Automatic differentiation---the mechanical transformation of numeric computer programs to calculate derivatives efficiently and accurately---dates to the origin of the computer age. Reverse mode automatic differentiation both antedates and generalizes the method of backwards propagation of errors used in machine learni…
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.
169,181 papers · 148 categories
Trend · papers per month
48 results for “Automatic Machine Learning”
Survey reviews machine learning for automatic movement generation.
problem Need for automatic movement animation in interactive media.
method Machine learning techniques and motion capture data.
result Discussion of research gaps and challenges for future work.
Paper presents an efficient method for selecting machine learning algorithms and hyper-parameters.
problem Efficient selection of machine learning algorithms and hyper-parameters is challenging for large datasets.
method Progressive sampling-based Bayesian optimization
result Significantly reduces search time, classification error rate, and error rate variability.
Develops a mathematical model for automatic differentiation in machine learning.
problem Current automatic differentiation lacks a simple mathematical model for machine learning.
method Articulates relationships between program differentiation and nonsmooth functions, provides a class of functions and nonsmooth calculus.
result Shows how nonsmooth calculus applies to stochastic approximation methods and evidence of artificial critical points.
System for automatic differentiation in a functional array-processing language.
problem Efficient automatic differentiation in functional array languages.
method Automatic differentiation in a higher-order functional array-processing language with source-to-source support and global optimizations.
result The system outperforms state-of-the-art tools on machine learning and computer vision benchmarks.
ARDA automatically augments datasets for machine learning models.
problem Improving machine learning model performance through data augmentation.
method ARDA combines data searching, joining, and feature selection to augment datasets.
result Training models on ARDA's augmented datasets leads to better performance.
Tangent uses Python code transformation for automatic differentiation.
problem Efficient and readable automatic differentiation in Python.
method Source code transformation to generate derivative code.
result Readable and debuggable gradient code in Python.
New system for automatic music emotion recognition considers multiple emotions simultaneously.
problem Automatic recognition of simultaneous and multiplicity of emotions in music.
method Comparison of multilabel and multiclass machine learning algorithms on the Emotify dataset.
result The Geneva Emotional Music Scale 9 is adopted for multilabel and multiclass classification of music emotions.
Paper proposes a method to automatically detect drift in machine learning models.
problem Detecting changes in class-label data distributions that affect model predictions.
method Self-evaluating predictive model degradation to detect concept drift.
result Effectiveness in automatically detecting and describing concept drift.
AutoSGD automatically adjusts learning rates for SGD.
problem Inefficient manual learning rate selection for SGD.
method AutoSGD automatically adjusts learning rates based on iteration.
result Empirical results show strong performance across various optimization tasks.
D-Adaptation automatically sets optimal learning rates without manual tuning.
problem Optimizing learning rates for efficient convergence in machine learning.
method D-Adaptation, which asymptotically achieves optimal learning rates without back-tracking or additional evaluations.
result D-Adaptation automatically matches hand-tuned learning rates across diverse problems.
MLtuner automates tuning machine learning parameters for better performance.
problem Manual tuning of machine learning parameters is error-prone and requires domain knowledge.
method Snapshotting, branching, and optimization-guided online trial-and-error.
result MLtuner finds and re-tunes parameters robustly and efficiently for various ML applications.
Amazon SageMaker AMT automates machine learning model tuning.
problem Challenging hyperparameter tuning for complex machine learning systems.
method Gradient-free optimization using random search or Bayesian optimization.
result AMT finds the best hyperparameter configurations for models.
Method explains machine learning diabetes risk predictions.
problem Lack of interpretability in machine learning models.
method Automatic explanation method for machine learning models.
result 87.4% of patients' predictions explained without accuracy loss.
Derivatives, mostly in the form of gradients and Hessians, are ubiquitous in machine learning. Automatic differentiation (AD), also called algorithmic differentiation or simply "autodiff", is a family of techniques similar to but more general than backpropagation for efficiently and accurately evaluating derivatives of…
Graph Neural Networks improve machine learning on relational databases.
problem Training machine learning models on relational databases requires costly data extraction and feature engineering.
method Uses Graph Neural Networks to extract features from relational databases.
result Outperforms state-of-the-art automatic feature engineering methods.
SAFE automates feature engineering for industrial tasks efficiently and scalably.
problem Efficiency and scalability of automatic feature engineering methods for industrial tasks.
method SAFE (Scalable Automatic Feature Engineering) method, which provides excellent efficiency and scalability.
result SAFE method provides prominent efficiency and competitive effectiveness in industrial tasks.
Paper provides a large dataset for exploring machine learning hyperparameters.
problem Lack of experimental meta data for evaluating hyperparameter influence.
method Automated random sampling strategy to generate 2.5 million experiments.
result Large dataset of 38 OpenML data sets, 6 algorithms, and many hyperparameters.
Paper introduces new estimator for continuous treatment effects.
problem Estimating the average dose-response function of continuous treatments.
method Utilizes ADML and DML tools, with a novel debiasing method.
result Proves asymptotic normality and shows good performance in simulations.
This paper proposes automatic tuning of Bayesian Optimization's acquisition function.
problem Optimizing black-box functions with noisy, expensive evaluations and hyperparameter tuning.
method Exploring heuristics to automatically tune acquisition functions in Bayesian Optimization.
result Demonstrates effectiveness of heuristics in automatic Bayesian Optimization.
Improves numerical solution of ill-conditioned linear systems for machine learning.
problem Wastefulness and instability in solving ill-conditioned linear systems.
method autonugget combines Richardson extrapolation to determine the solution of the ill-conditioned system, improving accuracy over a single nugget.
result Improves accuracy of numerical solution of ill-conditioned linear systems.
Method classifies Dyslexic and Skilled readers using ERP signals and machine learning.
problem Automatic identification of Dyslexic readers using ERP signals.
method Processing ERP signals, multivariate analysis, machine learning techniques.
result Automatic distinction between Dyslexic and Skilled readers with significant features in High Pass signals.
Teaches matrix calculus for machine learning and optimization.
problem Computing derivatives of functions involving matrices.
method Extends differential calculus to vector spaces, focusing on practical applications in machine learning.
result Introduction of adjoint and reverse-mode differentiation for efficient computation.
Deep learning predicts pharmaceutical formulations with high accuracy.
problem Laborious, time-consuming and costly traditional trial-and-error approach in pharmaceutical formulation development.
method Used deep learning for automatic feature extraction, developed automatic dataset selection algorithm, compared with six machine learning methods.
result Deep neural networks achieved accuracies above 80% in predicting pharmaceutical formulations.
This work evaluates machine learning-based hotspot detectors on synthesized layout patterns.
problem Evaluating model robustness and generality of machine learning-based hotspot detectors.
method Developed an automatic layout generation tool to synthesize various layout patterns and tested machine learning-based detectors on these synthesized layouts.
result Machine learning-based detectors need continuous study for robustness and generality in DFM flows.
AxCell automates results extraction from machine learning papers.
problem Difficulty in tracking progress in machine learning due to many papers.
method AxCell uses table segmentation and learns structural knowledge to extract results.
result AxCell significantly improves results extraction compared to existing methods.
Machine learning speeds up GPR simulations.
problem Computational demands of simulating practical GPR problems.
method Automatic ML-based forward solver framework using gprMax.
result Near-real-time GPR simulations achieved.
Machine learning classifies medical notes into disease codes.
problem Automatically categorizing patient discharge notes into standard disease labels.
method Used Convolutional Neural Networks with Attention.
result Convolutional Neural Networks with Attention outperform previous methods.
genriesz: A Python Package for Automatic Debiased Machine Learning with Generalized Riesz Regressionstat.ML
Python package automates causal parameter estimation using Riesz regression.
problem Efficient estimation of causal and structural parameters.
method Automatic DML and generalized Riesz regression framework.
result Automatic construction of balancing link functions for generalized Riesz regression.
Machine Learning-Based Analysis of Sperm Videos and Participant Data for Male Fertility Predictioncs.LG
Machine learning predicts sperm motility from videos and participant data.
problem Manual evaluation of semen samples is time-consuming and unreliable.
method Used machine learning techniques including simple linear regression and convolutional neural networks.
result Sperm motility prediction using deep learning is rapid and consistent.
Interpretable Bayesian Tensor Network Kernel Machines with Automatic Rank and Feature Selectionstat.ML
Bayesian TNKMs automatically infer model complexity and feature relevance.
problem Manual tuning of TN rank and feature dimensions is error-prone and computationally expensive.
method Bayesian approach with hierarchical priors on TN factors for automatic rank and feature selection.
result Superior performance in prediction accuracy, uncertainty quantification, interpretability, and scalability.
Semi-automatic data annotation helps experts label unlabeled samples based on feature space projection.
problem Laborious manual data annotation for machine learning.
method Interactive semi-automatic approach using feature space projection and semi-supervised learning.
result Reduces user annotation effort and improves classification accuracy.
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.
Auto-CASH uses Deep Q-Network to automatically select machine learning algorithms.
problem Automatic selection of machine learning algorithms and hyperparameters.
method Pre-trained model based on meta-learning using Deep Q-Network.
result Auto-CASH achieves better performance with shorter time compared to classical and state-of-the-art methods.
Improves deep learning models through automatic programming.
problem Enhance performance of deep learning models.
method Investigated automatic programming (ADATE) to improve deep learning models.
result Good results achieved but limited by current ADATE version.
AutoKE automates embedding physical knowledge into neural networks for complex engineering problems.
problem Complex physical equations in engineering problems.
method AutoKE framework using deep neural networks, equation parsing, automatic differentiation, adaptive weights, and NAS.
result Automatically embeds physical knowledge into neural networks for complex equations efficiently.
AD-EnKFs use machine learning to improve data assimilation in high-dimensional systems.
problem Data assimilation in high-dimensional, unknown dynamics systems.
method Auto-differentiable ensemble Kalman filters blending machine learning and ensemble Kalman filters.
result AD-EnKFs outperform existing methods in the Lorenz-96 model.
QC methods improve reliability of machine learning-based image segmentation.
problem Inaccuracies in machine learning algorithms limit their clinical applicability.
method Analysis and validation of QC approaches for automatic segmentation.
result Aggregation of uncertainty and Dice prediction methods improved segmentation reliability.
This research simplifies verification of machine learning systems using reparameterization.
problem Reduce or eliminate serious bugs in machine learning systems.
method Use proof assistants to construct machine-checked proofs of correctness, leveraging reparameterization to handle probabilistic claims.
result Demonstrates broad applicability of reparameterization to verify different types of machine learning systems.
Automatic Hyper-Parameter Optimization Based on Mapping Discovery from Data to Hyper-Parameterscs.LG
This paper proposes an efficient autoHPO method based on data-to-hyper-parameter mapping.
problem Manual hyper-parameter tuning is costly and dependent.
method The approach is based on mapping from data to hyper-parameters using a sophisticated network structure and effective construction algorithms.
result The proposed approach significantly outperforms state-of-the-art methods.
S4 learns new self-supervision automatically, improving accuracy with less human effort.
problem Lack of direct supervision in machine learning.
method Combines deep learning and probabilistic logic to automatically generate and verify new self-supervision.
result S4 can automatically propose accurate self-supervision, matching supervised methods with less human effort.
Deep learning classifies trees from UAV images with high accuracy.
problem Automatic tree classification from aerial images.
method Object-based deep learning on UAV RGB images.
result 7 tree types classified at 89.0% accuracy.
Automatically learns efficient algorithms for structured transforms like FFT.
problem Efficient algorithms for structured linear transforms.
method Generic parameterization of divide-and-conquer methods.
result Reproduces Cooley-Tukey FFT algorithm to machine precision.
CoLA automates efficient numerical linear algebra for complex matrix structures.
problem Efficiently solving large-scale linear algebra problems with complex matrix structures.
method Combining linear operator abstraction with compositional dispatch rules.
result Automatic and efficient numerical algorithms for various linear algebra operations.
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.
Develops ACE to automatically identify meaningful concepts from neural network predictions.
problem Challenges in interpreting feature importance scores for machine learning models.
method Proposes concept-based explanation principles and develops ACE algorithm to extract visual concepts.
result Demonstrates ACE discovers human-meaningful, coherent concepts for neural network predictions.
A rule selects the best gradient estimator for faster convergence in machine learning.
problem Choosing the best gradient estimator for faster convergence in machine learning.
method Analyzed convergence rates of SGD as a function of time, resulting in a simple rule to select the best estimator.
result The selected estimator leads to the best optimization convergence guarantee, same for different SGD variants and objective types.
AEQUITAS automatically tests and improves fairness of machine learning models.
problem Ensuring fairness in machine learning models used in sensitive domains.
method Probabilistic search over input space to discover discriminatory inputs, leveraging robustness of models.
result AEQUITAS effectively generates inputs to uncover and improve fairness in machine learning models.