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.

169,341 papers · 148 categories

Trend · papers per month

2515017521,002 · Jun 202019922001200920182026
48 results for bimodal neural network

DBNet improves natural language image localization and detection.

problem Natural language-based visual entity localization with limited accuracy.
method Discriminative bimodal neural network (DBNet) trained with extensive negative samples.
result Significantly outperforms previous methods on Visual Genome dataset.

Proposes new loss functions for better handling bimodal predictive uncertainty.

problem Bimodal predictive uncertainty in machine learning models.
method Family of distribution-aware loss functions integrating normalized RMSE with Wasserstein and Cramér distances.
result Proposed loss functions reduce predictive uncertainty estimation error by 45% on complex bimodal datasets.

Bayesian neural networks decompose uncertainty into epistemic and aleatoric components for efficient and risk-sensitive learning.

problem Uncertainty in Bayesian neural networks estimation of weights and complex noise patterns in data.
method Decomposition of uncertainty into epistemic and aleatoric components, and definition of a risk-sensitive criterion for reinforcement learning.
result Identification of informative points for active learning and policies balancing expected cost, model-bias, and noise aversion.

Deep networks achieve linear separability through progressive folding of data in higher dimensions.

problem How feed-forward networks achieve linear separability for classification tasks.
method Progressive folding of the data manifold in unoccupied higher dimensions.
result The folding operation allows efficient solutions by providing access to arbitrary regions in the distribution.

Proposes a new normalization method for deep neural networks in financial forecasting.

problem Deep neural networks are sensitive to input variable range and prone to numerical issues, especially with financial time-series.
method Bilinear input normalization method that handles high-frequency financial time-series without expert knowledge.
result Significant improvements in forecasting future stock price dynamics over other normalization techniques.

We find stationary distributions in a financial model with trends and mean-reversion.

problem Financial markets with competing trends and mean-reversion.
method Analytical derivation of stationary distributions in various noise and feedback regimes.
result The distributions are unimodal Gaussians in small noise, small feedback limits, but can be bimodal for stronger trends.

Improved simulation of phase transitions using hierarchical autoregressive networks.

problem Simulating phase transitions in complex systems.
method Hierarchical Autoregressive Neural (HAN) network sampling algorithm.
result Significant improvement in statistical uncertainty compared to the Wolff cluster algorithm.

A new method generates synthetic data with realistic marginal distributions.

problem Generating synthetic data with bimodal and skewed marginal distributions.
method Pre-transformation variational autoencoders (PTVAEs) with separate parameter optimization for each variable.
result PTVAEs outperform other methods in generating synthetic data with bimodal and skewed distributions.

A new model generates samples with a succinct common representation using Wyner's common information.

problem Generating samples with a succinct common representation.
method Proposes a variational Wyner model trained to minimize symmetric Kullback-Leibler divergence with regularization terms.
result Demonstrates utility through joint and conditional generation experiments.

This study examines how earnings announcements affect option volatility and pricing.

problem The impact of earnings announcements on option volatility and pricing.
method Analysis of extremely short-term options data to study bimodality and concavity in IV curves.
result Investors pay a premium to hedge against extreme volatility during earnings announcements in the presence of concave IV smiles.

This work improved clustering methods by analyzing various datasets and dendrograms.

problem Avoiding false positives in clustering, especially for unimodal and bimodal data.
method Applied agglomerative clustering methods (single, average, median, complete, centroid, Ward's) to various datasets.
result Many methods detected two clusters in unimodal data, with single-linkage being more resilient.

Improved speech emotion recognition using pre-trained language models.

problem Challenging task of speech emotion recognition for natural human-machine interaction.
method Fine-tuning pre-trained language models for text emotion recognition, combining with speech emotion recognition.
result 73.5% accuracy in speech emotion recognition on a subset of IEMOCAP dataset.

Filtering data with a pre-trained model improves multimodal contrastive learning performance.

problem Improving the quality of internet-scale multimodal datasets.
method Characterized the performance of filtered contrastive learning under a bimodal data generation model.
result Data filtering using a pre-trained model reduces contrastive learning error by a factor of η\sqrt{η} in the large ηη regime.

New methods improve prediction regions for high-dimensional data.

problem Creating effective prediction regions for high-dimensional data.
method CD-split and HPD-split methods that combine split method and data-driven partition.
result CD-split and HPD-split converge to oracle highest predictive density set and satisfy local and asymptotic conditional validity.

Deep learning speeds up pressure prediction in carbon storage reservoirs.

problem Accurately forecasting reservoir pressure in geologic carbon storage projects with sparse well data.
method Combining InSAR surface displacement data with deep learning and data assimilation techniques.
result Workflow can predict reservoir pressure with high efficiency and uncertainty quantification.

Spatially aware ESN detects anomalies in chaotic time series.

problem Automated anomaly detection in chaotic time series, especially turbulent ocean simulations.
method Extended Echo State Network with spatially aware input maps and loss function.
result Spatial ESN reduces anomaly detection to thresholding of prediction error.

New research reveals diverse cascade sizes in finite networks, challenging traditional risk assessments.

problem Predicting the size of cascades in finite networks is difficult due to uncertain parameters and missing information.
method Derived explicit closed-form solutions for cascade size distributions in complete and star networks.
result Broad and even bimodal cascade size distributions in finite networks, not centered around the average.

Improved financial market calibration reveals large excess volatility.

problem Large excess volatility in financial markets.
method Extended Chiarella model to handle long-term value drifts, calibrated on multiple asset classes.
result Large excess volatility (factor ≈ 4 for stock indices) and bimodal mispricing distribution.

A simple spin system is constructed to simulate dynamics of asset prices and studied numerically. The outcome for the distribution of prices is shown to depend both on the dimension of the system and the introduction of price into the link measure. For dimensions below 2, the associated risk is high and the price distr…

2014-08-01abs ↗pdf ↗

Much research has been conducted arguing that tipping points at which complex systems experience phase transitions are difficult to identify. To test the existence of tipping points in financial markets, based on the alternating offer strategic model we propose a network of bargaining agents who mutually either coopera…

2015-09-16abs ↗pdf ↗

The US GDP per capita growth alternates between high and low rates, with an average growth rate of 1.6% since 1800.

problem Understanding the fluctuations and stability of US GDP growth rates over time.
method Wavelet transform analysis of US GDP per capita data from 1800 to 2010.
result The growth rate of US GDP per capita is bimodal, alternating between high and low rates with an average of 1.6% since 1800.

The two phase behavior in financial markets actually means the bifurcation phenomenon, which represents the change of the conditional probability from an unimodal to a bimodal distribution. In this paper, the bifurcation phenomenon in Hang-Seng index is carefully investigated. It is observed that the bifurcation phenom…

2007-12-30abs ↗pdf ↗

Study improves stock movement prediction using multimodal data.

problem Inaccurate stock movement prediction due to incomplete multimodal data integration.
method Introduces MSGCA framework for robust multimodal fusion.
result MSGCA framework outperforms existing methods by 21.7% on multimodal datasets.

Extended Chiarella model explains coexistence of trend and value in financial markets.

problem Coexistence and interaction of trend and value anomalies in financial markets.
method Extended Chiarella model with noise traders and fundamentalists, calibrated using Bayesian filtering.
result Extended model reproduces non-monotonic relation between past trends and future returns, leading to bimodal mispricing distribution.

AMF-VI uses adaptive mixtures of flows for robust VI across diverse distributions.

problem Inconsistent behavior of single-flow models across different distributions.
method Sequential expert training of individual flows and adaptive global weight estimation via likelihood-driven updates.
result AMF-VI achieves lower negative log-likelihood and stable gains in transport metrics across various posterior families.

New model corrects bias in crowdsourced ratings for diverse items.

problem Bias and noise in crowdsourced ratings for training data.
method Bayesian rating model with item-level effects for difficulty, discriminativeness, and guessability.
result New model avoids bias in training data, improving model goodness of fit.

Graphs of neural networks are represented to preserve symmetry, improving performance across various tasks.

problem Lack of equivariance in neural network representations of other neural networks.
method Represent neural networks as computational graphs and use graph neural networks to preserve permutation symmetry.
result Single model encodes diverse neural architectures, outperforming state-of-the-art methods.

Optimal rates for shallow ReLU networks in nonparametric regression.

problem Approximating smooth and non-smooth functions with shallow ReLU networks.
method Analysis of shallow ReLUk^k neural networks, using variation norms and deep learning theory.
result Optimal approximation rates for shallow ReLU networks in nonparametric regression.

Neural networks can approximate functions uniformly across various measures.

problem Universal approximation of functions across different probability measures.
method Proving neural networks are dense in Orlicz spaces, extending classical theorems.
result Neural networks uniformly approximate functions for weakly compact families of measures.

Novel framework explains generalization in deep neural networks.

problem Understanding and improving generalization in deep neural networks.
method Topological Quantum Neural Networks as the semi-classical limit of Deep Neural Networks.
result Demonstrates that the perceptron, viewed as the semi-classical limit, achieves similar results to standard neural networks without training.

Investigates how neural network graph structure impacts predictive performance.

problem Lack of understanding between neural network graph structure and predictive performance.
method Developed relational graph representation to analyze neural networks, identifying a 'sweet spot' for improved performance.
result Identified a 'sweet spot' in relational graph structure that significantly improves neural network predictive performance.

The FAIRnets Ontology makes neural networks findable, accessible, interoperable, and reusable.

problem The resource-intensive training of neural networks and the lack of training data availability.
method Development of FAIRnets Ontology to model neural networks on a meta-level and creation of a knowledge graph (FAIRnets) of over 18,400 neural networks.
result The FAIRnets Ontology and knowledge graph enable the reuse and recommendation of neural networks to data scientists.

FGNN generalizes graph neural networks to capture higher-order dependencies.

problem Capturing higher-order dependencies in graph-structured data.
method Introducing a factor graph neural network (FGNN) that can represent Max-Product Belief Propagation.
result FGNN effectively represents Max-Product Belief Propagation and performs well on both synthetic and real datasets.