Approach to verify neural network training integrity.
problem Poisoning attacks during neural network training.
method Use of cryptographic mechanisms to verify training integrity.
result Provable verification of neural network training integrity.
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “training integrity”
learn2mix trains neural nets faster by adjusting class proportions dynamically.
problem Training neural nets efficiently with limited resources and imbalanced classes.
method Adaptive class proportion adjustment during training.
result Neural nets trained with learn2mix converge faster than static methods.
Improved speech recognition with language model integration in sequence-to-sequence models.
problem Improving word error rate in speech recognition models.
method Log-linear combination of acoustic and language models with per-token renormalization.
result The proposed method shows good improvements over standard model combination on Librispeech system.
Testing the implementation of deep learning systems and their training routines is crucial to maintain a reliable code base. Modern software development employs processes, such as Continuous Integration, in which changes to the software are frequently integrated and tested. However, testing the training routines requir…
Integral Transforms in a Physics-Informed (Quantum) Neural Network setting: Applications & Use-Casesquant-ph
This work integrates differentiation and integration in Physics-Informed Neural Networks.
problem Solving integro-differential equations and computing integral transforms.
method Augmenting Physics-Informed Neural Networks with automatic integration.
result Solving complex integral transforms and integro-differential equations.
ContinuousNet generalizes ResNets to continuous dynamical systems.
problem ResNets fail to be meaningful dynamical integrators.
method Embedding continuous dynamical systems into higher-order numerical integration schemes (Runge Kutta).
result ContinuousNet exhibits invariance to discrete time step sizes and numerical integration schemes.
A new model DKMPP integrates covariates and uses an integration-free method for spatio-temporal point processes.
problem Training intractable deep spatio-temporal point processes with multimodal covariates.
method DKMPP uses a deep kernel to model complex relationships and an integration-free score matching method.
result DKMPP and score-based estimators outperform baseline models in spatio-temporal point processes.
Improved time series forecasting with expert loss integration.
problem Enhancing time series forecasting accuracy and efficiency.
method Adaptive Mixture-of-Experts framework with expert-specific loss integration and online learning.
result Significantly improved forecasting accuracy and computational efficiency.
Paper introduces a novel error measure for neural networks integrating statistical and information theory.
problem No single error measure is universally best for neural network training.
method Developed a novel error measure and integrated it into the Levenberg-Marquardt algorithm.
result Self-adaptive, dynamic learning algorithm improves both model accuracy and training process.
Hybrid model improves weather forecasting accuracy.
problem Combining physics and machine learning for better weather predictions.
method Offline and online training of a neural network to correct model errors in the IFS.
result The hybrid model reduces forecast errors and improves accuracy.
New methods improve integration of external LMs with AED models.
problem Improving performance of AED models by integrating external LMs.
method Comparing and proposing novel methods to estimate implicit LM from AED models.
result Proposed methods outperform previous approaches.
UncertaintyPlayground simplifies uncertainty estimation in Python.
problem Uncertainty estimation in supervised learning tasks.
method Sparse and Variational Gaussian Process Regressions for normally distributed outcomes, Mixed Density Networks for mixed distributions.
result Fast and simplified uncertainty estimation through Python library.
New method stabilizes GAN training by solving ODEs.
problem Stability issues in GAN training.
method Solving ordinary differential equations (ODEs) to stabilize GAN training.
result Well-known ODE solvers can stabilize GAN training.
Background: Pharmacokinetic evaluation is one of the key processes in drug discovery and development. However, current absorption, distribution, metabolism, excretion prediction models still have limited accuracy. Aim: This study aims to construct an integrated transfer learning and multitask learning approach for deve…
The paper introduces a new ODE approach to improve Wasserstein GANs.
problem Improving Wasserstein GANs for better training results.
method Derives an ODE representing the gradient flow of Wasserstein-1 loss and proposes a new model W1-FE.
result W1-FE outperforms WGAN in training experiments across various dimensions.
Neural networks enjoy widespread use, but many aspects of their training, representation, and operation are poorly understood. In particular, our view into the training process is limited, with a single scalar loss being the most common viewport into this high-dimensional, dynamic process. We propose a new window into …
Multi-view Factorization AutoEncoder with Network Constraints for Multi-omic Integrative Analysiscs.LG
Multi-omic data provides multiple views of the same patients. Integrative analysis of multi-omic data is crucial to elucidate the molecular underpinning of disease etiology. However, multi-omic data has the "big p, small N" problem (the number of features is large, but the number of samples is small), it is challenging…
Although information extraction and coreference resolution appear together in many applications, most current systems perform them as ndependent steps. This paper describes an approach to integrated inference for extraction and coreference based on conditionally-trained undirected graphical models. We discuss the advan…
A new method for estimating uncertainties in neural ODEs without numerical integration.
problem Accurate estimation of predictive uncertainties in neural ODEs.
method Distributional Gradient Matching (DGM) algorithm that jointly trains a smoother and a dynamics model.
result Significantly more accurate predictions compared to traditional methods.
POET enables large neural network training on tiny devices with reduced energy.
problem Training large neural networks on memory-limited edge devices.
method Jointly optimizes rematerialization and paging for memory reduction, formulating an MILP for energy-efficient training.
result POET trains ResNet-18 and BERT within Cortex-M memory constraints, outperforming current methods in energy efficiency.
Derives ideal train/test split for ridge regression in large data limit.
problem Finding optimal train/test split for ridge regression in large data scenarios.
method Mathematical derivation of optimal train/test split, considering ridge tuning parameter and asymptotic behavior.
result The optimal train/test split for ridge regression in the large data limit depends weakly on the ridge tuning parameter alpha.
In recent years, more machine learning algorithms have been applied to odor classification. These odor classification algorithms usually assume that the training datasets are static. However, for some odor recognition tasks, new odor classes continually emerge. That is, the odor datasets are dynamically growing while b…
Study shows partially-typed NER datasets can match fully-typed ones in model performance.
problem Leveraging multiple partially-typed NER datasets for training models without fully-typed annotations.
method Systematic analysis and controlled experiments comparing partially-typed and fully-typed datasets.
result Models trained with partially-typed annotations can achieve similar performance to those trained with fully-typed annotations.
Improved S&P stock prediction by integrating related stocks' data.
problem Lack of comprehensive data in stock prediction models.
method Enriched stock data with related stocks, tested five similarity functions, and used co-integration similarity for best results.
result Prediction model on similar stocks had significantly better accuracy and profit.
In this paper, we present a novel unsupervised feature learning architecture, which consists of a multi-clustering integration module and a variant of RBM termed multi-clustering integration RBM (MIRBM). In the multi-clustering integration module, we apply three unsupervised K-means, affinity propagation and spectral c…
Next generation of embedded Information and Communication Technology (ICT) systems are collaborative systems able to perform autonomous tasks. The remarkable expansion of the embedded ICT market, together with the rise and breakthroughs of Artificial Intelligence (AI), have put the focus on the Edge as it stands as one…
We consider the problem of selective prediction (also known as reject option) in deep neural networks, and introduce SelectiveNet, a deep neural architecture with an integrated reject option. Existing rejection mechanisms are based mostly on a threshold over the prediction confidence of a pre-trained network. In contra…
Dropout is used to avoid overfitting by randomly dropping units from the neural networks during training. Inspired by dropout, this paper presents GI-Dropout, a novel dropout method integrating with global information to improve neural networks for text classification. Unlike the traditional dropout method in which the…
ForecastGAN: A Decomposition-Based Adversarial Framework for Multi-Horizon Time Series Forecastingcs.LG
ForecastGAN improves multi-horizon time series forecasting by integrating numerical and categorical features.
problem Limited performance of existing approaches in short-term and long-term forecasting.
method Decomposition, model selection, adversarial training.
result ForecastGAN consistently outperforms state-of-the-art transformer models for short-term forecasting.
Machine learning and deep learning have gained popularity and achieved immense success in Drug discovery in recent decades. Historically, machine learning and deep learning models were trained on either structural data or chemical properties by separated model. In this study, we proposed an architecture training simult…
This work introduces a fixed-point optimization for variational inference.
problem Improving quantified uncertainty in predictions by optimizing a simplified distribution over parameters.
method Projective integral updates for high-dimensional variational inference.
result Efficient quasirandom quadrature sequence for mean-field distributions, leading to quasi-Newton variational Bayes (QNVB).
We introduce new families of Integral Probability Metrics (IPM) for training Generative Adversarial Networks (GAN). Our IPMs are based on matching statistics of distributions embedded in a finite dimensional feature space. Mean and covariance feature matching IPMs allow for stable training of GANs, which we will call M…
Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systemsstat.ML
Despite its great success, machine learning can have its limits when dealing with insufficient training data. A potential solution is the additional integration of prior knowledge into the training process which leads to the notion of informed machine learning. In this paper, we present a structured overview of various…
We propose a new integrated method of exploiting model, batch and domain parallelism for the training of deep neural networks (DNNs) on large distributed-memory computers using minibatch stochastic gradient descent (SGD). Our goal is to find an efficient parallelization strategy for a fixed batch size using process…
Machine learning applications in medical imaging are frequently limited by the lack of quality labeled data. In this paper, we explore the self training method, a form of semi-supervised learning, to address the labeling burden. By integrating reinforcement learning, we were able to expand the application of self train…
Study integrates attentional and spacing factors to improve category learning models.
problem Understanding the impact of training sequences on category learning.
method Introduced a novel integration of attentional factors and spacing into logistic knowledge tracing models.
result Enhanced model predicts students' learning outcomes better than existing models.
DPSM minimizes prediction set size by integrating conformal principles into deep classifier training.
problem Large prediction sets from standard conformal methods are impractical.
method Formulates conformal training as bilevel optimization, proposing DPSM algorithm.
result Significantly reduces prediction set size compared to prior methods.
Deep neural networks (DNNs) provide high image classification accuracy, but experience significant performance degradation when perturbation from various sources are present in the input. The lack of resilience to input perturbations makes DNN less reliable for systems interacting with physical world such as autonomous…
Twin-Boot integrates uncertainty estimation into optimization using parallel training of identical models.
problem Uncertainty in overparameterized models, especially in low-data regimes.
method Twin-Bootstrap Gradient Descent (Twin-Boot) trains two identical models on independent bootstrap samples and uses their divergence to guide learning.
result Improves calibration and generalization, yields interpretable uncertainty maps.
Mean-Field Approximation to Gaussian-Softmax Integral with Application to Uncertainty Estimationcs.LG
A new method for uncertainty estimation in neural networks using Gaussian-softmax integration.
problem Quantifying uncertainty in neural network predictions.
method Proposes a single-model approach integrating Gaussian distribution with softmax outputs, using mean-field approximation.
result Competitive performance on uncertainty estimation tasks and outperforms many methods on out-of-distribution detection.
Mobile app development in recent years has resulted in new products and features to improve human life. Mobile telematics is one such development that encompasses multidisciplinary fields for transportation safety. The application of mobile telematics has been explored in many areas, such as insurance and road safety. …
New LFR algorithm ensures fair predictions with theoretical guarantees.
problem Ensuring fairness in AI algorithms for social decision-making.
method Proposes a new adversarial training scheme using IPM with a parametric family of discriminators.
result Theoretical guarantee of fairness in final prediction models.
Integrates fairness guarantees into deep learning models.
problem Ensuring fairness in deep learning models.
method Integrates a differentiable fairness layer into neural models and uses an online primal-dual algorithm for provable fairness guarantees.
result Guarantees a chosen notion of output parity in deep learning models.
Boosting CNNs with dynamic feature selection and boosting weights improves accuracy and efficiency.
problem Expensive training of deep CNNs and manual architecture design.
method Dynamic feature selection, importance sampling, and boosting weights integrated into network training.
result Boosted CNN variants consistently outperform conventional CNNs in accuracy and training speed.
We add prior knowledge to deep networks to make them invariant to transformations.
problem Creating deep networks invariant to transformations like rotation.
method A novel layer based on invariant integration to enforce feature space invariances.
result State-of-the-art performance on the Rotated-MNIST dataset.
Paper uses Random Matrix Theory for optimal training-testing data split.
problem Finding ideal training-testing data split for linear regression.
method Random Matrix Theory applied to Gaussian multivariate data.
result Ideal training and test sizes derived for any model.
New method uses TT approximations to solve HJB equations for efficient sampling.
problem Efficiently sampling from complex probability densities.
method Direct time integration of HJB equations using Tensor Train compression.
result Sample-free, dimensionality-avoiding integration method.
Q-NETs use neural networks to estimate integrals of low-dimensional functions efficiently.
problem Estimating integrals of multidimensional functions with costly evaluations.
method Fixed neural networks (Q-NETs) that operate on proxy function parameters to calculate exact integrals over subsets of dimensions.
result Q-NETs can calculate integrals over any subset of dimensions without resampling or retraining the proxy.