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.
Paper explores fast adversarial training to improve robustness with less computation.
Gradient-based meta-learning has proven to be highly effective at learning model initializations, representations, and update rules that allow fast adaptation from a few samples. The core idea behind these approaches is to use fast adaptation and generalization -- two second-order metrics -- as training signals on a me…
New method speeds up training of deep networks robust to adversarial attacks.
DIP-FAT improves adversarial training by diversifying perturbations.
A fast method for LOOCV in k-NN regression reduces computation time.
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…
The standard state-of-the-art backend for text-independent speaker recognizers that use i-vectors or x-vectors, is Gaussian PLDA (G-PLDA), assisted by a Gaussianization step involving length normalization. G-PLDA can be trained with both generative or discriminative methods. It has long been known that heavy-tailed PLD…
In this paper we propose a new method to assist in labeling data arriving from fast running processes using anomaly detection. A result is the possibility to manually classify data arriving at a high rates to train machine learning models. To circumvent the problem of not having a real ground truth we propose specific …
In this paper we propose a fast online Kernel SVM algorithm under tight budget constraints. We propose to split the input space using LVQ and train a Kernel SVM in each cluster. To allow for online training, we propose to limit the size of the support vector set of each cluster using different strategies. We show in th…
FROCC uses random projections for fast one-class classification.
This paper speeds up OCSSVM training using SMO.
Efficient algorithm finds fast Transformer models.
Adversarial training, a method for learning robust deep networks, is typically assumed to be more expensive than traditional training due to the necessity of constructing adversarial examples via a first-order method like projected gradient decent (PGD). In this paper, we make the surprising discovery that it is possib…
The loss functions of deep neural networks are complex and their geometric properties are not well understood. We show that the optima of these complex loss functions are in fact connected by simple curves over which training and test accuracy are nearly constant. We introduce a training procedure to discover these hig…
Regression is an important task in machine learning and data mining. It has several applications in various domains, including finance, biomedical, and computer vision. Recently, network Lasso, which estimates local models by making clusters using the network information, was proposed and its superior performance was d…
Investigates fast prediction rates with limited expert advice.
We present an efficient algorithm for simultaneously training sparse generalized linear models across many related problems, which may arise from bootstrapping, cross-validation and nonparametric permutation testing. Our approach leverages the redundancies across problems to obtain significant computational improvement…
Novel deep learning approach for fast, differentiable fluid simulations.
New method prevents adversarial training failure in deep networks.
Paper discovers simplicial complexes connecting trained models for improved ensembling.
FAST improves fast and stable task adaptation in DNNs.
How to train a machine learning model while keeping the data private and secure? We present CodedPrivateML, a fast and scalable approach to this critical problem. CodedPrivateML keeps both the data and the model information-theoretically private, while allowing efficient parallelization of training across distributed w…
We develop a fast, tractable technique called Net-Trim for simplifying a trained neural network. The method is a convex post-processing module, which prunes (sparsifies) a trained network layer by layer, while preserving the internal responses. We present a comprehensive analysis of Net-Trim from both the algorithmic a…
Paper presents a fast method for estimating hidden states in Bayesian models.
New method improves adversarial training efficiency and robustness.
Hierarchical pretraining with slow-fast ODEs
EControl improves fast distributed optimization with compression and error control.
This paper proposes an incremental solution to Fast Subclass Discriminant Analysis (fastSDA). We present an exact and an approximate linear solution, along with an approximate kernelized variant. Extensive experiments on eight image datasets with different incremental batch sizes show the superiority of the proposed ap…
Big data is one of the cornerstones to enabling and training deep neural networks (DNNs). Because of the lack of expertise, to gain benefits from their data, average users have to rely on and upload their private data to big data companies they may not trust. Due to the compliance, legal, or privacy constraints, most u…
Calcium imaging permits optical measurement of neural activity. Since intracellular calcium concentration is an indirect measurement of neural activity, computational tools are necessary to infer the true underlying spiking activity from fluorescence measurements. Bayesian model inversion can be used to solve this prob…
BayesFlow trains neural networks for fast Bayesian inference.
This study explains why approximate NGD works well in wide neural networks.
Paper tackles catastrophic overfitting in single-step adversarial training.
Improved GP models for fast training and good performance.
Consistency models generate high-quality samples fast and without iterative sampling.
New method speeds up Gaussian process training and inference for large datasets.
Deep learning speeds CAT bond valuation.
Convolutional autoregressive models have recently demonstrated state-of-the-art performance on a number of generation tasks. While fast, parallel training methods have been crucial for their success, generation is typically implemented in a naïve fashion where redundant computations are unnecessarily repeated. This res…
New method speeds up image denoising models without sacrificing performance.
A new method reduces adversarial training time without overfitting.
A new algorithm speeds up neural network training with less data.
Aims to describe neural network training dynamics using two-time-scale models.
New method learns robust meta-representations for fast task adaptation.
Sparse Meta Networks adapt deep neural networks incrementally for fast learning.
We study the problem of using low computational cost to automate the choices of learners and hyperparameters for an ad-hoc training dataset and error metric, by conducting trials of different configurations on the given training data. We investigate the joint impact of multiple factors on both trial cost and model erro…
Develops deep learning for fast, accurate option pricing models.
SFPO optimizes LLM reasoning by repositioning before updating, improving stability and efficiency.
Paper introduces a new gradient statistic to improve deep learning convergence.