We introduce a novel Deep Reinforcement Learning (DRL) algorithm called Deep Quality-Value (DQV) Learning. DQV uses temporal-difference learning to train a Value neural network and uses this network for training a second Quality-value network that learns to estimate state-action values. We first test DQV's update rules…
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.
169,051 papers · 148 categories
Trend · papers per month
48 results for “deep value networks”
Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximationcs.LG
Polynomial-time method approximates Shapley values for deep neural networks.
problem Lack of reliable attribution methods for deep neural networks.
method Polynomial-time approximation of Shapley values using uncertainty propagation.
result Our method produces significantly better approximations of Shapley values than existing methods.
New theorem for deep neural networks improves classification margins.
problem Improving classification margins in deep neural networks.
method Local class-purity theorem and margin p-values for training and testing samples.
result Enhanced understanding and computation of classification margins.
Under-parameterization hinders deep RL's efficiency.
problem Implicit under-parameterization impairs data-efficiency in deep RL.
method Characterized and mitigated the rank collapse of value network features.
result Controlling rank collapse improves deep RL performance.
It is well known that the initialization of weights in deep neural networks can have a dramatic impact on learning speed. For example, ensuring the mean squared singular value of a network's input-output Jacobian is is essential for avoiding the exponential vanishing or explosion of gradients. The stronger condi…
Bayesian sparsification improves complex-valued neural networks by 50-100x with minimal performance loss.
problem Efficiently compressing complex-valued neural networks for embedded systems.
method Extending Sparse Variational Dropout to complex-valued networks and conducting a numerical study.
result Achieved state-of-the-art performance on MusicNet with 50-100x compression.
Complex-valued neural networks improve seismic data analysis by preserving phase information.
problem Low-frequency aliasing in seismic data due to discarded phase information.
method Developed complex-valued deep convolutional networks to leverage phase information in deterministic physical data.
result Complex-valued networks outperform real-valued networks in training and inference from deterministic physical data.
Method selects the best deep learner for time-series prediction using Bayesian networks.
problem Selecting the most effective deep learning model for time-series prediction.
method Bayesian network selects deep learners based on input variables and cluster training data.
result Threshold value determines which deep learners predict time-series data robustly.
DNNSurv uses pseudo values to simplify deep learning for survival analysis.
problem Modeling survival data using deep learning methods.
method Two-step approach: transform survival times into pseudo values, then use them in a deep neural network.
result Deep neural networks can be applied to survival analysis by simplifying the problem into a regression task.
This paper shows using classification instead of regression improves deep RL scalability.
problem Challenges in training value functions for large networks in deep RL.
method Used categorical cross-entropy loss instead of mean squared error regression.
result Significant improvements in performance and scalability across various domains.
Deep ReLU networks can be simplified to a three-layer model.
problem Understanding the behavior of deep neural networks.
method Constructive proof and algorithm to transform deep networks into shallow ones.
result Deep ReLU networks can be represented by a simpler three-layer structure.
Deep neural networks reduce loan portfolio risk.
problem Minimizing risk in peer-to-peer lending portfolios.
method Proposed DeNN and DSNN models to predict default probability and time.
result DeNN model significantly reduces portfolio VaRs at various confidence levels.
Deep RBVFs improve continuous control in RL.
problem Challenges in finding optimal actions for continuous actions in RL.
method Introduced deep radial-basis value functions (RBVFs) for continuous control.
result RBF-DQN significantly outperforms value-function-only baselines and is competitive with actor-critic algorithms.
Deep ReLU networks escape from the origin via saddle points with a low-rank bias.
problem Understanding the dynamics of gradient descent in deep ReLU networks.
method Analysis of escape directions and singular values of weight matrices.
result The first singular value of the -th layer weight matrix is at least larger than any other singular value.
Introduces epistemic deep learning for better uncertainty estimation in neural networks.
problem Uncertainty quantification in deep neural networks.
method Random-set convolutional neural networks with belief function-based loss functions.
result Epistemic approach produces better performance in uncertainty estimation.
Develops deep learning model for detecting anomalies in transportation data.
problem Anomaly detection in temporal data of transportation networks.
method Proposes EVT-LSTM model combining LSTM and EVT, trained with an objective function.
result EVT-LSTM model outperforms other models in anomaly detection.
We review recent results about the maximal values of the Kullback-Leibler information divergence from statistical models defined by neural networks, including naive Bayes models, restricted Boltzmann machines, deep belief networks, and various classes of exponential families. We illustrate approaches to compute the max…
Paper tackles interpretability issues in deep learning models.
problem Lack of understanding of deep learning models' decision-making processes.
method Integrates concepts from machine learning, quantum computation, and quantum field theory.
result Demonstrates a many valued quantum logic system in Convolutional Deep Belief Networks.
Deep gated networks help understand training and generalization in deep learning.
problem Understanding the role of SGD in training and generalization of deep neural networks with ReLU activation.
method Developed deep gated networks (DGNs) as a framework to analyze training and generalization in DNNs with ReLU activation.
result Gate adaptation is key for generalization in deep neural networks.
Deep neural networks can solve optimal stopping problems without dimensionality issues.
problem Optimal stopping problems in high-dimensional state spaces.
method Established a general framework for deep ReLU neural networks to approximate value functions and continuation values.
result Deep neural networks can approximate value functions and continuation values with error at most ε of size κd^q ε^(-r).
GAN-powered Deep Distributional Reinforcement Learning for Resource Management in Network Slicingcs.LG
Paper proposes GAN-DDQN for efficient resource allocation in network slicing.
problem Efficient resource allocation in network slicing with varying service demands.
method Leverage deep reinforcement learning with GAN-DDQN to minimize SSR and SE discrepancies.
result Proposed GAN-DDQN and Dueling GAN-DDQN algorithms improve resource allocation efficiency.
Paper introduces vector-valued variation spaces for multi-output neural networks.
problem Understanding and optimizing multi-output neural networks.
method Development of vector-valued variation spaces and representer theorem.
result Novel bounds for layer widths in deep networks and a convex optimization method for compression.
Proto-value networks improve deep reinforcement learning representations using auxiliary tasks.
problem Improving deep reinforcement learning representations with auxiliary tasks.
method Derived a new family of auxiliary tasks based on the successor measure, combined with off-policy learning rule.
result Proto-value networks produce rich features comparable to established algorithms using only linear approximation and a small number of interactions.
DFNNs predict non-Euclidean responses from Euclidean predictors.
problem Regression with non-Euclidean responses.
method Deep Fréchet neural networks (DFNNs) approximating conditional Fréchet means.
result DFNNs consistently outperform existing methods in empirical studies.
Deep networks with path norm regularization can approximate analytic functions.
problem Approximating analytic functions with neural networks.
method Path norm regularized deep networks with activation function.
result Deep networks can approximate analytic functions with logarithmic dependence on approximation error.
Business analytics refers to methods and practices that create value through data for individuals, firms, and organizations. This field is currently experiencing a radical shift due to the advent of deep learning: deep neural networks promise improvements in prediction performance as compared to models from traditional…
Study interprets deep learning models for Heston model in finance.
problem Interpreting black-box deep learning models in finance.
method Investigated Heston model using local and global strategies from cooperative game theory.
result Shapley values can effectively explain neural networks and improve model architecture selection.
Stochastic neural networks can approximate any function, even with correlated outputs.
problem Approximating functions with stochastic outputs and correlations.
method Investigating deep sigmoid belief networks to approximate any stochastic mapping.
result Minimal number of layers and units needed for approximation.
Complex-valued neural networks can approximate any continuous function.
problem Generalizing the universal approximation theorem to complex-valued networks.
method Characterizing activation functions for complex networks to approximate any continuous function.
result Different activation functions are required for deep vs shallow complex networks to achieve universal approximation.
Every local minimum in non-convex machine learning is globally optimal.
problem Non-convex optimization challenges in machine learning.
method Proves every local minimum achieves globally optimal value of perturbable gradient basis model.
result Theoretical support for non-convex machine learning similar to convex machine learning.
Deep learning predicts S&P 500 index direction.
problem Accurate stock price prediction remains challenging.
method Convolutional neural network model for S&P 500 index forecasting.
result Model achieves over 55% accuracy in predicting index direction.
PIVEN predicts both specific values and prediction intervals.
problem Improving robustness of neural nets in regression tasks.
method PIVEN is a deep neural network that produces both a prediction interval and a specific value prediction.
result PIVEN produces tighter uncertainty bounds than state-of-the-art approaches for prediction intervals.
Unified framework for Riemannian deep learning across manifold-valued representations.
problem Deep learning on manifold-valued representations often relies on Euclidean approximations or costly geometric operations.
method Develops reusable neural modules, manifold-specific network architectures, and geometric designs.
result Generalizes batch normalization and multinomial logistic regression to broader classes of manifolds.
Unified framework for Riemannian deep learning across manifold-valued representations.
problem Deep learning on manifold-valued data lacks reusable modules, specific network architectures, and efficient geometric operations.
method Develops reusable neural modules, manifold-specific network architectures, and geometric designs for broad classes of Lie groups and gyrogroups.
result Generalizes batch normalization and multinomial logistic regression to Riemannian manifolds, including SPD and hyperbolic spaces.
Deep single-index Fréchet regression for metric space-valued outputs
problem Predicting outputs in non-Euclidean spaces
method DeSI (Deep Single-Index Fréchet Regression)
result Interpretable index direction for inputs
A new method trains deep networks by separating weight locations from values.
problem Training deep networks efficiently and effectively.
method Lookahead Permutation (LaPerm) to train DNNs by reconnecting weights.
result LaPerm can train DNNs with random and dense, sparse, or single-valued initial weights.
SVEHNN explains DNN diagnoses of Alzheimer's disease from neuroanatomy and biomarkers.
problem Interpreting deep neural networks for medical diagnosis, especially in the clinic.
method Shapley Value Explanation of Heterogeneous Neural Networks (SVEHNN) for local explanations.
result SVEHNN provides interpretable explanations for DNN diagnoses with reduced runtime.
A new method learns action representations for reinforcement learning.
problem Efficient action-value estimation in reinforcement learning.
method Action hypergraph networks framework for learning action representations.
result Hypergraph Q-networks show effectiveness on various domains.
This work examines aggregation functions in Deep Set learning.
problem The sensitivity of Deep Set networks to aggregation function choices.
method Investigation of alternative aggregation functions, including learnable recurrent ones.
result Learnable aggregations improve performance, reduce hyper-parameter sensitivity, and generalize better.
This paper studies learning rate policies for deep neural networks, offering metrics and tools for better tuning.
problem Effective tuning of learning rates for deep neural networks is challenging and crucial for achieving high accuracy.
method Comprehensive study of 13 learning rate functions, proposing metrics for evaluation, and developing LRBench for benchmarking and selection.
result Identification of good learning rate policies with effective ranges and step sizes for various LR update schedules.
Deep neural networks forecast financial return distributions accurately.
problem Forecasting probability distributions of financial returns.
method Used 1D CNN and LSTM architectures with custom loss functions to optimize distribution parameters.
result LSTM with skewed Student's t distribution outperformed classical models in multiple evaluation metrics.
The study compares econometric and deep learning models for forecasting COMEX copper futures volatility.
problem Forecasting volatility of COMEX copper futures across different time intervals.
method Econometric models (GARCH, HAR) and deep learning models (RNN, LSTM, GRU) applied to daily and hourly data.
result Deep learning models outperform econometric models in hourly data, but HAR remains the best overall for daily data.
We methodologically address the problem of Q-value overestimation in deep reinforcement learning to handle high-dimensional state spaces efficiently. By adapting concepts from information theory, we introduce an intrinsic penalty signal encouraging reduced Q-value estimates. The resultant algorithm encompasses a wide r…
Stochastic gradient descent (SGD) has achieved great success in training deep neural network, where the gradient is computed through back-propagation. However, the back-propagated values of different layers vary dramatically. This inconsistence of gradient magnitude across different layers renders optimization of deep …
Random matrix analysis reveals that neural network weights are mostly random, with some indicating learned information.
problem Understanding how neural networks store information needed for tasks.
method Random matrix theory (RMT) applied to weight matrices of trained deep neural networks.
result Most singular values and eigenvectors of trained neural networks follow universal RMT predictions, suggesting they are random and do not contain system-specific information.
Deep Galerkin Method estimates value function for mean-field control problem.
problem Optimal control of agents with average welfare as the objective.
method Apply DGM to estimate value function and distribution evolution.
result Neural network approximations converge to analytical solution.
We propose to explain the predictions of a deep neural network, by pointing to the set of what we call representer points in the training set, for a given test point prediction. Specifically, we show that we can decompose the pre-activation prediction of a neural network into a linear combination of activations of trai…
Deep-IRT combines deep learning and IRT for explainable knowledge tracing.
problem Lack of explainability in deep learning-based knowledge tracing models.
method Synthesis of DKVMN and IRT models to estimate student and item parameters.
result Deep-IRT retains DKVMN performance while providing psychological interpretations.