Proposes a method to improve neural architectures reproducibly.
problem Lack of reproducibility in Neural Architecture Transformer (NAT).
method Differentiable Neural Architecture Transformation (DNAT).
result DNAT outperforms NAT and is applicable to various models and datasets.
Study evaluates 21 KG embedding models, highlighting model architecture, training approach, and loss function importance.
problem Difficulty in fair and thorough comparisons of knowledge graph embedding models due to heterogeneity in implementations, training, and evaluation.
method Reimplemented and evaluated 21 models in PyKEEN, providing insights into reproducibility and best practices.
result Best practices and configurations for each model were identified, showing the importance of model architecture, training approach, and loss function.
New benchmarks provide full training data for NAS research.
problem Limited training data on popular benchmarks restricts multi-fidelity techniques.
method SVD and noise modeling to create surrogate benchmarks with full training info.
result Learning curve extrapolation framework improves single-fidelity algorithms.
Deep neural networks define suitable reproducing kernel Banach spaces.
problem Characterizing the function spaces of deep neural networks.
method Reproducing kernel Banach spaces and variational results.
result Deep neural networks define suitable reproducing kernel Banach spaces.
Anti-Distillation improves reproducibility of deep networks by making ensemble predictions more diverse.
problem Deep networks are prone to high prediction differences, making them less reproducible.
method Anti-Distillation uses ensembles to force predictions to be more different and diverse.
result Anti-Distillation reduces prediction differences by making ensemble predictions more diverse.
Recent advances in neural architecture search (NAS) demand tremendous computational resources, which makes it difficult to reproduce experiments and imposes a barrier-to-entry to researchers without access to large-scale computation. We aim to ameliorate these problems by introducing NAS-Bench-101, the first public arc…
We tackle the problem of protein secondary structure prediction using a common task framework. This lead to the introduction of multiple ideas for neural architectures based on state of the art building blocks, used in this task for the first time. We take a principled machine learning approach, which provides genuine,…
LLM-based trading systems vary in execution realism and reproducibility.
problem LLM-based trading systems vary in execution realism and reproducibility.
method Reproducibility audit of 30 trade-relevant primary studies.
result LLM-based trading systems vary in execution realism and reproducibility.
ModSSC unifies semi-supervised classification for various data types.
problem Fragmented support for semi-supervised classification across different methods, settings, and data types.
method ModSSC is a modular Python framework that supports reproducible and controlled experimentation for semi-supervised classification on heterogeneous data.
result ModSSC enables systematic comparison of semi-supervised learning across various datasets and model backbones.
New method creates diverse neural ensembles for better uncertainty estimation and robustness.
problem Creating more robust neural networks for uncertainty estimation and dataset shift.
method Automatically constructing ensembles with varying architectures.
result Ensembles with varying architectures outperform deep ensembles in accuracy, uncertainty calibration, and robustness.
Mixture components improve VAE performance by increasing latent flexibility.
problem Improving variational autoencoder (VAE) performance through more flexible latent representations.
method Modeling mixture components with separate encoder networks and analyzing their impact on ELBO.
result Increasing the number of mixture components improves VAE performance on various datasets.
Develops vector-valued RKBS for neural networks and operators.
problem Understanding function spaces of Rd-valued neural networks and neural operators. method Defines and constructs vector-valued RKBS (vv-RKBS) without restrictive assumptions.
result Establishes Representer Theorem for neural architectures.
Neural architecture search (NAS) is a promising research direction that has the potential to replace expert-designed networks with learned, task-specific architectures. In this work, in order to help ground the empirical results in this field, we propose new NAS baselines that build off the following observations: (i) …
This work improves GAN stability with theoretical conditions.
problem GANs exhibit unstable behavior during training.
method Developed a theoretical framework and conditions for GAN stability.
result Constructs a GAN that fulfills stability conditions.
Benchopt automates machine learning benchmarking across languages and hardware.
problem Limited transparency and tedious re-implementation work in machine learning validation.
method A collaborative framework for automating, reproducing, and publishing optimization benchmarks.
result Demonstrates practical findings that highlight the importance of details in machine learning validation.
NeurIPS 2019 program improves reproducibility in machine learning.
problem Ensuring machine learning research results are reproducible and reliable.
method Code submission policy, reproducibility challenge, and checklist integration.
result Improved reproducibility standards across the machine learning community.
New neural architectures with multivariate nonlinearities are optimal in function space.
problem Optimality of neural architectures with multivariate nonlinearities.
method Construction of Banach spaces via k-plane transform and sparsity-promoting norm, proving representer theorem. result Neural architectures with multivariate nonlinearities are optimal in function space.
This paper explores the recently proposed Graph Convolutional Network architecture proposed in (Kipf & Welling, 2016) The key points of their work is summarized and their results are reproduced. Graph regularization and alternative graph convolution approaches are explored. I find that explicit graph regularization was…
This chapter introduces reproducibility in machine learning for medical imaging.
problem Lack of reproducibility in machine learning for medical imaging.
method Distinguishes and defines types of reproducibility, outlines requirements, and discusses utility.
result Discussion on benefits and a plea for a non-dogmatic approach to reproducibility.
Tract-specific diffusion measures, as derived from brain diffusion MRI, have been linked to white matter tract structural integrity and neurodegeneration. As a consequence, there is a large interest in the automatic segmentation of white matter tract in diffusion tensor MRI data. Methods based on the tractography are p…
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.
A multilayer perceptron can behave as a generative classifier by applying bidirectional learning (BL). It consists of training an undirected neural network to map input to output and vice-versa; therefore it can produce a classifier in one direction, and a generator in the opposite direction for the same data. The lear…
In recent years, significant progress has been made in solving challenging problems across various domains using deep reinforcement learning (RL). Reproducing existing work and accurately judging the improvements offered by novel methods is vital to sustaining this progress. Unfortunately, reproducing results for state…
Recent developments in unsupervised representation learning have successfully established the concept of transfer learning in NLP. Mainly three forces are driving the improvements in this area of research: More elaborated architectures are making better use of contextual information. Instead of simply plugging in stati…
Hungarian text processing improved with efficient, accurate NLP pipelines.
problem Improving text processing for Hungarian language.
method Implemented in spaCy framework, focusing on efficiency and accuracy.
result Near state-of-the-art performance in all text preprocessing steps.
New model improves histopathology classification across magnifications.
problem Robust histopathology classification is difficult due to magnification shift.
method Domain-general model using stable sparse embedding signatures.
result Domain-general model outperformed baseline and GAN augmentation.
New activations improve deep network reproducibility without sacrificing accuracy.
problem Deep networks' reproducibility issues, especially on distributed systems.
method Developed SmeLU activations, smoother than ReLU, to enhance reproducibility.
result SmeLU activations provide better accuracy-reproducibility tradeoffs.
Deep learning has become increasingly popular in both supervised and unsupervised machine learning thanks to its outstanding empirical performance. However, because of their intrinsic complexity, most deep learning methods are largely treated as black box tools with little interpretability. Even though recent attempts …
This work benchmarks and theorizes robust NAS under adversarial training.
problem Lack of benchmark evaluations and theoretical guarantees for robust NAS architectures under adversarial training.
method Released a comprehensive data set and established a generalization theory using the neural tangent kernel.
result Established a generalization theory for robust NAS architectures under adversarial training.
New model explains visual illusions using sub-Riemannian geometry.
problem Mathematical modeling of Poggendorff-type visual illusions.
method Cortical-inspired sub-Riemannian model with sub-Laplacian evolution.
result Sub-Riemannian kernel enhances visual misperceptions and biases.
Survey of determinism issues in financial AI systems.
problem Vulnerabilities in reproducibility of financial AI systems.
method Literature review and first-party experiments on public financial datasets.
result Proposed a layered evaluation framework linking modality-specific metrics to audit readiness.
BayesBag improves reproducibility of Bayesian inference under model misspecification.
problem Bayesian posteriors can be unreliable and inconsistent under model misspecification.
method Apply bagging to the Bayesian posterior to improve reproducibility.
result Bagged posteriors typically satisfy reproducibility criteria under misspecification.
Machine-learning (ML) hardware and software system demand is burgeoning. Driven by ML applications, the number of different ML inference systems has exploded. Over 100 organizations are building ML inference chips, and the systems that incorporate existing models span at least three orders of magnitude in power consump…
A typical approach in estimating the learning rate of a regularized learning scheme is to bound the approximation error by the sum of the sampling error, the hypothesis error and the regularization error. Using a reproducing kernel space that satisfies the linear representer theorem brings the advantage of discarding t…
Fine-tuned open-source LLMs match or exceed closed-source models in social science research.
problem Limited scalability and high costs of large LLMs in social science research.
method Fine-tuning open-source models for specific tasks, exploring training set size effects, proposing hybrid workflow.
result Small, fine-tuned open-source LLMs achieve equal or superior performance to commercial alternatives.
For an unknown (new) classification dataset, choosing an appropriate deep learning architecture is often a recursive, time-taking, and laborious process. In this research, we propose a novel technique to recommend a suitable architecture from a repository of known models. Further, we predict the performance accuracy of…
NAS-Bench-Suite simplifies NAS evaluation across diverse tasks.
problem Limited and inconsistent NAS benchmarks hinder research reproducibility.
method Developed a comprehensive, extensible NAS benchmark suite.
result Many NAS conclusions do not generalize across different benchmarks.
Study assesses consistency and reproducibility of LLMs in finance and accounting tasks.
problem Consistency and reproducibility of LLM outputs in finance and accounting research.
method Extensive experimentation with 50 independent runs across 5 tasks using 3 OpenAI models.
result Task-specific patterns of consistency and reproducibility, with binary classification and sentiment analysis achieving near-perfect reproducibility.
Efficiently explains model outputs using HSIC, a dependence measure.
problem Efficiently explain model outputs for various architectures.
method HSIC, RKHS, Reproducing Kernel Hilbert Spaces, black-box attribution.
result Up to 8 times faster than previous methods while maintaining fidelity.
The Transformer architecture is widely used in natural language processing. Despite its success, the design principle of the Transformer remains elusive. In this paper, we provide a novel perspective towards understanding the architecture: we show that the Transformer can be mathematically interpreted as a numerical Or…
A benchmark for NLP models trained on text datasets.
problem Limited access to high-performance clusters for NAS experiments.
method Created a search space for recurrent neural networks on text datasets and trained 14k architectures.
result Demonstrated the potential of precomputed NAS results for NLP.
Co-designing efficient machine learning based systems across the whole hardware/software stack to trade off speed, accuracy, energy and costs is becoming extremely complex and time consuming. Researchers often struggle to evaluate and compare different published works across rapidly evolving software frameworks, hetero…
This work is a reproducibility study of the paper of Antoniou and Storkey [2019], published at NeurIPS 2019. Our results are in parts similar to the ones reported in the original paper, supporting the central claim of the paper that the proposed novel method, called Self-Critique and Adapt (SCA), improves the performan…
MACE architecture outperforms alternatives in various molecular and materials science tasks.
problem Improving machine learning force fields for diverse molecular and materials science applications.
method Evaluation of MACE architecture on various datasets and tasks, demonstrating data efficiency and excellent performance.
result MACE architecture generally outperforms alternatives across a wide range of systems, including amorphous carbon, universal materials modelling, and organic chemistry.
Improving the accuracy and robustness of deep neural nets (DNNs) and adapting them to small training data are primary tasks in deep learning research. In this paper, we replace the output activation function of DNNs, typically the data-agnostic softmax function, with a graph Laplacian-based high dimensional interpolati…
Role-wise data augmentation improves knowledge distillation effectiveness.
problem Existing knowledge distillation methods fail to utilize the full potential of teacher-student data interaction.
method Design and implement data augmentation agents with distinct roles for teacher and student.
result Specially tailored data points enhance the demonstration of teacher's knowledge to the student.
Study compares nine deep learning architectures for multi-horizon financial forecasting.
problem Evaluating the performance of deep learning architectures for multi-horizon financial forecasting.
method Conducted 918 experiments across cryptocurrency, forex, and equity markets using nine architectures.
result ModernTCN achieves the best mean rank (1.333) with a 75 percent first-place rate.
OGRePy simplifies tensor calculations in general relativity.
problem Complex tensor calculations in general relativity.
method Object-oriented Python package for symbolic tensor calculations.
result Reproduces functionality of Mathematica package OGRe with improvements.