Due to the surprisingly good representation power of complex distributions, neural network (NN) classifiers are widely used in many tasks which include natural language processing, computer vision and cyber security. In recent works, people noticed the existence of adversarial examples. These adversarial examples break…
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 “iterative training”
New method defends against both single-step and iterative adversarial examples.
problem Defending against adversarial examples, especially iterative ones, is computationally expensive.
method Single-Step Adversarial Training (SST) with modifications.
result Our method outperforms state-of-the-art methods in both accuracy and training time.
Adversarial training is a technique for training robust machine learning models. To encourage robustness, it iteratively computes adversarial examples for the model, and then re-trains on these examples via some update rule. This work analyzes the performance of adversarial training on linearly separable data, and prov…
Self-training in linear models shows a U-shaped test-risk curve due to signal forgetting and denoising.
problem Understanding the dynamics of iterative self-training in high-dimensional linear regression.
method Derivation of deterministic-equivalent recursions for prediction risk and effective noise, analysis of signal forgetting and denoising effects.
result An optimal early-stopping time is determined, and a U-shaped test-risk curve is observed.
Machine learning (ML) training algorithms often possess an inherent self-correcting behavior due to their iterative-convergent nature. Recent systems exploit this property to achieve adaptability and efficiency in unreliable computing environments by relaxing the consistency of execution and allowing calculation errors…
Improved pruning method using iterative sensitivity ranking before training.
problem Improper sensitivity propagation in existing pruning methods.
method Iterative application of SNIP criterion before training.
result State-of-the-art sparsity-performance trade-offs achieved.
The paper studies stability of generative models trained on mixed data.
problem Training generative models on mixed datasets (real and synthetic data).
method Developed a framework to rigorously study stability under specific conditions.
result Proved the stability of iterative training under certain conditions.
The paper shows how training with synthetic data can lead to model improvement, not degradation, under certain conditions.
problem Model collapse in iterative training on contaminated sources.
method Statistical analysis of iterative training on a mixture of true and synthetic data.
result Training with synthetic data can lead to model improvement, not degradation, under specific conditions.
WaveFit uses fixed-point iteration to create high-quality neural vocoders.
problem Creating high-quality neural vocoders with fast inference.
method Integrates GANs' adversarial training into a DDPM-like iterative framework based on fixed-point iteration.
result WaveFit synthesizes speech with naturalness comparable to human speech, and is significantly faster than existing methods.
Injecting adversarial examples during training, known as adversarial training, can improve robustness against one-step attacks, but not for unknown iterative attacks. To address this challenge, we first show iteratively generated adversarial images easily transfer between networks trained with the same strategy. Inspir…
The performance of deep (reinforcement) learning systems crucially depends on the choice of hyperparameters. Their tuning is notoriously expensive, typically requiring an iterative training process to run for numerous steps to convergence. Traditional tuning algorithms only consider the final performance of hyperparame…
Many real world learning tasks involve complex or hard-to-specify objectives, and using an easier-to-specify proxy can lead to poor performance or misaligned behavior. One solution is to have humans provide a training signal by demonstrating or judging performance, but this approach fails if the task is too complicated…
We present the use of the fitted Q iteration in algorithmic trading. We show that the fitted Q iteration helps alleviate the dimension problem that the basic Q-learning algorithm faces in application to trading. Furthermore, we introduce a procedure including model fitting and data simulation to enrich training data as…
We describe an approach to Grammatical Error Correction (GEC) that is effective at making use of models trained on large amounts of weakly supervised bitext. We train the Transformer sequence-to-sequence model on 4B tokens of Wikipedia revisions and employ an iterative decoding strategy that is tailored to the loosely-…
Deep RL agents suffer from transient non-stationarity, which ITER mitigates.
problem Transient non-stationarity in deep RL agents affects generalization.
method Iterated Relearning (ITER) transfers knowledge between networks to reduce non-stationarity.
result ITER improves deep RL agents' performance on generalization benchmarks.
A new iterative K-FAC algorithm reduces training time and memory usage.
problem Training deep learning models efficiently.
method Uses conjugate gradient to approximate Fisher information matrix without generating the matrix or factors.
result Time and memory complexity of iterative CG-FAC is less than standard K-FAC.
Generalization Bounds for Noisy Iterative Algorithms Using Properties of Additive Noise Channelsstat.ML
The paper analyzes generalization of noisy iterative algorithms using communication theory.
problem Generalization of models trained by noisy iterative algorithms under different distributions.
method Connecting noisy iterative algorithms to additive noise channels in communication theory.
result Distribution-dependent generalization bounds for noisy iterative algorithms.
PACE optimizes training for averaged language models, improving performance.
problem How to optimize training for averaged language model iterates.
method Formulated as an optimal-control problem, solved for minimizing error of the average with a penalty on intervention size.
result PACE improves the limiting squared error of the iterate-average estimator by an arbitrarily large factor on some instances.
Paper presents a new training method for overparametrized neural networks that reduces time per iteration.
problem Scalability issue in training overparametrized neural networks.
method Uses a new view of neural networks as binary search trees, modifying a small subset of nodes per iteration.
result Reduces amortized time per iteration to from previous .
Machine learning models are vulnerable to adversarial examples. Iterative adversarial training has shown promising results against strong white-box attacks. However, adversarial training is very expensive, and every time a model needs to be protected, such expensive training scheme needs to be performed. In this paper,…
ASTRA improves TDA by more accurately approximating iHVP.
problem Improving insights into training data attribution.
method ASTRA uses EKFAC-preconditioner on Neumann series iterations to accurately approximate iHVP.
result Improving iHVP approximation significantly improves TDA performance.
New method controls sparse feature updates in deep networks.
problem Understanding sparse feature updates in deep networks during training.
method Iterative linearised training method to control sparse feature updates.
result Iterative linearised training surprisingly performs on par with standard training, requiring less frequent feature learning.
The paper challenges the belief that more inner iterations at test time improve performance in implicit deep learning.
problem The performance improvement of implicit deep learning models with increased inner iterations at test time.
method Theoretical analysis of a simple setting, validation on implicit deep learning problems.
result Overparametrization plays a key role; increasing the number of iterations at test time does not improve performance for overparametrized networks.
Support Vector Data Description (SVDD) is a popular outlier detection technique which constructs a flexible description of the input data. SVDD computation time is high for large training datasets which limits its use in big-data process-monitoring applications. We propose a new iterative sampling-based method for SVDD…
OptEx accelerates first-order optimization with parallelized iterations.
problem Inefficiencies in first-order optimization algorithms for complex tasks.
method Approximately parallelized iterations using kernelized gradient estimation.
result OptEx achieves substantial efficiency improvements with an effective acceleration rate of .
Improving optimization for iterate-averaged language models
problem How to optimize the averaged model returned by Language Model pipelines
method Formulating optimizer design as an optimal-control problem
result Proven convergence rate and strict improvement in squared error
Generative models in molecular design tend to be richly parameterized, data-hungry neural models, as they must create complex structured objects as outputs. Estimating such models from data may be challenging due to the lack of sufficient training data. In this paper, we propose a surprisingly effective self-training a…
This paper improves self-play learning in games by manipulating experience distributions.
problem Improving self-play learning in games through better experience sampling.
method Three approaches: weighted sampling, Prioritized Experience Replay, and diversifying trajectories.
result Major improvements in early training performance in some games, minor improvements overall.
Inspired by recent advances in deep learning, we propose a novel iterative BP-CNN architecture for channel decoding under correlated noise. This architecture concatenates a trained convolutional neural network (CNN) with a standard belief-propagation (BP) decoder. The standard BP decoder is used to estimate the coded b…
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 …
LIIT uses large deviations to train neural networks faster.
problem Training neural networks requires large amounts of data, leading to inefficiencies.
method LIIT uses large deviations principle to generate and update training samples.
result LIIT achieves similar classification performance with smaller, more representative samples.
Pruning is a well-established technique for removing unnecessary structure from neural networks after training to improve the performance of inference. Several recent results have explored the possibility of pruning at initialization time to provide similar benefits during training. In particular, the "lottery ticket h…
Self-training improves generalization by fitting to reliable pseudo-labels or gradually improving the classification plane.
problem Understanding how self-training improves generalization in high-dimensional Gaussian mixtures.
method Analyzing iterative self-training on binary Gaussian mixtures in the asymptotic limit.
result ST improves generalization by fitting to reliable pseudo-labels or gradually improving the classification plane.
An iterative method of learning has become a paradigm for training deep convolutional neural networks (DCNN). However, utilizing a non-iterative learning strategy can accelerate the training process of the DCNN and surprisingly such approach has been rarely explored by the deep learning (DL) community. It motivates thi…
SINF models transform arbitrary PDFs to target PDFs using 1D slices.
problem Transforming arbitrary probability distributions to target distributions efficiently.
method Iterative Optimal Transport of 1D slices, maximizing Wasserstein distance.
result SINF models generate high-quality samples and competitive density estimates.
In unsupervised learning, collecting more data is not always a costly process unlike the training. For example, it is not hard to enlarge the 40GB WebText used for training GPT-2 by modifying its sampling methodology considering how many webpages there are in the Internet. On the other hand, given that training on this…
IMP finds sparse subnetworks that match full networks, revealing geometric insights.
problem Finding sparse subnetworks that match full, overparameterized networks.
method Iterative magnitude pruning (IMP) algorithm, analyzing error landscape geometry.
result IMP masks found at end of training convey useful information for rewound networks.
Recurrent Neural Networks (RNNs) are powerful models that achieve exceptional performance on several pattern recognition problems. However, the training of RNNs is a computationally difficult task owing to the well-known "vanishing/exploding" gradient problem. Algorithms proposed for training RNNs either exploit no (or…
New method speeds up Gaussian process training and inference for large datasets.
problem Training and inference in Gaussian processes are computationally expensive for large datasets.
method Iterative alternating projection method that accesses subblocks of the kernel matrix, reducing time and space complexity.
result Empirically, the method accelerates GP training and inference by up to 72x compared to conjugate gradients.
Bayesian optimization is popular for optimizing time-consuming black-box objectives. Nonetheless, for hyperparameter tuning in deep neural networks, the time required to evaluate the validation error for even a few hyperparameter settings remains a bottleneck. Multi-fidelity optimization promises relief using cheaper p…
Paper proposes an efficient method for bounding box annotation in object detection.
problem Manual annotation of bounding boxes is tedious and resource-intensive.
method Iterative training of object detector on small batches of labeled images, with human annotator correcting errors.
result Significant reduction in human annotation effort, up to 75%.
Traditional learning methods for training Markov random fields require doing inference over all variables to compute the likelihood gradient. The iteration complexity for those methods therefore scales with the size of the graphical models. In this paper, we propose \emph{block belief propagation learning} (BBPL), whic…
SGD's performance improves with critical batch size, minimizing SFO complexity.
problem Optimizing SGD's performance with batch size and learning rate.
method Analysis of SGD using constant and decaying learning rates, focusing on batch size effects.
result SGD with critical batch size minimizes SFO complexity.
Lottery tickets find good initializations for IMP with sparse training.
problem Finding good initializations for iterative magnitude pruning (IMP) in sparse networks.
method Empirical study of IMP performance with varying pre-training data and iterations.
result Training on a small fraction of data suffices to obtain good initializations for IMP.
Two preprocessing techniques reduce neural network training cost.
problem Training over-parameterized neural networks efficiently.
method Two novel preprocessing techniques to reduce training cost.
result Training cost reduced to sublinear per iteration.
Early neural network training reveals important sub-networks and weight distributions.
problem Understanding the early phases of neural network training.
method Extensive measurements and quantitative probing of weight distribution and dataset reliance.
result Deep networks are not robust to reinitializing with random weights while maintaining signs, and weight distributions are highly non-independent.
Speeding Up Budgeted Stochastic Gradient Descent SVM Training with Precomputed Golden Section Searchcs.LG
Limiting the model size of a kernel support vector machine to a pre-defined budget is a well-established technique that allows to scale SVM learning and prediction to large-scale data. Its core addition to simple stochastic gradient training is budget maintenance through merging of support vectors. This requires solvin…
Deep-neural-network-based image reconstruction has demonstrated promising performance in medical imaging for under-sampled and low-dose scenarios. However, it requires large amount of memory and extensive time for the training. It is especially challenging to train the reconstruction networks for three-dimensional comp…