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

285683111 · Jan 202619922001200920172026
48 results for market drop-out

CODA uses a new dropout technique inspired by constructivism learning to improve deep learning performance.

problem Existing dropout methods fail to differentiate among instances, leading to overfitting.
method CODA incorporates structural information and uses a Bayesian nonparametric method to create a better dropout technique.
result CODA outperformed other state-of-the-art dropout techniques on 5 real-world datasets.

Paper proposes an ensemble approach to improve fairness in classifier decisions.

problem Improving fairness in classifier decisions to prevent bias.
method Inspired by dropout techniques, feature drop-out is used to reduce classifier dependence on sensitive features while maintaining accuracy.
result An ensemble of classifiers with reduced sensitivity to sensitive features and improved accuracy.

New geometric regularizers improve deep learning generalization.

problem Improving deep learning models' ability to generalize to unseen data.
method Using Bregman divergence loss and bounded spectral products, we propose a novel geometric regularizer to enhance model generalization.
result Good generalization can be achieved by designing deep models with specific structural regularizers.

Investigates fairness in pipeline models where individuals may drop out.

problem Fairness in pipeline models where individuals may drop out and subsequent stages depend on remaining individuals.
method Rigorous framework for evaluating fairness guarantees, showing that naïve auditing is insufficient and dependence must exist between stages.
result Fairness in pipelines can be arbitrary, even with just two stages, and requires dependence between stages.

The Resilient Propagation (Rprop) algorithm has been very popular for backpropagation training of multilayer feed-forward neural networks in various applications. The standard Rprop however encounters difficulties in the context of deep neural networks as typically happens with gradient-based learning algorithms. In th…

2015-09-15abs ↗pdf ↗

We propose to incorporate adversarial dropout in generative multi-adversarial networks, by omitting or dropping out, the feedback of each discriminator in the framework with some probability at the end of each batch. Our approach forces the single generator not to constrain its output to satisfy a single discriminator,…

2018-07-30abs ↗pdf ↗

This paper studies directed exploration for reinforcement learning agents by tracking uncertainty about the value of each available action. We identify two sources of uncertainty that are relevant for exploration. The first originates from limited data (parametric uncertainty), while the second originates from the dist…

2017-11-29abs ↗pdf ↗

Algorithm corrects bias in classification data.

problem Underrepresentation and intersectional bias in classification data.
method Estimate group-wise drop-out rates with small unbiased data, construct reweighting scheme, and present algorithm.
result Efficiently approximate loss of any hypothesis on true distribution.

End-to-end solution for recognizing handwritten numerals, avoiding traditional preprocessing steps.

problem Handwritten numeral string recognition with traditional preprocessing steps.
method YoLo-based model for automatic detection and recognition, avoiding heuristic-based preprocessing and segmentation.
result Proposed method reduces complexity and is a feasible end-to-end solution for numeral string recognition.

Dropout is a very effective way of regularizing neural networks. Stochastically "dropping out" units with a certain probability discourages over-specific co-adaptations of feature detectors, preventing overfitting and improving network generalization. Besides, Dropout can be interpreted as an approximate model aggregat…

2017-03-18abs ↗pdf ↗

Deep learning methods have shown great promise in many practical applications, ranging from speech recognition, visual object recognition, to text processing. However, most of the current deep learning methods suffer from scalability problems for large-scale applications, forcing researchers or users to focus on small-…

2015-08-28abs ↗pdf ↗

Stochastic Sparse Subspace Clustering improves subspace clustering by reducing over-segmentation through dropout.

problem Over-segmentation in subspace clustering.
method Introducing dropout regularization to enforce denser connections between points from the same subspace.
result Stochastic Sparse Subspace Clustering effectively handles large datasets and reduces over-segmentation.

New method improves hyperparameter tuning efficiency across similar tasks.

problem Mismatch between evaluations in current and previous tasks.
method Nested drop-out and auto-relevance determination for learning basis functions of increasing complexity.
result Improves sample efficiency in hyperparameter tuning across different data regimes.

The study explores using unlabeled data to improve survival time predictions.

problem Challenges in clinical follow-up studies due to drop-out and data collection issues.
method Investigates three approaches to incorporate unlabeled data in survival analysis.
result All approaches improve predictive performance over independent test data.

Dropout is a simple yet effective algorithm for regularizing neural networks by randomly dropping out units through Bernoulli multiplicative noise, and for some restricted problem classes, such as linear or logistic regression, several theoretical studies have demonstrated the equivalence between dropout and a fully de…

2017-10-10abs ↗pdf ↗

Paper analyzes SHB method for neural networks, proving stability, connectivity, and global convergence.

problem Theoretical understanding of SHB method for neural networks.
method Mean-field analysis of SHB dynamics related to a partial differential equation.
result SHB method converges to global optimum and exhibits stability and connectivity.

VINNAS uses variational inference to avoid mode collapse in neural architecture search.

problem Mode collapse in gradient-based NAS methods, leading to suboptimal architectures.
method Differentiable variational inference with variational dropout and automatic relevance determination.
result State-of-the-art accuracy with up to twice fewer non-zero parameters.

Study predicts online procrastination using machine learning.

problem Predicting procrastination in eLearning to prevent drop-outs.
method Comparison of multiple machine learning models with subjective and objective predictors.
result Models with objective predictors outperform those with subjective predictors.

A remarkable characteristic of overparameterized deep neural networks (DNNs) is that their accuracy does not degrade when the network's width is increased. Recent evidence suggests that developing compressible representations is key for adjusting the complexity of large networks to the learning task at hand. However, t…

2019-12-10abs ↗pdf ↗

MINN-SA enhances cancer detection using TCR sequences with better interpretability.

problem Challenges in detecting cancers using TCR sequences due to one-to-many correspondence.
method Multiple Instance Neural Networks based on Sparse Attention (MINN-SA).
result MINN-SA achieves highest AUC scores on 10 cancer types compared to existing MIL approaches.

Modeling a sequence of interactions between users and items (e.g., products, posts, or courses) is crucial in domains such as e-commerce, social networking, and education to predict future interactions. Representation learning presents an attractive solution to model the dynamic evolution of user and item properties, w…

2018-12-06abs ↗pdf ↗

AdaptiveLRF adapts low-rank factorization for neural networks to improve generalization without sacrificing accuracy.

problem Overfitting in neural networks, especially in shallow and deep models.
method Adaptive Low-Rank Factorization (LRF) applied to neural network layers based on their complexity.
result AdaptiveLRF improves generalization without significantly decreasing training speed or accuracy.

Study optimizes market making in Chinese stock market with stochastic control and scenario analysis.

problem Limited research on market making in Chinese stock market.
method Optimal market making framework with exponential CARA utility function, accounting for market conditions and risks.
result Impact of volatility and stamp duty on market maker's profit and liquidity.
Open Marketsq-fin.MF

Open markets are a subset of equity markets with fixed top stocks, changing over time.

problem Understanding the dynamics and characteristics of open markets.
method Analyzing the similarities and differences between open markets and closed equity markets, and exploring specific topics like CAPM and portfolio construction.
result The equivalence of market viability and the existence of a numeraire portfolio holds in open markets, similar to closed markets.

Study applies market microstructure to Cuban informal currency market, finding market makers improve liquidity.

problem Understanding dynamics of informal currency markets.
method Modeling bid/ask intentions using Limit Order Book, applying Avellaneda-Stoikov model with Market Maker.
result Market Maker improves market quality and bid/ask dynamics.

We study the effect of globalization on the Korean market, one of the emerging markets. Some characteristics of the Korean market are different from those of the mature market according to the latest market data, and this is due to the influence of foreign markets or investors. We concentrate on the market network stru…

2005-09-13abs ↗pdf ↗

Study shows informed traders harm market makers but price discovery benefits outweigh costs.

problem Informed traders' impact on market makers' profitability.
method Agent-based model with heterogeneous learning agents, multi-agent reinforcement learning.
result Informed market order flow is harmful when aggregate informedness is low but beneficial as it increases.

Research predicts money market volume based on capital market and bank rates ratio.

problem Understanding the influence of capital market and bank rates on money market instruments.
method Correlation matrix and time series model to predict money market volume.
result Predictive model for money market instrument volume based on historical data.

This study examines how DMMs affect market liquidity and competition.

problem The impact of DMMs on market liquidity and competition.
method Agent-based simulations to explore the effects of varying competition levels and incentive structures among DMMs.
result Optimal competition among DMMs maximizes liquidity benefits without negatively impacting price discovery.

AI learns market manipulation through simulation, suggesting regulation.

problem Regulating AI to prevent market manipulation.
method Used a genetic algorithm in an artificial market simulation.
result AI discovered market manipulation as an optimal strategy.

The paper finds that bear markets cause recessions and bull markets cause expansions, with bull markets having a stronger causal effect.

problem Understanding the asymmetric causal relationships between market conditions and economic cycles.
method Asymmetric causality tests using partial sums of positive and negative market components, with bootstrap simulations and leverage adjustments.
result Bear markets cause recessions and bull markets cause expansions, with bull markets having a stronger causal effect.