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.

169,181 papers · 148 categories

Trend · papers per month

149298447596 · Jun 202019922001200920182026
48 results for Difference Modules

Introduces modular qq-holonomic modules to solve qq-difference equations.

problem Solving qq-difference equations in quantum invariants and Chern-Simons theory.
method Defines modular qq-holonomic modules with improved analyticity properties.
result Modular qq-holonomic modules explain structural properties of quantum invariants and Chern-Simons theory.

Minor typographical errors fixed. Cochran constructed many links with Alexander module that of the unlink and some nonvanishing Milnor invariants, using as input commutators in a free group and as an invariant the longitudes of the links. We present a different and conjecturally complete construction, that uses element…

2002-06-19abs ↗pdf ↗

Medusa detects significant modules in diverse biological data, improving gene-disease association predictions.

problem Ignoring semantic meanings in data modeling limits the value of diverse biological data.
method Medusa combines collective matrix factorization with submodular optimization to detect significant modules.
result Medusa outperforms methods ignoring semantic meanings in predicting gene-disease associations.

Study of 2d gauged linear sigma models to derive difference equations and spectral data.

problem Understanding monopole solutions and their spectral data in 2d gauged models.
method Analyzing ground states and cohomology of supercharges to derive difference modules and equations.
result Derived novel difference equations for brane amplitudes and hemisphere partition functions.

Enhanced bikei modules distinguish unoriented and non-orientable surface-links.

problem Distinguishing unoriented and non-orientable surface-links.
method Extending biquandle module invariants to unoriented surface-links using bikei modules.
result Enhanced bikei modules are more effective at distinguishing non-orientable surface-links than bikei homset cardinality alone.

HyperST-Net uses hypernetworks to improve spatio-temporal forecasting.

problem Forecasting spatio-temporal data is challenging due to complex spatial and temporal factors.
method Proposes a framework based on hypernetworks with three modules: spatial, temporal, and deduction.
result Models achieve significant improvements over state-of-the-art baselines.

Improves speaker verification for variable-duration utterances using a feature pyramid module.

problem Improving robustness for variable-duration utterances in speaker verification.
method Integrates a feature pyramid module into multi-scale aggregation to enhance speaker-discriminative information from multiple layers.
result Improves performance for both short and long utterances compared to state-of-the-art approaches.

Study Berry connections for 2d GLSMs, linking to cohomology theories.

problem Quantise ground states of 2d (2,2)(2,2) GLSMs on a circle.
method Relate periodic monopole solutions to difference modules and vector bundles with filtrations.
result Derive novel difference equations for brane amplitudes and vortex partition functions.

We establish a relationship between two different generalizations of Lie algebroid representations: representation up to homotopy and Vaintrob's Lie algebroid modules. Specifically, we show that there is a noncanonical way to obtain a representation up to homotopy from a given Lie algebroid module, and that any two rep…

2011-07-07abs ↗pdf ↗

Paper defends deep learning classifiers against channel-aware adversarial attacks.

problem Deep learning classifiers are vulnerable to adversarial attacks.
method Channel-aware adversarial attacks are presented and defended against.
result Certified defense based on randomized smoothing makes classifiers robust.

The classical abelian invariants of a knot are the Alexander module, which is the first homology group of the the unique infinite cyclic covering space of S^3-K, considered as a module over the (commutative) Laurent polynomial ring, and the Blanchfield linking pairing defined on this module. From the perspective of the…

2002-06-25abs ↗pdf ↗

Study connects knot contact homology to Chern-Simons theory's large N limit.

problem Relate knot contact homology to Chern-Simons theory's large N limit.
method Prove conjecture linking augmentation varieties to Chern-Simons theory's large N limit; characterize HOMFLYPT difference module.
result Classical limit of HOMFLYPT difference module equals degree 0 abelianized knot contact homology.

Learn to automatically plug domain-specific modules into a common network.

problem Learning inflexibility and computational intensiveness in multi-domain learning.
method Neural Architecture Search (NAS) for data-driven adapter plugging and structure design.
result NAS-driven MDL model achieves comparable performance to existing approaches.

Improves Bayesian optimization efficiency for mixed variable spaces.

problem Boosting sample efficiency in Bayesian optimization for mixed variable spaces.
method Proposes frequency modulated (FM) kernels to model complex dependencies across different types of variables.
result BO-FM outperforms competitors in various optimization problems.

Let Dk{\cal D}^k be the space of kk-th order linear differential operators on R{\bf R}: A=ak(x)dkdxk++a0(x)A=a_k(x)\frac{d^k}{dx^k}+\cdots+a_0(x). We study a natural 1-parameter family of $\Diff(\bf R)$- (and $\Vect(\bf R)$)-modules on Dk{\cal D}^k. (To define this family, one considers arguments of differential operators as tensor-d…

1996-02-04abs ↗pdf ↗

Proposes GPCA module for channel attention in CNNs using Gaussian processes.

problem Improving performance in visual tasks through effective channel selection.
method Integrates Gaussian processes into channel attention mechanisms for probabilistic modeling of channel correlations.
result Demonstrates improved performance of GPCA module in end-to-end CNN training.

Paper proposes a predictive maintenance system for solar plants using big data.

problem Fault prediction in photovoltaic plants to reduce downtime and maintenance costs.
method Data-driven approach with unsupervised clustering and Pattern Recognition Neural Network.
result Effective prediction of both generic and specific faults, up to 7 days in advance.

PICLE uses probabilistic models to efficiently evaluate and compose modules for continual learning.

problem Challenging search space of module compositions in continual learning.
method Probabilistic framework to cheaply compute module compositions' fitness.
result First modular CL algorithm to achieve perceptual, few-shot, and latent transfer.

Developed a new statistic to test binary regime switching models.

problem Testing the model assumption of binary regime switching extension of GBM.
method Proposed a new discriminating statistics and identified an admissible class of regime switching candidate models.
result Sampling distribution of the test statistics differs significantly between different regime switching models.

Dynamic information balancing reduces catastrophic forgetting in modular neural networks.

problem Catastrophic forgetting in neural networks when learning multiple tasks.
method Dynamic Information Balancing (DIB) using reinforcement learning to adaptively route inputs based on module information load.
result DIB combined with EWC regularization outperforms models with similar capacity and EWC regularization.

Two solutions for multi-modal record linkage using Deep Learning inspired by Visual Question Answering.

problem Matching records from multiple sources representing the same entity.
method Two fusion modules: Recurrent Neural Network + Convolutional Neural Network and Stacked Attention Network. A Siamese Neural Network computes similarity.
result Recurrent Neural Network + Convolutional Neural Network fusion module outperforms a simple model.

A framework evaluates the impact of different modules in graph contrastive learning.

problem Insufficient module-level evaluation in existing graph contrastive learning methods.
method Proposes a framework decomposing GCL models into four modules for module-level evaluation.
result Identifies module-level guidelines and competitive performance of different modules.

In this paper the properties of the Kauffman bracket skein module of L(p,q)L(p,q) are investigated. Links in lens spaces are represented both through band and disk diagrams. The possibility to transform between the diagrams enables us to compute the Kauffman bracket skein module on an interesting class of examples consisti…

2015-06-03abs ↗pdf ↗

CardiacGen generates realistic ECG signals for training deep learning models.

problem Creating realistic synthetic ECG signals for training deep learning models.
method Hierarchical deep generative model with multi-objective loss functions.
result Synthetic ECG signals from CardiacGen can be used for data augmentation and improve classifier performance.

Paper proposes a time-frequency analysis method for blind modulation classification in MIMO systems.

problem Blind modulation classification in MIMO systems with overlapping signals and unknown channel parameters.
method Time-frequency analysis using windowed short-time Fourier transform, conversion to RGB spectrogram images, convolutional neural network for classification, decision fusion.
result Proposed scheme achieves high classification accuracy at different SNRs, outperforming existing methods.

Current deep learning models are mostly build upon neural networks, i.e., multiple layers of parameterized differentiable nonlinear modules that can be trained by backpropagation. In this paper, we explore the possibility of building deep models based on non-differentiable modules. We conjecture that the mystery behind…

2017-02-28abs ↗pdf ↗

Develops a new model for radar waveform classification and clustering.

problem Classifying and clustering radar waveforms with different modulation types.
method Introduces a generalized multivariate Student-t mixture model with a new prior distribution for hyper-parameters.
result The method is less sensitive to initialization and provides more accurate results.

Improved recurrent neural networks learn long-term dependencies through multi-scale memory.

problem Capturing long-term dependencies in recurrent neural networks.
method Incremental training of a modular RNN architecture with multi-scale hidden states.
result Incremental training and multi-scale memory enhance RNNs' ability to learn long-term dependencies.