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.
The paper addresses selection bias in conformal prediction for focal units.
Regularizing for or against class selectivity in DNNs improves test accuracy.
Lower class selectivity makes networks more robust to natural perturbations but more vulnerable to adversarial attacks.
This paper tackles federated learning for automatic latent variable selection in multi-output Gaussian processes.
Despite their ability to memorize large datasets, deep neural networks often achieve good generalization performance. However, the differences between the learned solutions of networks which generalize and those which do not remain unclear. Additionally, the tuning properties of single directions (defined as the activa…
The study designs a green investment fund and a hedging strategy for insurance policies linked to it.
Improves TTS accuracy by correcting context-dependent units.
A method to detect spillover effects and select valid donors for synthetic control models.
METASET selects diverse unit cells for efficient data-driven metamaterial design.
Activation functions influence behavior and performance of DNNs. Nonlinear activation functions, like Rectified Linear Units (ReLU), Exponential Linear Units (ELU) and Scaled Exponential Linear Units (SELU), outperform the linear counterparts. However, selecting an appropriate activation function is a challenging probl…
Optimizes experimental design using synthetic controls for better outcomes.
The condition number predicts efficient information encoding in neural units, aiding model fine-tuning.
Conformal Alignment ensures trustworthy outputs from foundation models.
Study tail risk in high-frequency finance using -regularized regression.
Automates feature selection and weighting in molecular systems.
In a seminal paper Abadie, Diamond, and Hainmueller [2010] (ADH), see also Abadie and Gardeazabal [2003], Abadie et al. [2014], develop the synthetic control procedure for estimating the effect of a treatment, in the presence of a single treated unit and a number of control units, with pre-treatment outcomes observed f…
Recurrent Neural Network (RNN) has been successfully applied in many sequence learning problems. Such as handwriting recognition, image description, natural language processing and video motion analysis. After years of development, researchers have improved the internal structure of the RNN and introduced many variants…
Deep Neural Networks are highly over-parameterized and the size of the neural networks can be reduced significantly after training without any decrease in performance. One can clearly see this phenomenon in a wide range of architectures trained for various problems. Weight/channel pruning, distillation, quantization, m…
The problem of attributing a deep network's prediction to its \emph{input/base} features is well-studied. We introduce the notion of \emph{conductance} to extend the notion of attribution to the understanding the importance of \emph{hidden} units. Informally, the conductance of a hidden unit of a deep network is the \e…
New deep learning model robust to adversarial attacks using stochastic LWTA units.
Optimizes kernel discrepancies by selecting subsets efficiently.
Although deep convolutional networks have achieved improved performance in many natural language tasks, they have been treated as black boxes because they are difficult to interpret. Especially, little is known about how they represent language in their intermediate layers. In an attempt to understand the representatio…
Study uses exchangeable GPs for staggered-adoption policy evaluation in panel data.
Dropout has proven to be an effective technique for regularization and preventing the co-adaptation of neurons in deep neural networks (DNN). It randomly drops units with a probability during the training stage of DNN. Dropout also provides a way of approximately combining exponentially many different neural networ…
Neural Network is a powerful Machine Learning tool that shows outstanding performance in Computer Vision, Natural Language Processing, and Artificial Intelligence. In particular, recently proposed ResNet architecture and its modifications produce state-of-the-art results in image classification problems. ResNet and mos…
Synthetic control method improves policy evaluation in high-dimensional settings.
Significant differences in the evolution of firm size distribution for various industries in the United States have been revealed and documented. For theoretical considerations, this finding puts major constraints on the modelling of firm growth. For practical purposes, the observed differences create a solid basis for…
Adaptive Prespecification improves precision in randomized trials.
This work extends neural networks to automatically select features by stochastically penalizing feature involvement.
The study extracts market direction from transaction data.
Neural networks are easier to optimise when they have many more weights than are required for modelling the mapping from inputs to outputs. This suggests a two-stage learning procedure that first learns a large net and then prunes away connections or hidden units. But standard training does not necessarily encourage ne…
The impact of the maximally possible batch size (for the better runtime) on performance of graphic processing units (GPU) and tensor processing units (TPU) during training and inference phases is investigated. The numerous runs of the selected deep neural network (DNN) were performed on the standard MNIST and Fashion-M…
We derive a selection of energy estimates for a generalisation of a critical equation on the unit disc in introduced by Rivière. Applications include sharp regularity results and compactness theorems which generalise a large amount of previous geometric PDE theory, including some of the theory of harmoni…
Class selectivity affects robustness to corruptions but not to adversarial attacks.
Paper proposes a sparse synthetic control method to select important predictors.
In this paper, we introduce an alternative approach, namely GEN (Genetic Evolution Network) Model, to the deep learning models. Instead of building one single deep model, GEN adopts a genetic-evolutionary learning strategy to build a group of unit models generations by generations. Significantly different from the well…
A method of simultaneously optimizing both the structure of neural networks and the connection weights in a single training loop can reduce the enormous computational cost of neural architecture search. We focus on the probabilistic model-based dynamic neural network structure optimization that considers the probabilit…
Deep neural networks (DNNs) are powerful machine learning models and have succeeded in various artificial intelligence tasks. Although various architectures and modules for the DNNs have been proposed, selecting and designing the appropriate network structure for a target problem is a challenging task. In this paper, w…
Proposes PEMI for online selective conformal prediction with asymmetric rules.
Network anomaly detection is still a vibrant research area. As the fast growth of network bandwidth and the tremendous traffic on the network, there arises an extremely challengeable question: How to efficiently and accurately detect the anomaly on multiple traffic? In multi-task learning, the traffic consisting of flo…
A recent literature in econometrics models unobserved cross-sectional heterogeneity in panel data by assigning each cross-sectional unit a one-dimensional, discrete latent type. Such models have been shown to allow estimation and inference by regression clustering methods. This paper is motivated by the finding that th…
Partial soft-matching distance improves neural representation comparison by allowing some neurons to remain unmatched.
CFR-Pro enhances treatment effect estimation by incorporating local proximity.
Study finds long memory in some emerging Asian stocks but not in developed markets.
A method selects candidates based on predictions with statistical control.
CAP algorithm controls FCR in online selective prediction.
ClusterSC improves synthetic control by selecting relevant donor groups.
A new algorithm efficiently selects features for functional data classification.