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.
A new screening rule improves lasso solving speed.
The paper tackles financial market dynamics with new tech-driven data.
It has been shown that instead of learning actual object features, deep networks tend to exploit non-robust (spurious) discriminative features that are shared between training and test sets. Therefore, while they achieve state of the art performance on such test sets, they achieve poor generalization on out of distribu…
In this paper we use wavelet concepts to show that correlation coefficient between two financial data's is not constant but varies with scale from high correlation value to strongly anti-correlation value This studies is important because correlation coefficient is used to quantify degree of independence between two va…
Obesity is an important concern in public health, and Body Mass Index is one of the useful (and proliferant) measures. We use Convolutional Neural Networks to determine Body Mass Index from photographs in a study with 161 participants. Low data, a common problem in medicine, is addressed by reducing the information in …
We introduce a Bayesian framework for inference with a supervised version of the Gaussian process latent variable model. The framework overcomes the high correlations between latent variables and hyperparameters by using an unbiased pseudo estimate for the marginal likelihood that approximately integrates over the late…
We propose improved methods to identify stock groups using the correlation matrix of stock price changes. By filtering out the marketwide effect and the random noise, we construct the correlation matrix of stock groups in which nontrivial high correlations between stocks are found. Using the filtered correlation matrix…
Improved clustering of extra-financial data using NMF with data separation.
Financial asset markets are sociotechnical systems whose constituent agents are subject to evolutionary pressure as unprofitable agents exit the marketplace and more profitable agents continue to trade assets. Using a population of evolving zero-intelligence agents and a frequent batch auction price-discovery mechanism…
Recently, there has been interest in multiplicative recurrent neural networks for language modeling. Indeed, simple Recurrent Neural Networks (RNNs) encounter difficulties recovering from past mistakes when generating sequences due to high correlation between hidden states. These challenges can be mitigated by integrat…
The downside risk of a portfolio of (equity)assets is generally substantially higher than the downside risk of its components. In particular in times of crises when assets tend to have high correlation, the understanding of this difference can be crucial in managing systemic risk of a portfolio. In this paper we genera…
Simple model finds high correlation in retail crypto returns.
Optimization with noisy gradients has become ubiquitous in statistics and machine learning. Reparameterization gradients, or gradient estimates computed via the "reparameterization trick," represent a class of noisy gradients often used in Monte Carlo variational inference (MCVI). However, when these gradient estimator…
We study utility indifference prices and optimal purchasing quantities for a contingent claim, in an incomplete semi-martingale market, in the presence of vanishing hedging errors and/or risk aversion. Assuming that the average indifference price converges to a well defined limit, we prove that optimally taken position…
We investigate the properties of correlation based networks originating from economic complex systems, such as the network of stocks traded at the New York Stock Exchange (NYSE). The weaker links (low correlation) of the system are found to contribute to the overall connectivity of the network significantly more than t…
We consider the high-dimensional sparse linear regression problem of accurately estimating a sparse vector using a small number of linear measurements that are contaminated by noise. It is well known that the standard cadre of computationally tractable sparse regression algorithms---such as the Lasso, Orthogonal Matchi…
Paper uses LSTM to predict inflation, finds it performs well over long periods.
Standard gradient descent methods are susceptible to a range of issues that can impede training, such as high correlations and different scaling in parameter space.These difficulties can be addressed by second-order approaches that apply a pre-conditioning matrix to the gradient to improve convergence. Unfortunately, s…
Paper proposes Coalitional BAE to improve explainability of unsupervised deep learning models.
The Soil Moisture Active Passive (SMAP) mission has delivered valuable sensing of surface soil moisture since 2015. However, it has a short time span and irregular revisit schedule. Utilizing a state-of-the-art time-series deep learning neural network, Long Short-Term Memory (LSTM), we created a system that predicts SM…
An automated metric to evaluate dialogue quality is vital for optimizing data driven dialogue management. The common approach of relying on explicit user feedback during a conversation is intrusive and sparse. Current models to estimate user satisfaction use limited feature sets and employ annotation schemes with limit…
We revisit the trading invariance hypothesis recently proposed by Kyle and Obizhaeva by empirically investigating a large dataset of bets, or metaorders, provided by ANcerno. The hypothesis predicts that the quantity $I:=\ri/N^{3/2}$, where $\ri$ is the exchanged risk (volatility volume price) and …
Paper introduces new importance metrics for machine learning models, linking them to CATE.
Novel method decorrelates neurons for better deep learning model generalization.
We study historical correlations and lead-lag relationships between individual stock risk (volatility of daily stock returns) and market risk (volatility of daily returns of a market-representative portfolio) in the US stock market. We consider the cross-correlation functions averaged over all stocks, using 71 stock pr…
Pipeline learns topological features for protein stability prediction.
With the recent rise of Machine Learning as a candidate to partially replace classic Financial Mathematics methodologies, we investigate the performances of both in solving the problem of dynamic portfolio optimization in continuous-time, finite-horizon setting for a portfolio of two assets that are intertwined. In Fin…
Paper reduces movement primitive dimensionality in parameter space.
Proposes a method to select features for deep learning in noisy, high-dimensional data.
Matrices satisfying the Restricted Isometry Property (RIP) play an important role in the areas of compressed sensing and statistical learning. RIP matrices with optimal parameters are mainly obtained via probabilistic arguments, as explicit constructions seem hard. It is therefore interesting to ask whether a fixed mat…
New method selects features for big data efficiently.
Study of the forecasting models using large scale microblog discussions and the search behavior data can provide a good insight for better understanding the market movements. In this work we collected a dataset of 2 million tweets and search volume index (SVI from Google) for a period of June 2010 to September 2011. We…
New measure predicts deep neural network generalization better than existing ones.
The progress of deep convolutional neural networks has been successfully exploited in various real-time computer vision tasks such as image classification and segmentation. Owing to the development of computational units, availability of digital datasets, and improved performance of deep learning models, fully automati…
Hierarchical-CPI improves variable importance measurement for medical data.
GRIP2 improves deep learning feature selection robustness in correlated and noisy data.
New method recovers latent confounders from high-dimensional proxy variables.
Fitting statistical models is computationally challenging when the sample size or the dimension of the dataset is huge. An attractive approach for down-scaling the problem size is to first partition the dataset into subsets and then fit using distributed algorithms. The dataset can be partitioned either horizontally (i…
New mechanism discovered for feature learning in CNNs.
PNNs model aleatoric uncertainty in scientific machine learning with high accuracy.
Preformer improves Transformer for long-term time series forecasting.
Rank-based Bayesian Optimization improves molecule selection in chemical systems.
Proposes using mode connectivity to improve adversarial robustness of neural networks.
We study directed, weighted graphs and consider the (not necessarily symmetric) averaging operator where are normalized edge weights. Given a vertex , we define the diffusion distance to a set as the smallest n…
Spatially relaxed inference tackles high-dimensional linear models with correlated covariates.
Paper proposes learning causal graphs with only relevant variables.
Mean representations of VAEs are correlated but still useful for tasks.
Source imaging based on magnetoencephalography (MEG) and electroencephalography (EEG) allows for the non-invasive analysis of brain activity with high temporal and good spatial resolution. As the bioelectromagnetic inverse problem is ill-posed, constraints are required. For the analysis of evoked brain activity, spatia…