problem Developing high-performing predictive models for large tabular data sets is challenging.
method Combines aging evolution NAS and asynchronous Bayesian optimization for hyperparameter tuning in data-parallel training.
result Automatically discovered neural network models outperform state-of-the-art AutoML ensembles in inference speed by two orders of magnitude.
Introduces AMLB, an open benchmark for AutoML frameworks.
problem Challenges in comparing AutoML frameworks.
method Open benchmark with 9 AutoML frameworks, 71 classification, 33 regression tasks, multi-faceted analysis, Bradley-Terry trees.
result Differences in AutoML frameworks' performance and trade-offs.
Auto-sklearn 2.0 simplifies AutoML with meta-learning and meta-feature-free techniques.
problem Designing efficient machine learning pipelines for large datasets under time constraints.
method PoSH Auto-sklearn uses meta-learning and bandit strategy for budget allocation.
result Reduces relative error by up to a factor of 4.5 and improves performance in 10 minutes.
GAMA is a user-friendly AutoML system for machine learning pipeline optimization.
problem Empowering users to control and optimize machine learning pipelines.
method Modular AutoML system with three search algorithms and two post-processing steps.
result GAMA allows users to track and control the search process for optimal machine learning pipelines.
Comparison of AutoML and DL shows AutoML outperforms simple DL for binary classification.
problem Choosing between AutoML and DL for binary classification tasks.
method Comparison of AutoML and DL on 6 public datasets, evaluation of a new AutoML tool.
result AutoML outperforms simple DL classifiers but integrating DL into AutoML improves performance further.
This paper surveys and benchmarks AutoML frameworks.
problem Reducing the need for data scientists in building machine learning applications.
method Survey and benchmark of popular AutoML frameworks on real data sets.
result Evaluation of 137 data sets from established AutoML benchmark suits.
Open-source benchmark for AutoML systems.
problem Difficulty in comparing AutoML systems.
method Open-source benchmark framework with public datasets and results.
result Compared 4 AutoML systems across 39 datasets.
AutoML frameworks outperform human data scientists on 7 out of 12 OpenML tasks.
problem Evaluating if AutoML can outperform human data scientists.
method Comparison of four AutoML frameworks on 12 popular OpenML datasets (6 supervised classification, 6 supervised regression).
result AutoML frameworks perform better or equal to human data scientists in 7 out of 12 tasks.
Study finds transparency and model performance metrics increase trust in AutoML systems.
problem Understanding what information influences trust in AutoML systems.
method Three studies: qualitative interviews, controlled experiment, and card-sorting task.
result Transparency and model performance metrics are most important for establishing trust in AutoML systems.
AutoML aims to automate machine learning tasks, reviewed in this chapter.
problem Automating the design of machine learning systems.
method Historical review and description of main paradigms.
result Major achievements in AutoML have been made in recent years.
Automated ML simplifies machine learning configurations.
problem Difficulty in configuring and selecting ML methods.
method Bi-level learning objective, learning strategy, and evaluation strategy.
result Satisfactory ML configurations generated automatically.
AutoML struggles with climate change data, but offers potential improvements.
problem Improving machine learning for climate change applications.
method Benchmarked AutoML libraries on climate modeling, wind power, and catalyst discovery.
result Current AutoML techniques fail to surpass human-designed models in climate change applications.
A new AutoML framework uses ADMM to optimize machine learning pipeline configurations.
problem Optimizing machine learning pipelines with mixed integer and continuous variables.
method Leverages ADMM to decompose and solve the optimization problem.
result Significant gains in comparison to other AutoML frameworks.
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.
LightAutoML automates ML for a large financial services company.
problem Building high-quality ML models for a complex financial ecosystem.
method Developed an AutoML system tailored to a large European financial services company's unique requirements.
result LightAutoML outperformed experienced data scientists and other open-source solutions.
Study examines AutoML adaptation to evolving data.
problem Understanding and improving AutoML performance with concept drift.
method 6 concept drift adaptation strategies evaluated on various AutoML approaches.
result Robust AutoML techniques can be developed to handle concept drift.
CNAS optimizes neural architectures for class-incremental learning.
problem Capacity saturation in static neural architectures for class-incremental learning.
method CNAS uses reinforcement learning and network transformations to adaptively select architectures.
result CNAS outperforms static architectures and is more efficient.
ATMSeer improves AutoML by making it more transparent and controllable.
problem Users distrust automatic AutoML results and increase search budgets.
method Interactive visualization tool to refine search space and analyze results.
result ATMSeer enhances efficiency and user trust in AutoML.
AutoML benchmarks compare different frameworks.
problem No objective comparison of AutoML frameworks exists.
method Benchmarked four open-source AutoML solutions using open-source datasets.
result auto-sklearn outperformed TPOT in classification and regression tasks respectively.
Auto-Keras efficiently searches neural architectures with less computation.
problem Expensive computational cost in existing NAS algorithms.
method Bayesian optimization guided by network morphism.
result Framework outperforms state-of-the-art methods on real-world datasets.
Iterative AutoML improves ASR model compression by 5x without WER degradation.
problem Challenges in achieving high compression levels without degrading ASR performance.
method Iterative AutoML-based Low Rank Factorization (LRF) approach.
result Achieved over 5x compression without WER degradation.
AutoGluon-Tabular automates tabular data ML with single line Python.
problem Training accurate ML models on unprocessed tabular data.
method Ensembling multiple models in multiple layers.
result Outperforms competitors in accuracy and robustness.
Paper proposes an AutoML framework for efficient device-edge co-inference.
problem Finding optimal hyper-parameters for model sparsity and feature compression.
method Sequential decision problem solved using deep reinforcement learning (DRL).
result Achieves better communication-computation trade-off and significant speedup.
AutoML enhances clinical metabolic profiling by adjusting for confounders.
problem Identifying and adjusting for clinical confounders in AutoML for metabolic profiling.
method Tandem rank-accuracy measure for feature selection, residual training adjustment for confounders.
result Increased homocysteine concentration associated with long-term metformin exposure.
AutoML system boosts interpretability without sacrificing performance.
problem Laypeople struggle with interpreting complex ensembles of black-box models.
method Componentwise boosting algorithm for interpretable additive models.
result Interpretable models are competitive in performance and user-friendly.
Automates neural network design for diverse tasks.
problem Designing neural networks for new, under-explored domains.
method Introduces XD-Operations and a weight-sharing scheme to transform standard backbones into search spaces of operations.
result Models using XD-Operations achieve lower error than baseline and expert-designed networks on diverse tasks.
AutoML simplifies two-sample tests for detecting distribution shifts.
problem Detecting distribution shifts between datasets.
method Uses mean discrepancy of a witness function with squared loss minimization.
result AutoML simplifies and improves two-sample testing performance.
AutoML enhances credit decisions with XAI for better transparency.
problem Transparency in AI-driven financial decisions.
method Combining AutoML and XAI (SHAP) for credit scoring.
result Improved efficiency and accuracy in credit decisions with enhanced transparency.
This paper explores AutoML for practical business applications.
problem Building machine learning models from data.
method Overview and benchmarking of AutoML algorithms.
result Recent benchmark results on AutoML algorithms.
AutoML uses MCTS to optimize machine learning algorithms and hyperparameters.
problem Optimizing machine learning algorithms and hyperparameters efficiently.
method MCTS-based approach for hybrid optimization of machine learning portfolios.
result Mosaic outperforms Auto-Sklearn on OpenML 100 benchmark and Scikit-learn portfolio.
AutoML-GPT uses GPT to automate AI model training.
problem Manual model selection and tuning requires significant human effort.
method Develops task-oriented prompts and utilizes LLMs for automated training.
result Achieves remarkable results in various AI tasks.
This paper evaluates AutoML tools for ML tasks.
problem Efficiency in machine learning for ML engineers.
method Evaluation and comparison of AutoML tools on various datasets.
result Performance and advantages/disadvantages of AutoML tools.
Deep-n-Cheap automates deep learning model search for low complexity.
problem Finding efficient deep learning models for various datasets.
method Automated search framework for architecture and hyperparameters, including search transfer.
result Models offer comparable performance to state-of-the-art but are faster to train.
AutoML tackles evolving data with drift detection.
problem Handling changing data distributions in AutoML.
method Extended Auto-Sklearn with drift detection mechanisms.
result Demonstrated effectiveness of the proposed methodology.
AutoML improves electricity demand forecasting models.
problem Optimizing GAM and state-space model parameters for short-term forecasting.
method Automated online generalized additive model selection using DRAGON package.
result The approach enhances predictive performance of adaptive models.
This paper automates multi-label classification using an extended AutoML tool.
problem Lack of automated solutions for multi-label classification.
method Extends ML-Plan for multi-class classification to multi-label classification using MEKA.
result The proposed approach yields superb results and performs significantly better than baselines.
Paper compares AutoML methods for recommending classification algorithms.
problem Finding the best classification algorithm for a dataset.
method Four AutoML methods using Evolutionary Algorithms and CASH approach.
result EA-based methods, especially decision-tree induction, produce interpretable models.
FLAML automates model selection and hyperparameter tuning with low resource cost.
problem Automating model selection and hyperparameter tuning for ad-hoc datasets and metrics.
method Conducts trials of different configurations on training data, optimizing for low computational cost.
result Significantly outperforms top-ranked AutoML libraries under smaller budget constraints.
Automated machine learning simplifies model selection and tuning.
problem Manual tuning of machine learning models by data scientists is time-consuming and requires extensive expertise.
method Review of AutoML techniques including automated feature engineering, model learning, and deep learning.
result Current AutoML techniques can significantly reduce the burden of manual tuning.