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.

168,742 papers · 148 categories

Trend · papers per month

150300450600 · Jun 202019922001200920172026
48 results for Deep Variable-Block Chain

The paper models blockchain queues and trading dynamics, finding conditions for transaction priority and price impact.

problem Understanding and predicting price impacts in blockchain trading environments.
method Developed a probabilistic model for blockchain queues with adversarial scheduling, derived expressions for transaction priority and price impact.
result Conditions for transaction priority and statistical models for price impact in blockchain trading environments.

Develops a new framework for temporal anchoring in deep embedding spaces.

problem Temporal anchoring in deep embedding spaces, especially drift and convergence issues.
method Operator-theoretic framework with drift maps and event-indexed blocks, proving convergence theorems and equivalence theorems.
result Proves convergence theorems and equivalence theorems for the proposed framework.

Deep networks are shown to be equivalent to a new type of kernel chain.

problem Identifying an appropriate function space for deep neural networks.
method Extending Reproducing Kernel Banach Spaces (RKBS) to chain RKBS (cRKBS), which composes kernels rather than functions.
result Any deep neural network function is a neural cRKBS function, and conversely, any neural cRKBS function corresponds to a deep neural network.

Deep neural networks optimize inventory decisions in complex supply chains.

problem Optimizing inventory decisions in stochastic multi-echelon supply chains.
method Pairwise modeling and DNN agents for order-up-to levels.
result The method performs better than alternate methods in general supply chain networks.

DCDC calculates convergence rates for Markov chains using neural networks.

problem Computing precise convergence rates for Markov chains is hard.
method Developed a neural network-based algorithm (DCDC) to bound convergence rates in Wasserstein distance.
result Demonstrated effective convergence bounds for real-world Markov chains.

The paper bounds generalization errors for deep neural networks with Markov datasets.

problem Bounding generalization errors for deep learning with Markov datasets.
method Developed new symmetrization inequalities for Markov chains, using spectral gap of the infinitesimal generator.
result Derived upper bounds on generalization errors for deep neural networks with Markov datasets.

Deep unfolding accelerates MCMC-based COP solvers.

problem Optimizing combinatorial problems with MCMC and gradient descent.
method Combines MCMC and gradient descent, trains step sizes, uses variance estimation for non-differentiable MCMC.
result Significantly accelerates convergence speed for COPs.

GNNs improve supply chain analytics with real-world benchmarks.

problem Limited research on applying GNNs to supply chain management.
method Conceptual discussions, detailed formulations, examples, mathematical definitions, and task guidelines.
result GNN-based models outperform other methods by 10-40% in various supply chain tasks.

Variational inference (VI) and Markov chain Monte Carlo (MCMC) are two main approximate approaches for learning deep generative models by maximizing marginal likelihood. In this paper, we propose using annealed importance sampling for learning deep generative models. Our proposed approach bridges VI with MCMC. It gener…

2019-06-12abs ↗pdf ↗

The time to converge to the steady state of a finite Markov chain can be greatly reduced by a lifting operation, which creates a new Markov chain on an expanded state space. For a class of quadratic objectives, we show an analogous behavior where a distributed ADMM algorithm can be seen as a lifting of Gradient Descent…

2017-03-10abs ↗pdf ↗

Paper revisits Deep Variational Information Bottleneck and proposes a new optimization approach.

problem Limitations of Deep Variational Information Bottleneck in optimizing mutual information.
method Proposes a new optimization approach by circumventing the limitation of requiring both Markov chains during optimisation.
result Shows how to optimise a lower bound for mutual information, circumventing the limitation of requiring both Markov chains.

New algorithm trains deep neural networks without global optimization.

problem Training deep neural networks efficiently and without global optimization.
method Uses random complex exponential activation functions and Markov Chain Monte Carlo sampling.
result Consistently attains theoretical approximation rate for residual networks.

Deep learning model reduces food waste by stabilizing online food delivery supply chains.

problem Wastage and bullwhip effect in online food delivery services.
method Two-phase LSTM network for demand forecasting, newsvendor model for inventory management.
result Significant reduction in bullwhip effect and food waste, improved forecasting accuracy.

Survey on Evidential Deep Learning for uncertainty estimation in deep neural networks.

problem Uncertainty estimation in deep neural networks with overhead or limited diversity.
method Evidential Deep Learning, parameterizing distributions over distributions.
result Single model and forward pass uncertainty estimation with a unified notation.

Proposes a new CG interpretation of neural networks for better theoretical analysis.

problem Lack of theoretical analysis in neural networks interpretation.
method Interprets neural networks as chain graphs and feed-forward as approximate inference.
result Provides novel theoretical support and insights for various neural network techniques.

Bayesian neural networks show complex posterior distributions that HMC can capture effectively.

problem Understanding and approximating the high-dimensional, non-convex posterior of Bayesian neural networks.
method Full-batch Hamiltonian Monte Carlo (HMC) on modern architectures.
result HMC provides a robust and comparable representation of the BNN posterior, with significant performance gains over standard training and deep ensembles.

A new stopping rule based on E-values helps efficiently use sampling in Bayesian Deep Ensembles.

problem How long should sampling continue in Bayesian Deep Ensembles to yield significant improvements?
method Formulated as a sequential anytime-valid hypothesis test, using E-values to decide when to stop sampling.
result Only a fraction of the full-chain budget is often required for significant improvements.

Study forecasts supply chain disruptions in automotive industry.

problem Operational disruptions in automotive supply chain cause financial losses.
method Constructed dataset of multivariate time series, used Attention Sequence to Sequence Deep Learning architecture.
result Model achieved 0.85 precision and 0.8 recall in QA phase across five plants.

A new method uses GANs for robust optimization under uncertain data.

problem Optimizing supply chains under demand uncertainty with ambiguous distributions.
method Generative adversarial networks (GANs) for data-driven distributionally robust chance constrained programming.
result The approach effectively handles uncertain data distributions and improves supply chain optimization.

A deep Neyman-Scott process uses Poisson processes for efficient inference in complex point processes.

problem Efficient inference in complex hierarchical point processes.
method Developed an efficient posterior sampling via Markov chain Monte Carlo for likelihood-based inference.
result More hidden Poisson processes improve likelihood fitting and event prediction.

We propose a framework that directly tackles the probability distribution of the value function parameters in Deep Q Network (DQN), with powerful variational inference subroutines to approximate the posterior of the parameters. We will establish the equivalence between our proposed surrogate objective and variational i…

2017-11-30abs ↗pdf ↗

RSO uses random weight perturbations to train deep networks without gradients.

problem Training deep neural networks efficiently and without gradient information.
method RSO is a gradient-free Markov Chain Monte Carlo approach that updates weights based on mini-batch loss reduction.
result RSO achieves high accuracy (99.1% on MNIST) with significantly fewer updates than traditional methods.

VAE improves MCMC efficiency by generating diverse prior proposals.

problem Inefficient MCMC methods in Bayesian inverse problems, especially subsurface flow modeling.
method Uses Variational Autoencoder (VAE) to generate broader-spectrum prior proposals.
result VAE achieves comparable accuracy to Karhunen-Loève Expansion (KLE) and outperforms it when correlation length is unknown.

Existing Markov Chain Monte Carlo (MCMC) methods are either based on general-purpose and domain-agnostic schemes which can lead to slow convergence, or hand-crafting of problem-specific proposals by an expert. We propose A-NICE-MC, a novel method to train flexible parametric Markov chain kernels to produce samples with…

2017-06-23abs ↗pdf ↗

Study uses generative models to assess credit risk and determine loan sizes in e-commerce supply chain finance.

problem Credit risk assessment and loan size determination for small- and medium-sized sellers in e-commerce supply chain finance.
method Proposes a unified framework using Quantile-Regression-based Generative Metamodeling (QRGMM) integrated with Deep Factorization Machines (DeepFM) to capture complex covariate interactions in e-commerce sales data.
result Validates the model's efficacy for credit risk assessment and loan size determination on synthetic and real-world data.

Bounding the generalization error of learning algorithms has a long history, which yet falls short in explaining various generalization successes including those of deep learning. Two important difficulties are (i) exploiting the dependencies between the hypotheses, (ii) exploiting the dependence between the algorithm'…

2018-06-11abs ↗pdf ↗

This study compares parallel SMC and MCMC for Bayesian deep learning, showing SMC parallel is faster.

problem Efficiently performing Bayesian deep learning with parallel computing.
method Compared sequential Monte Carlo (SMC) and Markov chain Monte Carlo (MCMC) in parallel settings.
result Parallel SMC achieves similar convergence as a single SMC but with reduced communication time.

Proposes a new model for joint probability distributions in computer vision.

problem Limitation of existing models in meeting diverse downstream tasks.
method Uses parametric conditional probability distributions for each group of variables conditioned on the rest.
result Models can be used for any downstream task without task-specific design.

Langevin autoencoders improve deep latent variable models with efficient posterior sampling.

problem Efficient posterior sampling in deep latent variable models using MCMC.
method Amortized Langevin dynamics (ALD) replaces datapoint-wise sampling with encoder updates.
result ALD is valid as an MCMC algorithm with the target posterior as a stationary distribution.

This paper examines the convergence of adaptive sampling methods for Bayesian neural networks.

problem Uncertainty quantification in deep neural networks, especially for medical applications.
method Locally adaptive and scalable diffusion-based sampling methods.
result These methods can have a substantial bias in the distribution they sample, even in the limit of vanishing step sizes.

Enhances crypto-asset AMM with deep learning for better liquidity and efficiency.

problem Reduced slippage and improved liquidity in decentralized finance.
method Deep reinforcement learning for predicting market equilibrium and optimizing liquidity.
result Improved capital efficiency and reduced slippage for crypto-asset traders.

In this paper we propose a novel variance reduction approach for additive functionals of Markov chains based on minimization of an estimate for the asymptotic variance of these functionals over suitable classes of control variates. A distinctive feature of the proposed approach is its ability to significantly reduce th…

2019-10-08abs ↗pdf ↗

Markov Chain Monte Carlo methods have revolutionised mathematical computation and enabled statistical inference within many previously intractable models. In this context, Hamiltonian dynamics have been proposed as an efficient way of building chains which can explore probability densities efficiently. The method emerg…

2017-05-08abs ↗pdf ↗

EEGNN improves graph neural networks by enhancing graph structure.

problem Mis-simplification of graphs by removing self-loops and unweighted edges reduces GNN performance.
method Proposes EEGNN framework using DMPGM for better graph structural information.
result EEGNN achieves significant performance improvement over baselines.

Bayesian methods enhance deep learning models by improving reliability and uncertainty.

problem Improving reliability and uncertainty awareness in deep learning models.
method Approximate Bayesian inference techniques, including SG-MCMC and VI, applied to deep learning models.
result Enhanced posterior inference for deep learning models, particularly in neural networks and generative models.

Markov chain decoders improve generative models' ability to produce heavy-tailed data.

problem Generative models struggle with heavy-tailed distributions.
method Replaced Gaussian decoder with Markov chain-based Phase-Type distributions.
result Significantly reduced tail Kolmogorov-Smirnov distance and extreme quantile error.