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.
Spiking neural networks enable efficient approximate Bayesian inference via permanent dropout.
We introduce the notion of regular finite decomposition complexity of a metric family. This generalizes Gromov's finite asymptotic dimension and is motivated by the concept of finite decomposition complexity (FDC) due to Guentner, Tessera and Yu. Regular finite decomposition complexity implies FDC and has all the perma…
There are two schools of thought regarding market impact modeling. On the one hand, seminal papers by Almgren and Chriss introduced a decomposition between a permanent market impact and a temporary (or instantaneous) market impact. This decomposition is used by most practitioners in execution models. On the other hand,…
AdaPart efficiently samples permanent distributions, improving tracking performance.
The paper analyzes optimal liquidation strategies for cryptocurrencies considering both temporary and permanent price impacts.
New network learns non-parametric invariances from data.
Stochastic discount factor (SDF) processes in dynamic economies admit a permanent-transitory decomposition in which the permanent component characterizes pricing over long investment horizons. This paper introduces an empirical framework to analyze the permanent-transitory decomposition of SDF processes. Specifically, …
We study the relaxation dynamics of the bid-ask spread and of the midprice after a sudden, large variation of the spread, corresponding to a temporary crisis of liquidity in a double auction financial market. We find that the spread decays very slowly to its normal value as a consequence of the strategic limit order pl…
Paper improves likelihood estimation for discrete distributions.
Advanced Dropout improves DNN performance without requiring model-specific dropout techniques.
Enhanced dropout technique improves training speed and generalization.
Dropout is often used in deep neural networks to prevent over-fitting. Conventionally, dropout training invokes \textit{random drop} of nodes from the hidden layers of a Neural Network. It is our hypothesis that a guided selection of nodes for intelligent dropout can lead to better generalization as compared to the tra…
Continuous dropout mimics brain neuron firing rates to prevent feature detector co-adaptation.
Dropout regularizes against high-order interactions by canceling interaction rates.
We consider a financial model with permanent price impact. Continuous time trading dynamics are derived as the limit of discrete rebalancing policies. We then study the problem of super-hedging a European option. Our main result is the derivation of a quasi-linear pricing equation. It holds in the sense of viscosity so…
We analyze dropout in deep networks with rectified linear units and the quadratic loss. Our results expose surprising differences between the behavior of dropout and more traditional regularizers like weight decay. For example, on some simple data sets dropout training produces negative weights even though the output i…
Dropout is one of the key techniques to prevent the learning from overfitting. It is explained that dropout works as a kind of modified L2 regularization. Here, we shed light on the dropout from Bayesian standpoint. Bayesian interpretation enables us to optimize the dropout rate, which is beneficial for learning of wei…
Adversarial dropout improves RNNs' performance on sequential data tasks.
Dropout is a simple but effective technique for learning in neural networks and other settings. A sound theoretical understanding of dropout is needed to determine when dropout should be applied and how to use it most effectively. In this paper we continue the exploration of dropout as a regularizer pioneered by Wager,…
Dropout has been witnessed with great success in training deep neural networks by independently zeroing out the outputs of neurons at random. It has also received a surge of interest for shallow learning, e.g., logistic regression. However, the independent sampling for dropout could be suboptimal for the sake of conver…
Dropout is used to avoid overfitting by randomly dropping units from the neural networks during training. Inspired by dropout, this paper presents GI-Dropout, a novel dropout method integrating with global information to improve neural networks for text classification. Unlike the traditional dropout method in which the…
Rate-In dynamically adjusts dropout rates during inference to improve uncertainty estimation in neural networks.
QSD enhances deep network performance through biologically plausible dropout.
Analyzes dropout in neural networks using differential equations.
Develops a multilevel Monte Carlo framework with dropout for efficient uncertainty quantification.
Dropout introduces both explicit and implicit regularization effects.
Structured dropout improves confidence calibration in convolutional neural networks.
Dropout technique is analyzed using information geometry.
The paper analyzes SGD with dropout regularization in linear models, proving asymptotic properties and providing inference tools.
Deep learning is the state-of-the-art in fields such as visual object recognition and speech recognition. This learning uses a large number of layers and a huge number of units and connections. Therefore, overfitting is a serious problem with it, and the dropout which is a kind of regularization tool is used. However, …
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…
Dropout training improves neural networks' performance.
The paper improves dropout's utility by reducing interactions in deep neural networks.
Study compares dropout and l2 regularization in linear models.
Qualitative analysis of MC dropout for NN model uncertainty.
Dropout is typically interpreted as bagging a large number of models sharing parameters. We show that using dropout in a network can also be interpreted as a kind of data augmentation in the input space without domain knowledge. We present an approach to projecting the dropout noise within a network back into the input…
Dropout controls model capacity in deep learning and matrix completion.
Characterizes dropout's regularizer in deep linear networks.
Continuum Dropout improves neural differential equations by preventing overfitting.
The paper improves marine buoy placement to detect ships robustly against disruptions.
Dropout and other feature noising schemes control overfitting by artificially corrupting the training data. For generalized linear models, dropout performs a form of adaptive regularization. Using this viewpoint, we show that the dropout regularizer is first-order equivalent to an L2 regularizer applied after scaling t…
Study on dropout in neural networks using percolation theory.
We explore a recently proposed Variational Dropout technique that provided an elegant Bayesian interpretation to Gaussian Dropout. We extend Variational Dropout to the case when dropout rates are unbounded, propose a way to reduce the variance of the gradient estimator and report first experimental results with individ…
Optimal strategy for liquidating portfolios under discrete time intervals.
Proposes LBD for more robust deep learning models.
Wasserstein Dropout improves uncertainty estimation in neural networks.
Dropout training, originally designed for deep neural networks, has been successful on high-dimensional single-layer natural language tasks. This paper proposes a theoretical explanation for this phenomenon: we show that, under a generative Poisson topic model with long documents, dropout training improves the exponent…
Dropout is used as a practical tool to obtain uncertainty estimates in large vision models and reinforcement learning (RL) tasks. But to obtain well-calibrated uncertainty estimates, a grid-search over the dropout probabilities is necessary - a prohibitive operation with large models, and an impossible one with RL. We …