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.
Statistical test detects model degradations in optimized language models.
CRC improves multivariate forecasting accuracy without risking performance degradation.
The most common method for DNN pruning is hard thresholding of network weights, followed by retraining to recover any lost accuracy. Recently developed smart pruning algorithms use the DNN response over the training set for a variety of cost functions to determine redundant network weights, leading to less accuracy deg…
Self-training with noisy student-teacher boosts keyword spotting accuracy.
Deep learning predicts RNA degradation from crowdsourced data.
We study the tradeoff between computational effort and classification accuracy in a cascade of deep neural networks. During inference, the user sets the acceptable accuracy degradation which then automatically determines confidence thresholds for the intermediate classifiers. As soon as the confidence threshold is met,…
Recurrent Neural Networks (RNNs) are becoming increasingly important for time series-related applications which require efficient and real-time implementations. The recent pruning based work ESE suffers from degradation of performance/energy efficiency due to the irregular network structure after pruning. We propose bl…
Paper develops a hybrid DNN approach for RUL prediction with adaptive drift.
Theoretical framework for neural network compression using sparsity norms.
Suitability filter detects model performance degradation in real-world deployment.
Artificial neural network (ANN) provides superior accuracy for nonlinear alternating current (AC) state estimation (SE) in smart grid over traditional methods. However, research has discovered that ANN could be easily fooled by adversarial examples. In this paper, we initiate a new study of adversarial false data injec…
In this work, we ask two questions: 1. Can we predict the type of community interested in a news article using only features from the article content? and 2. How well do these models generalize over time? To answer these questions, we compute well-studied content-based features on over 60K news articles from 4 communit…
Improved neural quantization reduces accuracy loss to less than 1% with 4-bit weights.
Paper presents robust boosting methods for label noise.
The potential for learned models to amplify existing societal biases has been broadly recognized. Fairness-aware classifier constraints, which apply equality metrics of performance across subgroups defined on sensitive attributes such as race and gender, seek to rectify inequity but can yield non-uniform degradation in…
Neural Network classifiers have been used successfully in a wide range of applications. However, their underlying assumption of attack free environment has been defied by adversarial examples. Researchers tried to develop defenses; however, existing approaches are still far from providing effective solutions to this ev…
New techniques improve 16-bit training accuracy without 32-bit units.
Paper presents a probabilistic diagnostic model for identifying and treating supervised learning degradation issues.
This paper improves deep learning models' accuracy with differential privacy using gradient encoding and denoising.
The paper examines how adversarial robustness affects accuracy disparity across different classes.
TxSim models DNN training on resistive crossbars, improving accuracy and feasibility.
Study optimizes HTL-free PSCs with MWCNTs, improving efficiency and stability.
Enhances image quality to improve test-time adaptation accuracy.
Background: Predictive modeling is a key component of solutions to many healthcare problems. Among all predictive modeling approaches, machine learning methods often achieve the highest prediction accuracy, but suffer from a long-standing open problem precluding their widespread use in healthcare. Most machine learning…
New trade-off found between accuracy and adversarial robustness in regression.
We present a principled framework to address resource allocation for realizing boosting algorithms on substrates with communication or computation noise. Boosting classifiers (e.g., AdaBoost) make a final decision via a weighted vote from the outputs of many base classifiers (weak classifiers). Suppose that the base cl…
This paper proposes a cooperative mechanism for mitigating the performance degradation due to non-independent-and-identically-distributed (non-IID) data in collaborative machine learning (ML), namely federated learning (FL), which trains an ML model using the rich data and computational resources of mobile clients with…
In the past years, Deep convolution neural network has achieved great success in many artificial intelligence applications. However, its enormous model size and massive computation cost have become the main obstacle for deployment of such powerful algorithm in the low power and resource-limited mobile systems. As the c…
New features from early battery cycles predict lifetime with high accuracy.
New algorithm improves multitask learning across diverse agents.
Despite its simplicity, the naive Bayes classifier has surprised machine learning researchers by exhibiting good performance on a variety of learning problems. Encouraged by these results, researchers have looked to overcome naive Bayes primary weakness - attribute independence - and improve the performance of the algo…
Measures DNA quality degradation effects.
Modeling coating degradation with fewer data points.
A remarkable characteristic of overparameterized deep neural networks (DNNs) is that their accuracy does not degrade when the network's width is increased. Recent evidence suggests that developing compressible representations is key for adjusting the complexity of large networks to the learning task at hand. However, t…
Improves decentralized learning by teleporting active nodes for better convergence.
Residual Networks with convolutional layers are widely used in the field of machine learning. Since they effectively extract features from input data by stacking multiple layers, they can achieve high accuracy in many applications. However, the stacking of many layers raises their computation costs. To address this pro…
The performance of automatic speech recognition systems(ASR) degrades in the presence of noisy speech. This paper demonstrates that using electroencephalography (EEG) can help automatic speech recognition systems overcome performance loss in the presence of noise. The paper also shows that distillation training of auto…
Paper uses deep learning to model systems with degrading behavior.
Study shows accuracy of neural networks depends more on error location than percentage of error.
Deep neural networks (DNNs) have achieved significant success in a variety of real world applications, i.e., image classification. However, tons of parameters in the networks restrict the efficiency of neural networks due to the large model size and the intensive computation. To address this issue, various approximatio…
MGD improves ML training efficiency and accuracy.
TSSM splits neural networks for parallel training with minimal accuracy loss.
BNCR-GAN improves GANs to generate clean images from degraded inputs.
Ensemble pruning, selecting a subset of individual learners from an original ensemble, alleviates the deficiencies of ensemble learning on the cost of time and space. Accuracy and diversity serve as two crucial factors while they usually conflict with each other. To balance both of them, we formalize the ensemble pruni…
DOPPLER optimizes DP training with low-pass filtering, improving model accuracy.
Deep learning improves Hurst parameter estimation for fractional processes.
We present a theoretical analysis of Maximum a Posteriori (MAP) sequence estimation for binary symmetric hidden Markov processes. We reduce the MAP estimation to the energy minimization of an appropriately defined Ising spin model, and focus on the performance of MAP as characterized by its accuracy and the number of s…
New framework predicts time series with missing values without imputation.