Research
On-device research index

arXiv research

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.

168,932 papers · 148 categories

Trend · papers per month

3.3%6.6%10.0%13.3% · Jun 202019922001200920172026
48 results for Bayesian Dark Knowledge

Bayesian Dark Knowledge fails to perform well with high posterior uncertainty.

problem Performance degradation of Bayesian Dark Knowledge with high posterior uncertainty.
method Compresses posterior predictive distribution into a single network, using a student network matching the teacher ensemble architecture.
result Using a matching student network architecture does not guarantee acceptable performance with high posterior uncertainty.

New method uses neural networks to infer dark matter subhalo abundance from stellar streams.

problem Constrain warm dark matter mass using stellar streams.
method Amortized Approximate Likelihood Ratios (AALR) for likelihood-free Bayesian inference.
result Demonstrates effectiveness of new method for estimating dark matter subhalo abundance.

Interpreting black box classifiers, such as deep networks, allows an analyst to validate a classifier before it is deployed in a high-stakes setting. A natural idea is to visualize the deep network's representations, so as to "see what the network sees". In this paper, we demonstrate that standard dimension reduction m…

2018-03-11abs ↗pdf ↗

Dark Experience improves continual learning with a simple, strong baseline.

problem General Continual Learning in scenarios where tasks are not sequential and offline training is not possible.
method Mixing rehearsal with knowledge distillation and regularization.
result Dark Experience outperforms consolidated approaches and leverages limited resources.

Probabilistic programming allows specification of probabilistic models in a declarative manner. Recently, several new software systems and languages for probabilistic programming have been developed on the basis of newly developed and improved methods for approximate inference in probabilistic models. In this contribut…

2013-06-02abs ↗pdf ↗

Paper assesses adversarial robustness of MCMC and BDK methods for deep Bayesian networks.

problem Assessing adversarial robustness of deep neural networks under MCMC and BDK approximations.
method Characterizes robustness of MCMC and BDK methods to FGSM and PGD attacks.
result Full MCMC-based inference shows excellent robustness, outperforming standard point estimation.

This paper distills Bayesian posterior expectations for deep neural networks.

problem Improving deep neural network performance and uncertainty quantification.
method Develops a framework for distilling expectations from Bayesian posterior distributions using Monte Carlo samples.
result The framework successfully distills posterior predictive distribution and expected entropy.

We accelerate Bayesian inference for neutrino physics experiments by 100-60x.

problem Complex posterior geometries in multi-dimensional parameter spaces.
method GPU acceleration, automatic differentiation, neural-network-guided reparameterization.
result Significant performance improvements in Bayesian inference for direct detection experiments.

We consider the problem of Bayesian parameter estimation for deep neural networks, which is important in problem settings where we may have little data, and/ or where we need accurate posterior predictive densities, e.g., for applications involving bandits or active learning. One simple approach to this is to use onlin…

2015-06-14abs ↗pdf ↗

Physics-informed neural networks improve baryonic predictions from dark matter simulations.

problem Recreating hydrodynamic simulations from dark matter requires expensive and time-consuming computations.
method Combining neural network architectures with physical constraints and using Kullback-Leibler divergence for prediction comparison.
result Improved accuracy of baryonic predictions based on dark matter halo properties, successful recovery of the metallicity relation, and preserved scatter.

This paper investigates the impact of dark pools on price discovery (the efficiency of prices on stock exchanges to aggregate information). Assets are traded in either an exchange or a dark pool, with the dark pool offering better prices but lower execution rates. Informed traders receive noisy and heterogeneous signal…

2016-12-27abs ↗pdf ↗

We explore a model of dark matter called wave dark matter (also known as scalar field dark matter and boson stars) which has recently been motivated by a new geometric perspective by Bray. Wave dark matter describes dark matter as a scalar field which satisfies the Einstein-Klein-Gordon equations. These equations rely …

2013-11-24abs ↗pdf ↗

This study identifies RwD crash patterns on rural two-lane highways under different lighting conditions.

problem Insufficient investigation of RwD crashes under varying lighting conditions.
method Data mining using association rules mining (ARM) on crash database.
result Interesting crash patterns and risk factors identified under different lighting conditions.

Machine learning helps infer dark matter substructure from strong lensing images.

problem Extracting information about dark matter substructure from strong lensing images is challenging.
method Simulation-based inference techniques and neural networks trained on simulator data.
result Efficiently trained neural networks can estimate likelihood ratios for substructure parameters.

Paper explains how early stopping helps distillation in overparameterized neural networks.

problem Understanding how overparameterized neural networks can improve with early stopping.
method Introducing Anisotropic Information Retrieval (AIR) to justify early stopping in distillation.
result Self-distillation algorithm improves over just early stopping, leading to better generalization.

Study optimal liquidation strategies in lit and dark pools with and without regulation.

problem Optimal liquidation strategies in dark and lit pools with execution uncertainty.
method Design optimal make-take fee policies, solve HJB-Fokker-Planck systems, use BSDEs.
result Explicit solutions for optimal strategies in both competitive and regulated markets.

New method extracts cosmological information from dark matter halo catalogues using graph neural networks.

problem Quantifying cosmological information from large-scale structure data.
method Implicit likelihood approach with Information Maximising Neural Networks (IMNNs) on graph representations of dark matter halo catalogues.
result Graph neural network summaries can extract information from noisy catalogues and improve parameter constraints.

For a market impact model, price manipulation and related notions play a role that is similar to the role of arbitrage in a derivatives pricing model. Here, we give a systematic investigation into such regularity issues when orders can be executed both at a traditional exchange and in a dark pool. To this end, we focus…

2012-05-17abs ↗pdf ↗

In order to reduce signalling, traders may resort to limiting access to dark venues and imposing limits on minimum fill sizes they are willing to trade. However, doing this also restricts the liquidity available to the trader since an ever increasing quantity of orders are traded by algos in clips. An alternative is to…

2017-10-17abs ↗pdf ↗

Characterizing statistical properties of solutions of inverse problems is essential for decision making. Bayesian inversion offers a tractable framework for this purpose, but current approaches are computationally unfeasible for most realistic imaging applications in the clinic. We introduce two novel deep learning bas…

2018-11-14abs ↗pdf ↗

We consider a finite-horizon market-making problem faced by a dark pool that executes incoming buy and sell orders. The arrival flow of such orders is assumed to be random and, for each transaction, the dark pool earns a per-share commission no greater than the half bid-ask spread. Throughout the entire period, the mai…

2015-02-10abs ↗pdf ↗

Hybrid model speeds up galaxy simulations by incorporating baryonic properties.

problem Inaccurate baryonic properties in dark matter-only simulations.
method Combining analytic models and machine learning for faster, more accurate simulations.
result Hybrid model outperforms machine learning alone for some baryonic properties.

Knowledge Distillation (KD) consists of transferring “knowledge” from one machine learning model (the teacher) to another (the student). Commonly, the teacher is a high-capacity model with formidable performance, while the student is more compact. By transferring knowledge, one hopes to benefit from the student’s…

2018-05-12abs ↗pdf ↗

Recurrent neural networks (RNNs), particularly long short-term memory (LSTM), have gained much attention in automatic speech recognition (ASR). Although some successful stories have been reported, training RNNs remains highly challenging, especially with limited training data. Recent research found that a well-trained …

2015-05-18abs ↗pdf ↗

We consider an optimal trading problem over a finite period of time during which an investor has access to both a standard exchange and a dark pool. We take the exchange to be an order-driven market and propose a continuous-time setup for the best bid price and the market spread, both modelled by Lévy processes. Effect…

2014-05-08abs ↗pdf ↗

The paper examines how macroeconomic control tools lost effectiveness, leading to a 'dark ages' period.

problem Loss of effectiveness of control tools in macroeconomic stabilization policy.
method Historical analysis of macroeconomic stabilization policy from 1948 to 1993.
result The overstatement of the Lucas critique and Kydland and Prescott's time-inconsistency led to a period of ineffective stabilization policy.

We consider an illiquid financial market where a risk averse investor has to liquidate a portfolio within a finite time horizon [0,T] and can trade continuously at a traditional exchange (the "primary venue") and in a dark pool. At the primary venue, trading yields a linear price impact. In the dark pool, no price impa…

2012-01-30abs ↗pdf ↗

Paper tackles hypothesis transfer learning for black-box models.

problem Difficult to build universal machine learning models across different institutions.
method Dynamic Knowledge Distillation (dkdHTL) with instance-wise weighting.
result Empirical results show the effectiveness of dkdHTL.

Deep learning and genetic algorithms speed up cosmological Bayesian inference.

problem Substantial computational demands in Bayesian inference for cosmological parameter estimation.
method Deep learning using feedforward neural networks to approximate likelihood functions dynamically, optimized with genetic algorithms.
result Significant speed-up in Bayesian inference process for cosmological models and datasets.

We study the problem of allocating stocks to dark pools. We propose and analyze an optimal approach for allocations, if continuous-valued allocations are allowed. We also propose a modification for the case when only integer-valued allocations are possible. We extend the previous work on this problem to adversarial sce…

2010-03-11abs ↗pdf ↗

This study uses ARM to analyze pedestrian crashes under different lighting conditions.

problem Identifying crash risk factors under varying lighting conditions.
method Applied Association Rules Mining to Louisiana pedestrian crash data.
result Daylight crashes are associated with children, seniors, and older drivers.

Rectified decision trees improve machine learning interpretability and effectiveness.

problem Combining interpretability and effectiveness in machine learning models.
method Knowledge distillation and modified decision tree splitting criteria.
result Soft labels improve model performance and reduce model size.

Study on ensemble, distillation, and self-distillation in deep learning models.

problem Improving test accuracy in deep learning models using ensemble and distillation methods.
method Formal study of ensemble and distillation, considering multi-view data structure.
result Proven that ensemble and distillation can improve test accuracy in deep learning models, and the superior performance can be distilled into a single model.

Bayesian neural networks incorporate domain knowledge through variational inference.

problem Specifying priors for Bayesian neural networks that capture domain knowledge is challenging.
method Proposes a framework for integrating domain knowledge into BNN priors through variational inference.
result BNNs with proposed domain knowledge priors outperform those with standard priors, achieving better predictive performance.