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.
Designs a neural network to reduce training cost by mapping to higher dimensions.
Improves generative models for cost-sensitive decisions.
State-of-the-art convolutional neural networks (CNNs) used in vision applications have large models with numerous weights. Training these models is very compute- and memory-resource intensive. Much research has been done on pruning or compressing these models to reduce the cost of inference, but little work has address…
This work reduces computation cost for on-device CNN training.
Ensembles of deep neural networks significantly improve generalization accuracy. However, training neural network ensembles requires a large amount of computational resources and time. State-of-the-art approaches either train all networks from scratch leading to prohibitive training cost that allows only very small ens…
This paper proposes CSADA to make DNNs cost-sensitive.
Two preprocessing techniques reduce neural network training cost.
New algorithm reduces online hyperparameter optimization costs.
Budgeted deferral framework reduces expert query costs in machine learning.
New algorithm reduces misclassification costs in neural networks.
A new cost-frugal HPO method controls training cost during optimization.
A new method for decision-focused learning reduces computational cost.
MCAL reduces labeling costs by 6x for auto-labeling data sets.
Adversarial training, in which a network is trained on adversarial examples, is one of the few defenses against adversarial attacks that withstands strong attacks. Unfortunately, the high cost of generating strong adversarial examples makes standard adversarial training impractical on large-scale problems like ImageNet…
Several recent works have developed methods for training classifiers that are certifiably robust against norm-bounded adversarial perturbations. These methods assume that all the adversarial transformations are equally important, which is seldom the case in real-world applications. We advocate for cost-sensitive robust…
The paper constructs upper bounds for cost minimization in shallow neural networks.
PaGoDA reduces diffusion model training costs by 64x.
Pruning filters in neural networks improves performance and reduces costs.
Cost-effective strategies for training machine learning models on volatile cloud instances.
Learning a policy using only observational data is challenging because the distribution of states it induces at execution time may differ from the distribution observed during training. We propose to train a policy by unrolling a learned model of the environment dynamics over multiple time steps while explicitly penali…
Asynchronous algorithms reduce privacy costs in distributed machine learning.
The paper discusses the limitations of efficiency metrics in machine learning models.
Frequently, acquiring training data has an associated cost. We consider the situation where the learner may purchase data during training, subject TO a budget. IN particular, we examine the CASE WHERE each feature label has an associated cost, AND the total cost OF ALL feature labels acquired during training must NOT e…
We propose a novel adaptive approximation approach for test-time resource-constrained prediction. Given an input instance at test-time, a gating function identifies a prediction model for the input among a collection of models. Our objective is to minimize overall average cost without sacrificing accuracy. We learn gat…
LMM predicts healthcare costs and risks with improved accuracy.
We present a dynamic model selection approach for resource-constrained prediction. Given an input instance at test-time, a gating function identifies a prediction model for the input among a collection of models. Our objective is to minimize overall average cost without sacrificing accuracy. We learn gating and predict…
This study optimizes DRL for American option hedging with new training methods.
Deep convolutional neural networks have achieved great success in various applications. However, training an effective DNN model for a specific task is rather challenging because it requires a prior knowledge or experience to design the network architecture, repeated trial-and-error process to tune the parameters, and …
Proposes a method to train neural networks that solve differential equations faster.
Machine learning has automated much of financial fraud detection, notifying firms of, or even blocking, questionable transactions instantly. However, data imbalance starves traditionally trained models of the content necessary to detect fraud. This study examines three separate factors of credit card fraud detection vi…
New method reduces deep learning training costs by approximating vector-jacobian products.
Combines cost-sensitive and Neyman-Pearson paradigms for better binary classification.
Efficiently identifies promising hyperparameters for online learning models.
We propose an algorithm for exploring the entire regularization path of asymmetric-cost linear support vector machines. Empirical evidence suggests the predictive power of support vector machines depends on the regularization parameters of the training algorithms. The algorithms exploring the entire regularization path…
We seek decision rules for prediction-time cost reduction, where complete data is available for training, but during prediction-time, each feature can only be acquired for an additional cost. We propose a novel random forest algorithm to minimize prediction error for a user-specified {\it average} feature acquisition b…
Method curates cost-effective, high-quality datasets using AI models.
Study assesses CNN model robustness to noise in low-cost CT scans.
Graph Neural Networks (GNN) are a promising technique for bridging differential programming and combinatorial domains. GNNs employ trainable modules which can be assembled in different configurations that reflect the relational structure of each problem instance. In this paper, we show that GNNs can learn to solve, wit…
Label tree-based algorithms are widely used to tackle multi-class and multi-label problems with a large number of labels. We focus on a particular subclass of these algorithms that use probabilistic classifiers in the tree nodes. Examples of such algorithms are hierarchical softmax (HSM), designed for multi-class class…
FedLion improves Federated Learning by speeding up convergence and reducing communication costs.
Cost-aware BO minimizes function evaluations with varying costs.
The usability and practicality of any machine learning (ML) applications are largely influenced by two critical but hard-to-attain factors: low latency and low cost. Unfortunately, achieving low latency and low cost is very challenging when ML depends on real-world data that are highly distributed and rapidly growing (…
Paper proposes a cost-sensitive conformal training method with provably controllable learning bounds.
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…
Paper presents a new training method for overparametrized neural networks that reduces time per iteration.
The neural network (NN)-based direct uncertainty quantification (UQ) methods have achieved the state of the art performance since the first inauguration, known as the lower-upper-bound estimation (LUBE) method. However, currently-available cost functions for uncertainty guided NN training are not always converging and …
DRSSS method reduces model training costs by eliminating unsafe samples.
Label space expansion for multi-label classification (MLC) is a methodology that encodes the original label vectors to higher dimensional codes before training and decodes the predicted codes back to the label vectors during testing. The methodology has been demonstrated to improve the performance of MLC algorithms whe…