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…
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 “train set”
Training set bugs are flaws in the data that adversely affect machine learning. The training set is usually too large for man- ual inspection, but one may have the resources to verify a few trusted items. The set of trusted items may not by itself be adequate for learning, so we propose an algorithm that uses these ite…
Machine-learned diagnosis models have shown promise as medical aides but are trained under a closed-set assumption, i.e. that models will only encounter conditions on which they have been trained. However, it is practically infeasible to obtain sufficient training data for every human condition, and once deployed such …
FLOPART solves peak detection by creating accurate train and test set predictions.
problem Correctly detecting peaks in sequential data.
method Dynamic programming changepoint algorithm with zero train label errors.
result FLOPART provides highly accurate predictions on both train and test sets.
Paper improves conformal prediction for imprecise training data.
problem Applying conformal prediction to partially labeled data.
method Generalizes conformal prediction for set-valued training and calibration data.
result Validates the proposed method and shows it outperforms baselines.
Stochastic gradient decent~(SGD) and its variants, including some accelerated variants, have become popular for training in machine learning. However, in all existing SGD and its variants, the sample size in each iteration~(epoch) of training is the same as the size of the full training set. In this paper, we propose a…
Deep learning models generalize by extending decision boundaries outside the convex hull of training data.
problem Understanding how deep learning models generalize beyond their training data.
method Investigation of decision boundaries inside and outside the convex hull of training sets, using various neural network architectures and training regimes.
result Over-parameterization is necessary for deep learning models to extend decision boundaries outside the convex hull of their training data.
Challenge encourages reproducible deep learning methods.
problem Inconsistent training behavior in deep learning competitions.
method Evaluate methods based on their training procedures, retrain in controlled settings.
result Guaranteed reproducibility and generalization of methods.
A conceptually simple way to classify images is to directly compare test-set data and training-set data. The accuracy of this approach is limited by the method of comparison used, and by the extent to which the training-set data cover configuration space. Here we show that this coverage can be substantially increased u…
Adversarial training effectiveness varies widely due to inconsistent training settings.
problem Variability in adversarial training effectiveness due to inconsistent training settings.
method Comprehensive evaluation of 10+ adversarial training methods and their hyperparameters.
result Basic training settings like weight decay can significantly impact adversarial robustness.
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.
We train a network to generate mappings between training sets and classification policies (a 'classifier generator') by conditioning on the entire training set via an attentional mechanism. The network is directly optimized for test set performance on an training set of related tasks, which is then transferred to unsee…
Recently, a backdoor data poisoning attack was proposed, which adds mislabeled examples to the training set, with an embedded backdoor pattern, aiming to have the classifier learn to classify to a target class whenever the backdoor pattern is present in a test sample. Here, we address post-training detection of innocuo…
Deep learning improves image reconstruction, but scaling up training sets doesn't significantly boost performance.
problem Understanding the impact of training set size on deep learning image reconstruction.
method Empirical study and analytical characterization of performance scaling laws.
result Scaling up training set size does not significantly improve reconstruction quality for deep learning.
Deep networks with a wide layer ensure sublevel set connectivity.
problem Ensuring connectivity of sublevel sets in deep learning.
method Analyzing the connectivity of sublevel sets in deep neural networks with a specific layer width.
result A single wide layer of width suffices to prove connectivity of sublevel sets.
Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task Arithmeticcs.LG
CUTS removes corruption from models without clean data, improving utility and security.
problem Removing corruption from models without access to clean training data.
method CUTS uses a proxy set to amplify corruption and subtract it from model weights.
result CUTS recovers a large fraction of lost utility and nearly eliminates attacks with minimal damage.
In this paper we propose the use of Generative Adversarial Networks (GAN) to generate artificial training data for machine learning tasks. The generation of artificial training data can be extremely useful in situations such as imbalanced data sets, performing a role similar to SMOTE or ADASYN. It is also useful when t…
Automated suggestions help train technicians diagnose incidents faster.
problem Manual and time-consuming incident diagnosis by train maintenance technicians.
method Developed and deployed a learning machine to suggest diagnostics to technicians.
result The model refines its accuracy through feedback from experts and uses feature engineering.
Deep neural networks are vulnerable to adversarial examples. Prior defenses attempted to make deep networks more robust by either changing the network architecture or augmenting the training set with adversarial examples, but both have inherent limitations. Motivated by recent research that shows outliers in the traini…
A new method selects training samples for fine-tuning using validation set inference.
problem Selecting training examples for fine-tuning with limited target data.
method Invert train-validation roles; select samples affecting most predictions.
result Our method achieves lower test log-loss than state-of-the-art approaches.
The paper addresses the reliability of conformal prediction under covariate shift.
problem Ensuring reliable prediction sets under covariate shift.
method Derives upper bounds on training-conditional coverage.
result Offers PAC guarantees for conformal prediction methods.
A form of generalisation error known as Off Training Set (OTS) error was recently introduced in [Wolpert, 1996b], along with a theorem showing that small training set error does not guarantee small OTS error, unless assumptions are made about the target function. Here it is shown that the applicability of this theorem …
Efficiently trains SVM models on large datasets using coreset technology.
problem Training large-scale SVM models efficiently on Big Data.
method Developed an algorithm to create a coreset, a small representative subset of data.
result Proved the size of coreset required for SVM models and showed its applicability to streaming data.
Recently, a special type of data poisoning (DP) attack targeting Deep Neural Network (DNN) classifiers, known as a backdoor, was proposed. These attacks do not seek to degrade classification accuracy, but rather to have the classifier learn to classify to a target class whenever the backdoor pattern is present in a tes…
Training Deep Neural Networks with Different Datasets In-the-wild: The Emotion Recognition Paradigmcs.LG
A novel procedure is presented in this paper, for training a deep convolutional and recurrent neural network, taking into account both the available training data set and some information extracted from similar networks trained with other relevant data sets. This information is included in an extended loss function use…
Large labeled training sets are the critical building blocks of supervised learning methods and are key enablers of deep learning techniques. For some applications, creating labeled training sets is the most time-consuming and expensive part of applying machine learning. We therefore propose a paradigm for the programm…
Zellner (1988) modeled statistical inference in terms of information processing and postulated the Information Conservation Principle (ICP) between the input and output of the information processing block, showing that this yielded Bayesian inference as the optimum information processing rule. Recently, Alemi (2019) re…
Study proves existence of robust classifiers in multiclass adversarial training.
problem Proves existence of robust classifiers in multiclass adversarial training.
method Three models of adversarial training in multiclass classification, proving existence of Borel measurable robust classifiers.
result Proves existence of Borel measurable robust classifiers in each model.
Research improves open-set learning by leveraging unlabelled data.
problem Learning between observed and unobserved novel categories.
method Unified policy of positive and unlabelled learning, semi-supervised learning, and open-set recognition.
result Achieves state-of-the-art results in open-set learning.
PFNs pre-train models on simulated data to predict class probabilities.
problem Training machine learning models on large datasets.
method Pre-train a fixed model on small simulated datasets and use it to infer class probabilities in-context.
result PFNs achieve state-of-the-art performance and improve with larger inference data.
This paper improves deep learning classifiers by integrating conformal prediction during training.
problem High-stake AI applications require reliable uncertainty estimates for safe deployment.
method Integrates conformal prediction (CP) during training of deep learning models.
result Reduces inefficiency and allows more control over confidence sets.
We propose a novel method to train deep convolutional neural networks which learn from multiple data sets of varying input sizes through weight sharing. This is an advantage in chemometrics where individual measurements represent exact chemical compounds and thus signals cannot be translated or resized without disturbi…
Machine Learning (ML) algorithms are used to train computers to perform a variety of complex tasks and improve with experience. Computers learn how to recognize patterns, make unintended decisions, or react to a dynamic environment. Certain trained machines may be more effective than others because they are based on mo…
Develops a fast method to analyze image similarities without pre-trained models.
problem Lack of efficient methods to analyze fine-level similarities in large image datasets.
method Wavelet decomposition and numerical analysis tools.
result Identifies similar images in standard datasets (like CIFAR) in a few seconds.
Machine learning classifiers are often trained to recognize a set of pre-defined classes. However, in many applications, it is often desirable to have the flexibility of learning additional concepts, with limited data and without re-training on the full training set. This paper addresses this problem, incremental few-s…
Vanilla CNNs, as uncalibrated classifiers, suffer from classifying out-of-distribution (OOD) samples nearly as confidently as in-distribution samples. To tackle this challenge, some recent works have demonstrated the gains of leveraging available OOD sets for training end-to-end calibrated CNNs. However, a critical que…
GMVAE improves open-set classification by clustering latent representations.
problem Improving open-set classification accuracy and robustness.
method Cooperative learning of reconstruction and clustering in the latent space of a GMVAE.
result Achieved an average F1 improvement of 29.5% in open-set classification.
This paper applies combinatorial testing to machine learning for robust model performance.
problem Identifying robust machine learning models using test and training sets.
method Adapting combinatorial interaction testing for machine learning, focusing on simple features.
result Combinatorial coverage can enhance model performance and robustness.
Generative Adversarial Networks are a new family of generative models, frequently used for generating photorealistic images. The theory promises for the GAN to eventually reach an equilibrium where generator produces pictures indistinguishable for the training set. In practice, however, a range of problems frequently p…
MCAL reduces labeling costs by 6x for auto-labeling data sets.
problem Expensive human annotation for ground-truth data sets.
method Iterative approach that trains a classifier to auto-label part of the data set, determining which samples to label using humans and which to label using the classifier at each step.
result 6x lower overall cost compared to human labeling the entire data set, always cheaper than competing strategies.
Building a large image dataset with high-quality object masks for semantic segmentation is costly and time consuming. In this paper, we introduce a principled semi-supervised framework that only uses a small set of fully supervised images (having semantic segmentation labels and box labels) and a set of images with onl…
Training on mixed distributions improves test performance even when components are unrelated.
problem Improving test performance with mismatched training and test distributions.
method Analyzing mixture distributions with different training and test proportions.
result Distribution shift can be beneficial, improving test performance even when components are unrelated.
Modern machine learning systems such as image classifiers rely heavily on large scale data sets for training. Such data sets are costly to create, thus in practice a small number of freely available, open source data sets are widely used. We suggest that examining the geo-diversity of open data sets is critical before …
S2OSC improves OSC by filtering and re-training models with out-of-class instances.
problem Difficulty in classifying out-of-class instances during inference.
method S2OSC combines semi-supervised learning, out-of-class instance filtering, and model re-training.
result S2OSC achieves state-of-the-art performance in various OSC tasks.
Enhances ZSL models with biologically inspired feature enhancement.
problem Limited training data leads to poor feature extraction from pre-trained models.
method Dual-channel learning framework using auxiliary data sets.
result Improves ZSL model's generalization ability and achieves state-of-the-art results.
PLRM synthesizes labels from mismatched sources for better training sets.
problem Creating labeled training sets is a major challenge in machine learning.
method PLRM uses probabilistic modeling to synthesize labels from indirect supervision sources with different output spaces.
result PLRM outperforms baselines by 2%-9% on various tasks.
Paper shows pre-training and transfer learning reduce sample complexity for neural networks.
problem Training high-dimensional supervised learning with limited labeled data.
method Study of single-layer neural networks via online stochastic gradient descent, considering concept shift.
result Pre-training and transfer learning reduce sample complexity by polynomial factors under general assumptions.
A remarkable recent discovery in machine learning has been that deep neural networks can achieve impressive performance (in terms of both lower training error and higher generalization capacity) in the regime where they are massively over-parameterized. Consequently, over the past year, the community has devoted growin…