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.

169,236 papers · 148 categories

Trend · papers per month

10.3%20.6%30.9%41.2% · May 201919922001200920182026
48 results for hybrid adversarial networks

GPDNNs inherit robustness from GPs and DNNs, outputting high entropy for adversarial examples.

problem Robustness of deep neural networks in real-world scenarios.
method GP hybrid deep networks (GPDNNs) combining GPs and DNNs.
result GPDNNs output high entropy for adversarial examples, indicating uncertainty.

Paper proposes a hybrid model for financial time series prediction using sentiment analysis.

problem Challenges in forecasting in non-stationary, complex environments with heterogeneous data.
method Hybrid model combining GANs with NLP-based sentiment analysis.
result Hybrid model enhances robustness in non-stationary environments.

Bidirectional learning improves neural network robustness to noise and attacks.

problem Improving neural network robustness to adversarial and static noise.
method Bidirectional learning (BL) techniques using error propagation and hybrid adversarial networks (HAN).
result Both methods improve robustness and accuracy, with HAN showing state-of-the-art performance.

Paper addresses hybrid learning with constrained adversaries, achieving optimal performance.

problem Hybrid learning problem with i.i.d. features and adversarial labels.
method Structured adversarial setting, efficient algorithm with ERM oracle.
result Oracle-efficient algorithm with regret scaling with Rademacher complexity.

Flow-GAN combines GAN and maximum likelihood for better sample quality and likelihood evaluation.

problem Challenges in evaluating generative models trained by maximum likelihood.
method Proposes Flow-GAN, a generative adversarial network that allows exact likelihood evaluation.
result Hybrid training of Flow-GAN can achieve high held-out likelihoods while maintaining visual fidelity.

We present a new autoencoder-type architecture that is trainable in an unsupervised mode, sustains both generation and inference, and has the quality of conditional and unconditional samples boosted by adversarial learning. Unlike previous hybrids of autoencoders and adversarial networks, the adversarial game in our ap…

2017-04-07abs ↗pdf ↗

This paper improves DQN agents' robustness to adversarial perturbations.

problem Improving DQN agents' robustness to adversarial perturbations.
method Adversarial training and a novel AGE mechanism based on εε-greedy and Boltzmann exploration.
result AGE mechanism enhances DQN agents' robustness to adversarial perturbations.

New measure assesses deep neural networks' robustness to adversarial attacks.

problem Deep learning's fragility to adversarial attacks limits its adoption in mission-critical applications.
method Introduces residual error as a new performance measure for assessing adversarial robustness.
result Demonstrates effectiveness of residual error in assessing robustness of deep neural networks.

The increasingly photorealistic sample quality of generative image models suggests their feasibility in applications beyond image generation. We present the Neural Photo Editor, an interface that leverages the power of generative neural networks to make large, semantically coherent changes to existing images. To tackle…

2016-09-22abs ↗pdf ↗

A new perspective on deep neural network regularization using RKHS norms.

problem Improving deep neural network performance and robustness.
method Using the norm of a reproducing kernel Hilbert space (RKHS) for regularization, with practical approximations.
result Effective regularization strategies for deep neural networks, including new penalties and hybrid approaches.

CANs improve GANs by enforcing structured constraints during training.

problem Generating valid structured objects like molecules and game maps from examples alone.
method Constrained Adversarial Networks (CANs) embed constraints into the model during training, penalizing invalid structures.
result CANs efficiently generate high-quality and novel valid structures.

Unified framework for learning from incomplete data under adversarial perturbations.

problem The role of unlabeled data in inference when the underlying distribution is adversarially perturbed.
method Unified learning framework combining Semi-Supervised Learning and Distributionally Robust Learning, with a novel generalization theory based on complexity measures.
result The method shows comparable performance to state-of-the-art on real-world datasets.

InfoQGAN uses mutual information to improve QGANs, overcoming mode collapse and feature disentanglement issues.

problem Mode collapse and lack of feature control in QGANs.
method Integrates InfoGAN principles with variational quantum circuit, classical discriminator, and MINE for mutual information optimization.
result InfoQGAN effectively mitigates mode collapse and achieves robust feature disentanglement.

Paper shows simple losses are effective at image reconstruction and detects overfitting in deep generators.

problem Detecting overfitting in deep generative networks, especially GANs.
method Simple losses for image reconstruction, analysis of reconstruction errors, comparison of GAN models.
result Overfitting is not detectable in pure GAN models but is in hybrid adversarial models.

Optimal semi-bandit algorithm for both stochastic and adversarial environments.

problem Optimal semi-bandit algorithm for both stochastic and adversarial environments.
method Developed a general semi-bandit algorithm that achieves O(logT)\mathcal{O}(\log T) regret for stochastic and O(T)\mathcal{O}(\sqrt{T}) regret for adversarial environments without regime or TT knowledge.
result First algorithm to achieve optimal O(logT)\mathcal{O}(\log T) and O(T)\mathcal{O}(\sqrt{T}) regret simultaneously for stochastic and adversarial environments.

Improved ExO method achieves near-optimal bounds in both stochastic and adversarial settings.

problem Finding optimal exploration strategies in online decision-making with limited feedback.
method Exploration by Optimization with hybrid regularizers for locally observable games.
result Achieved nearly optimal bounds of O(aeqak2m2logT/Δa)O(\sum_{a eq a^*} k^2 m^2 \log T / Δ_a) in stochastic and adversarial environments.

NSC classifies hybrid system states for time-bounded reachability, achieving high accuracy with minimal false negatives.

problem Classifying states in hybrid systems for time-bounded reachability.
method Neural State Classification using Deep Neural Networks.
result Achieved 99.25% to 99.98% accuracy with false-negative rates reduced to 0.0015 to 0 after tuning.

A new hybrid approach combines physics and machine learning for porous media transport.

problem Simulating 2-phase immiscible transport in porous media.
method Physics-informed deep learning with adversarial neural networks and automatic differentiation.
result The model accurately simulates shock and rarefaction phenomena with limited data.

New algorithm reduces online learning error for unknown feature distributions.

problem Oracle-efficient hybrid online learning with unknown feature and label distributions.
method Computational efficient online predictor using ERM oracle for finite-VC and fat-shattering classes.
result Oracle-efficient sublinear regret bounds for hybrid online learning with unknown feature generation.

Develops numerical methods for PDEs on hypergraphs and networks.

problem Solving PDEs on complex geometric structures like hypergraphs and networks.
method Hybrid finite element methods, focusing on hybrid discontinuous Galerkin methods.
result Derives numerical approximations for PDEs on hypergraphs and networks.

This work combines GANs and A3C for high-resolution image compression.

problem Image compression for high-resolution images without loss of quality.
method Hybrid approach using GANs and A3C for end-to-end learning.
result Improves PSNR for high-resolution images through end-to-end learning.

Robust ASR model removes fast-changing features to resist attacks.

problem Vulnerability of ASR systems to adversarial attacks.
method Removing fast-changing features using slow feature analysis or low-pass filtering.
result Hybrid ASR models are more than four times more robust against targeted attacks.

This work studies PAC learning under evasion attacks, proving exponential sample complexity for high-dimensional inputs.

problem Formal study of PAC learning under evasion attacks where the adversary misclassifies perturbed samples.
method Proves exponential sample complexity for high-dimensional inputs under evasion attacks, formalizes hybrid attacks.
result PAC learning requires exponential sample complexity for high-dimensional inputs under evasion attacks.

Efficient hybrid networks improve AI performance at the edge.

problem Achieving AI performance at the edge with minimal energy and memory usage.
method Proposed hybrid networks combining binary and full-precision layers.
result Hybrid networks achieve close to full-precision performance with up to 21.8x memory compression.

Bayesian network framework assesses urban risks across multiple domains.

problem Complex interdependencies in urban systems.
method Bayesian Belief Networks (BBNs) with DAGs, Hill-Climbing search, BIC, K2 scoring, synthetic data, SMOTE.
result Identifies key risk factors and quantifies likelihood of cascading failures.

A new framework handles hybrid action spaces in reinforcement learning.

problem Handling reinforcement learning with both discrete and continuous actions.
method Parametrized Deep Q-Networks (P-DQN) framework integrating DQN and DDPG.
result Empirical validation of efficiency and effectiveness in simulated RoboCup soccer and game King of Glory.

Novel hybrid method for Bayesian network structure learning reduces computational time without sacrificing accuracy.

problem Bayesian network structure learning efficiency and accuracy trade-off.
method Partitioned PC (pPC), pp-value adjacency thresholding (PATH), hybrid greedy initialization (HGI).
result pHGS achieves significant computational reductions compared to the PC algorithm without sacrificing structure learning accuracy.

New framework improves adversarial robustness in one-stage L2D.

problem Adversarial robustness in one-stage Learning-to-Defer (L2D).
method Formalizes attacks, proposes cost-sensitive adversarial surrogate losses, establishes theoretical guarantees.
result Improves robustness against untargeted and targeted attacks while preserving clean performance.

Transfer learning adapted for hybrid classical-quantum neural networks.

problem Optimizing data preprocessing and feature embedding for quantum processors.
method Adapting transfer learning to hybrid networks, using a pre-trained classical network augmented by a quantum circuit.
result Demonstrated the effectiveness of quantum transfer learning for image recognition and quantum state classification.

Hybrid model predicts flow and pressure in water systems.

problem Predicting flow and pressure in water distribution systems with complex spatial-temporal correlations.
method Hybrid dual-stage spatial-temporal attention-based recurrent neural networks (hDS-RNN).
result Our model outperformed 9 baseline models in flow and pressure series prediction.

Hybrid model combines VAR and neural network for OFI prediction.

problem Accurate prediction of Order Flow Imbalance (OFI) in high frequency trading.
method Combines Vector Auto Regression (VAR) and a simple feedforward neural network (FNN).
result Hybrid model achieves superior predictive accuracy compared to standalone models.