This paper investigates the optimal choices of financial derivatives to complete a financial market in the framework of stochastic volatility (SV) models.
This paper challenges the use of stocks in portfolio construction, instead we demonstrate that Asian derivatives, straddles, or baskets could be more convenient substitutes.
The TLA enables the ReViT to process the image with the minimum sufficient number of tokens during inference.
Critically, there is no effort to understand 1) why training BatchNorm only can find the perform-well architectures with the reduced supernet-training time, and 2) what is the difference between the train-BN-only supernet and the standard-train supernet.
We propose NETS-ImpGAN, a novel deep learning framework that can be trained on incomplete data with missing values in both history and future.
We formulate the knowledge distillation as a multi-task learning problem so that the teacher transfers knowledge to the student only if the student can benefit from learning such knowledge.
When data are limited in one or more of the classes, the estimated decision boundaries are often irregularly shaped due to the limited sample size, leading to poor generalization error.
In this paper, we propose a learnable sampling module based on variational auto-encoder (VAE) for neural architecture search (NAS), named as VAENAS, which can be easily embedded into existing weight sharing NAS framework, e. g., one-shot approach and gradient-based approach, and significantly improve the performance of searching results.
We introduce the adaptive resizable networks as dynamic networks, which further improve the performance with less computational cost via data-dependent inference.
The most commonly used open-source traffic simulator SUMO is, however, not scalable to large road network and large traffic flow, which hinders the study of reinforcement learning on traffic scenarios.
Variable selection is a classic problem in machine learning (ML), widely used to find important explanatory factors, and improve generalization performance and interpretability of ML models.
In this paper, we address these three issues by (1) seeking convex relaxations of the original nonconvex problems so that the global optimal is guaranteed to be achievable; (2) providing a formal analysis on OPR's capability of promoting balancedness; (3) providing a theoretical analysis that directly reveals the relationship between OPR and generalization performance.