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.

168,657 papers · 148 categories

Trend · papers per month

164328492656 · Jun 202019922001200920172026
48 results for deep insights

Study explores fairness in financial deep learning through multi-scale trust quantification.

problem Ensuring fairness in financial deep learning models, especially under regulatory compliance.
method Conducts multi-scale trust quantification on a deep neural network for credit card default prediction.
result Demonstrates the feasibility and utility of multi-scale trust quantification for financial deep learning fairness.

A simple model explains deep learning phenomena like grokking and gradient boosting.

problem Understanding the unexpected behaviors of deep learning models.
method A telescoping sequence of first-order approximations to explain neural network performance.
result Empirical insights into neural network performance and training process.

Develops a deep multi-factor model for factor investing with clear financial insights.

problem Lack of interpretability and unclear financial insights in non-linear factor models.
method Industry and market neutralization modules, graph attention modules, factor-attention module.
result Demonstrates effectiveness in factor investing with real-world stock market data.

Paper explores Monge-Ampère in deep learning and quantum geometry.

problem Understanding the Monge-Ampère equation in deep learning.
method Review of Boltzmann learning, connection to optimal transport, insights from quantum geometry, renormalization group flow.
result Space of covariance matrices in learning dynamics coincides with the CAH cone.

The paper explores stability and generalization of deep GCNs.

problem Understanding the stability and generalization of deep GCNs from a theoretical perspective.
method Theoretical analysis of stability and generalization properties of deep GCNs.
result The stability and generalization of deep GCNs are influenced by the maximum absolute eigenvalue of the graph filter operators and the depth of the network.

This paper provides theoretical insights into why and how deep learning can generalize well, despite its large capacity, complexity, possible algorithmic instability, nonrobustness, and sharp minima, responding to an open question in the literature. We also discuss approaches to provide non-vacuous generalization guara…

2017-10-16abs ↗pdf ↗

HAD-Net forecasts glucose levels with insights into insulin and carbs diffusion.

problem Inaccurate predictions in glucose level forecasting without context understanding.
method Hybrid model combining deep learning and physiological models, using recurrent attention network.
result Achieves competitive performance in glucose level forecasting with plausible diffusion insights.

RSM provides insights into deep survival models' decision-making.

problem Ensuring trust in deep survival models' predictions for healthcare applications.
method Reverse survival model (RSM) framework that explains deep survival models' decisions.
result RSM extracts relevant features for deep survival models' predictions.

New framework explains deep neural networks using variational spline theory.

problem Understanding functions learned by deep neural networks.
method Developed a variational framework and function space.
result Deep ReLU networks are solutions to regularized data fitting problems over the proposed function space.

Gradient methods work well on overparameterized diagonal linear networks.

problem Understanding why gradient-based methods work well in overparameterized models.
method Study of Deep Diagonal Linear Networks with gradient flow analysis.
result Gradient flow on layer parameters induces a mirror-flow dynamic in the effective parameter space, leading to explicit convergence guarantees.

Deep convolutional networks can be understood through kernel methods, providing insights into their inductive bias.

problem Understanding the functional space and inductive bias of deep convolutional networks.
method Using kernel methods to analyze simple hierarchical kernels with convolution and pooling layers.
result The RKHS consists of additive models of interaction terms between patches, and pooling layers encourage spatial similarities.

New insights on how weight structure affects generalization in deep Gaussian feature models.

problem Understanding how weight structure impacts generalization in deep learning models.
method Using the replica trick from statistical physics to derive learning curves for models with structured Gaussian features.
result Allowing correlations between the rows of the first layer of features can aid generalization, while structure in later layers is generally detrimental.

This paper investigates how synthetic data and overparameterization improve VAE generalization.

problem Improving generalization performance of Variational Autoencoders (VAEs).
method Investigates the effectiveness of synthetic data and overparameterization in VAEs.
result Training on synthetic data and using more parameters improves VAE generalization, inference, and robustness.

Optimizes deep learning training by treating it as an optimal control problem.

problem Fragility of deep neural networks to adversarial inputs.
method Formulates adversarial training as a min-max optimization problem and interprets it as an optimal control problem.
result Provides the first convergence analysis of adversarial training algorithm.

New insights into Deep Autoencoders for better data approximation and generalization.

problem Understanding and improving generalization of deep learning models with more parameters than data.
method Interpreting Deep Autoencoders' structure and using Lie group theory for regularization.
result Regularizations enable Deep Autoencoders to better approximate data manifolds and generalize.

Recently, studies on deep Reservoir Computing (RC) highlighted the role of layering in deep recurrent neural networks (RNNs). In this paper, the use of linear recurrent units allows us to bring more evidence on the intrinsic hierarchical temporal representation in deep RNNs through frequency analysis applied to the sta…

2017-05-16abs ↗pdf ↗

Measuring sentence similarity is a classic topic in natural language processing. Light-weighted similarities are still of particular practical significance even when deep learning models have succeeded in many other tasks. Some light-weighted similarities with more theoretical insights have been demonstrated to be even…

2020-01-28abs ↗pdf ↗

New method improves deep learning models in noisy label classification.

problem Improving deep learning models in noisy label classification.
method Analyzes loss and uncertainty changes during training, designs a new robust training method.
result Significantly outperforms other state-of-the-art methods in various deep learning models.

This paper analyzes DRL strategies in finance, revealing unique trading patterns and performance differences.

problem Limited research on DRL behavior in finance applications.
method Analysis of trading behaviors and purchase diversity of DRL algorithms (A2C, PPO, SAC, DDPG, TD3).
result DRL algorithms exhibit distinct trading patterns and performance differences, with A2C outperforming others in terms of cumulative rewards.

CONFETTI improves interpretability of deep learning models for MTS by providing counterfactual explanations.

problem Lack of transparency in deep learning models for multivariate time series classification.
method CONFETTI is a novel multi-objective counterfactual explanation method that balances prediction confidence, proximity, and sparsity.
result CONFETTI outperforms state-of-the-art methods in various metrics, improving interpretability and decision support.

The design of codes for communicating reliably over a statistically well defined channel is an important endeavor involving deep mathematical research and wide-ranging practical applications. In this work, we present the first family of codes obtained via deep learning, which significantly beats state-of-the-art codes …

2018-07-02abs ↗pdf ↗

This paper explores SSL for graph neural networks, improving performance on real-world datasets.

problem Leveraging unlabeled data for graph neural networks to improve deep learning performance.
method Empirical study of various SSL pretext tasks on graphs and proposing a new approach called SelfTask.
result Proposes SelfTask, achieving state-of-the-art performance on real-world datasets.

Deep learning uses layers of transformations to predict structured data with uncertainty.

problem Predicting structured high-dimensional data efficiently and with uncertainty.
method Applying layers of semi-affine input transformations to find features for probabilistic statistical methods.
result Achieves scalable prediction rules with uncertainty quantification and feature selection.

Deep learning improves portfolio optimization in volatile markets.

problem Challenges in long-only, multi-asset strategies across market cycles.
method Training DL models with limited regime data using pre-training techniques and transformer architectures.
result Models show resilience and improved predictive accuracy in volatile markets.

New insights into using momentum for non-convex optimization.

problem Improving training of non-convex models like deep neural networks.
method Developed a Lyapunov analysis of SGD with momentum using stochastic primal averaging.
result Precise conditions under which SGD+M outperforms SGD and optimal hyper-parameter schedules.

We propose Deep Feature Factorization (DFF), a method capable of localizing similar semantic concepts within an image or a set of images. We use DFF to gain insight into a deep convolutional neural network's learned features, where we detect hierarchical cluster structures in feature space. This is visualized as heat m…

2018-06-26abs ↗pdf ↗

A deep probabilistic model analyzes DNA-encoded library data for efficient screening.

problem Complex data from DNA-encoded library experiments mask underlying signals.
method Compositional deep probabilistic model of DEL data, modeling latent reactions between synthons.
result DEL-Compose model demonstrates strong performance and valuable insights.

In recent years, Deep Learning has become the go-to solution for a broad range of applications, often outperforming state-of-the-art. However, it is important, for both theoreticians and practitioners, to gain a deeper understanding of the difficulties and limitations associated with common approaches and algorithms. W…

2017-03-23abs ↗pdf ↗

This review clarifies XAI for regression models and establishes new theoretical insights.

problem Lack of XAI techniques for regression models, especially in safety-critical applications.
method Clarifies conceptual differences, establishes theoretical insights, provides demonstrations, discusses challenges.
result Novel theoretical insights and demonstrations of XAI for regression models.

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 ↗

User smeznar achieved 8th place in PGDL by predicting generalization of deep learning models.

problem Understanding and predicting generalization in deep learning models.
method Creating simple metrics and finding their best combination for automatic testing on a dataset.
result Combination of various properties of neural network architectures can be used for generalization prediction.

New insights into continual learning for deep models, showing convergence issues but local linear solutions.

problem Challenges in continual learning for homogeneous deep models.
method Sequential projections onto task margin sets, leveraging nonconvex projection theory.
result Local linear convergence under certain conditions for homogeneous deep networks.

The study characterizes the conditioning of the Gauss-Newton matrix in neural networks.

problem Understanding the conditioning of the Gauss-Newton matrix in neural networks.
method Theoretical analysis of the GN matrix in deep linear and ReLU networks, extending to residual connections and convolutional layers.
result Established tight bounds on the condition number of the GN matrix in neural networks.