Research
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.

169,051 papers · 148 categories

Trend · papers per month

16314762 · Jun 202019922001200920182026
48 results for ML libraries

We consider the problem of finding the minimizer of a function f:RdRf: \mathbb{R}^d \rightarrow \mathbb{R} of the finite-sum form minf(w)=1/ninfi(w)\min f(w) = 1/n\sum_{i}^n f_i(w). This problem has been studied intensively in recent years in the field of machine learning (ML). One promising approach for large-scale data is to use a stoc…

2017-10-27abs ↗pdf ↗

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.

This work shows how to compute subderivatives efficiently without errors.

problem Inefficient and incorrect computation of subderivatives in ML libraries.
method Developed a method to compute provably correct generalized subderivatives at a cost close to the function itself.
result Provable correct generalized subderivatives can be computed at a cost within a factor of 6 of the function itself.

ALICE combines feature selection and inter-rater agreeability for ML model insights.

problem Improving interpretability of black box machine learning models.
method Integrates feature selection and inter-rater agreeability into a user-friendly Python library.
result Initial experiments on customer churn modeling show promising insights.

pyLOT library simplifies machine learning on 3D point clouds via linearized optimal transport.

problem Performing machine learning tasks on 3D point clouds.
method Linearized optimal transport (LOT) to embed distributions into Hilbert space, enabling linear machine learning.
result Downstream tasks on embedded representations are simplified to linear operations.

MARVIN offers an open ML environment for automated primitive annotation and execution.

problem Automated machine learning primitive annotation and execution.
method Web-based Python application with Docker containers on Kubernetes.
result Over 400 datasets and challenges from various ML domains.

Mango automates hyperparameter tuning for large-scale ML training.

problem Manual hyperparameter tuning is tedious and inefficient for large-scale machine learning.
method Parallel hyperparameter tuning with intelligent search strategies and flexible abstractions.
result Mango achieves comparable performance to Hyperopt while supporting distributed computing.

With few exceptions, the field of Machine Learning (ML) research has largely ignored the browser as a computational engine. Beyond an educational resource for ML, the browser has vast potential to not only improve the state-of-the-art in ML research, but also, inexpensively and on a massive scale, to bring sophisticate…

2014-12-08abs ↗pdf ↗

This paper emphasizes the need for uncertainty quantification in data-driven ML models for nuclear engineering.

problem Uncertainty in ML predictions due to data noise, model architecture, and stochastic training.
method Explains and compares uncertainties in physics-based and data-driven models, and presents techniques to quantify ML prediction uncertainties.
result The importance of uncertainty quantification in ML models for nuclear engineering applications.

SAGDA generates synthetic agricultural datasets to improve ML in African farming.

problem Data scarcity in African agriculture limits machine learning innovations.
method SAGDA is an open-source Python toolkit that generates, augments, and validates synthetic agricultural datasets.
result SAGDA enhances ML applications in agriculture, such as yield prediction and fertilizer recommendation.

XSP profiles ML models across hardware and software stacks.

problem Challenges in profiling ML model performance across different layers of the stack.
method XSP uses distributed tracing to aggregate data from various sources and introduces a leveled, iterative measurement approach.
result XSP provides insights into ML model execution not easily discernible otherwise.

Machine Learning (ML) has been successfully applied to a wide range of domains and applications. One of the techniques behind most of these successful applications is Ensemble Learning (EL), the field of ML that gave birth to methods such as Random Forests or Boosting. The complexity of applying these techniques togeth…

2017-06-28abs ↗pdf ↗

CodeReef enables sharing ML models across platforms efficiently.

problem Sharing and deploying ML models across different systems efficiently.
method Developed an open platform to share ML components, automate deployment, and benchmark models.
result Demonstrated efficient deployment and benchmarking of ML models across diverse platforms.

AutoML library TPOT optimizes brain age prediction models without prior knowledge.

problem Optimizing machine learning models for brain age prediction.
method TPOT uses genetic programming to find optimal machine learning pipelines.
result TPOT outperformed state-of-the-art models in brain age prediction.

Efficiently reduces costs for Bayesian networks in FGrn form.

problem High computational and memory costs of Bayesian networks in FGrn form.
method Detailed algorithmic and structural analysis leading to cost reduction solutions, including an online learning algorithm.
result Proposed solutions and online learning algorithm significantly reduce costs for Bayesian networks.

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.

Python's tools drive machine learning advancements across industries.

problem Processing and analyzing large data sets for insights.
method Advancements in deep learning, classical ML, and GPU computing.
result Python's dominance in scientific computing boosts machine learning adoption.

AITuning uses reinforcement learning to optimize communication libraries.

problem Optimizing communication libraries for better performance in parallel applications.
method Deep reinforcement learning applied to tuning communication libraries.
result Demonstrates the effectiveness of reinforcement learning for tuning communication libraries.

πBO augments BO with user beliefs for better hyperparameter optimization.

problem BO ignores user beliefs, reducing its appeal to practitioners.
method Proposes ππBO, an acquisition function that incorporates user-provided prior beliefs.
result ππBO outperforms competing approaches and deep learning tasks.

TrueLearn Python library for personalized educational recommendations.

problem Building educational recommendation systems with humanly-intuitive user representations.
method Online learning Bayesian models and open learner concept.
result Library includes models and representations for user control and interpretability.

IllinoisSL is a Java library for learning structured prediction models. It supports structured Support Vector Machines and structured Perceptron. The library consists of a core learning module and several applications, which can be executed from command-lines. Documentation is provided to guide users. In Comparison to …

2015-09-23abs ↗pdf ↗

Analyzes 6M Python notebooks and 2M enterprise DS pipelines to guide investments in data science.

problem Challenges in following the rapidly evolving landscape of data science technologies and applications.
method Downloaded and analyzed over 6M Python notebooks and 2M enterprise DS pipelines, performing statistical and comparative analyses.
result Identifies actionable conclusions for system builders and technology bets for practitioners based on current trends.

Modified BFGS and LBFGS++ libraries boost performance for non-parallelizable functions.

problem Improving performance of non-parallelizable functions using SIMD and AAD.
method Modifications to BFGS and LBFGS++ libraries, utilizing SIMD and Automatic Differentiation (AAD).
result Up to 3.8 times faster for European Swaption curve calibration and 1.4 times faster for LMM model calibration.

FCL3 learns from multiple representative models to adapt to new tasks.

problem Degradation of performance in lifelong learning models for new task environments.
method Two knowledge libraries: feature learning and model knowledge. Self-selection of representative models for new tasks.
result FCL3 achieves better performance than most lifelong learning frameworks.