Neural network approximates diffusion bridges for efficiency and robustness.
problem Efficient simulation of conditioned diffusion processes, especially rare events and multimodal distributions.
method Trains a neural network to approximate bridge dynamics, eliminating MCMC and score modeling.
result Efficient sampling of conditioned diffusion bridges at comparable cost to unconditioned process.
BM2 learns Schrödinger bridges using neural networks.
problem Learning dynamic transport maps between two distributions.
method Coupled Bridge Matching (BM2) with neural networks. result Preliminary theoretical analysis and numerical experiments show BM2's effectiveness. New method samples from time-integrated stochastic bridges using neural networks.
problem Sampling from time-integrated stochastic bridges with high accuracy and speed.
method Polynomial chaos expansion and artificial neural networks.
result Robust, data-driven Monte Carlo sampling with thousands of samples in milliseconds.
A new method estimates Schrödinger bridges without iterative simulations or neural networks.
problem Estimating the time-dependent drift between two probability distributions.
method Solving the static entropic optimal transport problem and modifying the potentials.
result The Sinkhorn bridge method provably estimates Schrödinger bridges with a rate of convergence dependent on the target measure's intrinsic dimensionality.
BNN learns shared features between two data sources for specific tasks.
problem Learning shared features between two data sources for specific tasks.
method BNN uses two CNNs to project data sources into a feature space and learns a common representation for each task.
result BNN achieves state-of-the-art performance on various tasks.
New methods optimize transport and sampling for neural networks.
problem Designing effective training losses for neural networks.
method Optimal transport and stochastic optimal control through Schrödinger bridge problem.
result Valid training losses can be designed with numerical advantages.
SVD improves neural network optimization.
problem Optimizing neural networks.
method Using SVD as an initial guess for neural network parameters.
result Better optimization results.
In order to alleviate data sparsity and overfitting problems in maximum likelihood estimation (MLE) for sequence prediction tasks, we propose the Generative Bridging Network (GBN), in which a novel bridge module is introduced to assist the training of the sequence prediction model (the generator network). Unlike MLE di…
Unified framework extends adjoint Schrödinger bridge sampler to discrete spaces.
problem Challenges in learning discrete neural samplers due to gradients and combinatorial complexity.
method Introduces discrete ASBS, a unified framework that extends adjoint Schrödinger bridge sampler to discrete spaces.
result Empirically, discrete ASBS achieves competitive sample quality with significant advantages in training efficiency and scalability.
SIAN bridges simple models to neural networks by identifying necessary feature combinations.
problem The gap between simple models and powerful neural networks in performance.
method Feature interaction detection and sparse selection algorithm.
result Competitive performance across multiple tabular datasets with optimal tradeoff.
Improves discrete latent representations using differentiable approximation bridges.
problem Improving discrete latent representations in neural networks.
method Training with a differentiable approximation bridge (DAB) neural network.
result Improves state-of-the-art performance in various domains.
New approach uses Boolean circuits to optimize neural networks.
problem Improving efficiency of neural network implementations on hardware accelerators.
method Formalized neural networks as Boolean circuits, showing binarized networks are functionally complete.
result Binarized neural networks are functionally complete, suggesting new possibilities for neural network accelerators.
This research bridges binary and spiking neural networks for efficient on-chip AI.
problem Reducing compute requirements in machine learning frameworks.
method Training Spiking Neural Networks in extreme quantization regime and utilizing standard training techniques for conversion.
result Training Spiking Neural Networks in extreme quantization regime achieves near full precision accuracies.
UNSB uses neural Schrödinger Bridge to solve unpaired image-to-image translation.
problem Difficulties in unpaired image-to-image translation with diffusion models.
method Expresses SB problem as adversarial learning problems, incorporating advanced discriminators and regularization.
result Successfully solves various unpaired image-to-image translation tasks.
Develops active learning for scale-bridging simulations.
problem Quantitative predictions in nanoporous media and inertial confinement fusion.
method Active learning approach to optimize fine-scale simulations for coarse-scale hydrodynamics.
result Optimizes use of fine-scale simulations for coarse-scale predictions.
FKEE estimates expectations without samples, using diffusion bridges and PINNs.
problem Estimating expectations without large sample sizes.
method Diffusion bridge models and Feynman-Kac operator approximation using PINNs.
result Significantly reduces variance and improves efficiency.
This work bridges continual learning, active learning, and open set recognition in deep neural networks.
problem Protecting previously acquired representations from catastrophic forgetting in deep neural networks.
method Surveying the literature and proposing a consolidated view to integrate open set recognition and active learning principles.
result Joint improvement in alleviating catastrophic forgetting, querying data, selecting task orders, and robust open world application.
The paper bridges spectral and spatial graph convolutions, improving model capacity and transferability.
problem Improving graph neural networks by bridging spectral and spatial design.
method Theoretical demonstration and general framework for spectral analysis, new spectral convolutions, and depthwise separable convolutions.
result General framework allows spectral analysis of ConvGNNs, showing their performance and limits, and proposing new spectral convolutions.
Recognition of defects in concrete infrastructure, especially in bridges, is a costly and time consuming crucial first step in the assessment of the structural integrity. Large variation in appearance of the concrete material, changing illumination and weather conditions, a variety of possible surface markings as well …
One of the ways to train deep neural networks effectively is to use residual connections. Residual connections can be classified as being either identity connections or bridge-connections with a reshaping convolution. Empirical observations on CIFAR-10 and CIFAR-100 datasets using a baseline Resnet model, with bridge-c…
A new method uses Schrödinger bridges for deep conditional generative learning.
problem Learning conditional distributions with additional information.
method Schrödinger bridge approach with discretized SDE and deep neural network.
result Generated samples have higher quality and can estimate conditional density.
DCNs mimic neuronal networks for improved neural classification.
problem Lack of topological similarity between DNNs and biological neural networks.
method Developed DCNs with topologies inspired by real-world neuronal networks.
result High classification accuracy achieved by DCNs.
A new framework connects machine learning models with simulation models efficiently.
problem Interpreting complex machine learning models for real-world applications.
method Model-bridging framework using kernel mean embeddings.
result Simulations and machine learning models can be used together without high computational costs.
We propose using category theory to unify deep learning architectures.
problem Lack of a coherent bridge between model constraints and implementations.
method Apply category theory to unify neural network design.
result Theory recovers constraints from geometric deep learning and encodes standard constructs.
Neural networks have many successful applications, while much less theoretical understanding has been gained. Towards bridging this gap, we study the problem of learning a two-layer overparameterized ReLU neural network for multi-class classification via stochastic gradient descent (SGD) from random initialization. In …
Proposes TSBP for matching topological signal distributions.
problem Matching signal distributions on topological domains.
method Topological Schrödinger Bridge (TSBP) with linear topology-aware stochastic dynamics.
result Derives closed-form topological SB (TSB) for Gaussian boundary distributions.
Neural networks improve structural optimization solutions.
problem Quality of structural optimization solutions depends on parameterization.
method Optimizing neural network parameters to output densities for optimization.
result Our approach produces the best design 50% more often than baselines.
Study bridges GARCH and NN models for volatility forecasting.
problem Lack of interaction between GARCH and NN approaches for volatility forecasting.
method Established equivalence between GARCH and NN models, introduced GARCH-NN approach.
result GARCH-NN approach enhances volatility forecasting compared to standalone models.
This study bridges the gap between spatial and spectral GNNs.
problem Lack of direct comparison and cross-reference of existing GNNs.
method Systematically categorizes and examines GNNs into spatial and spectral domains.
result Establishes a strong relationship between spatial and spectral GNNs.
Neural approach enhances AI trustworthiness, generalization, and robustness.
problem Challenges in explaining, generalizing, and adapting AI models to uncertain environments.
method Customized trustworthy networks, flexible learning regularizers, open-world recognition losses.
result Significant performance improvements across various open-world multimedia recognition scenarios.
GAIL with neural networks converges to global optima and has a known rate.
problem Uncertainty about GAIL with neural networks achieving global optimality.
method Gradient-based alternating updates algorithm.
result Established sublinear convergence to globally optimal solution.
This paper analyzes how normalization layers improve neural network training.
problem Improving generalization performance and training speed of neural networks.
method Global convergence analysis of two-layer neural networks with ReLU activations and Weight Normalization.
result Introduction of normalization layers changes the optimization landscape, enabling faster convergence.
Deep Curvature Suite offers a PyTorch package for neural network curvature analysis.
problem Insufficient use of curvature information in neural networks.
method Implementation of Lanczos algorithm for neural network curvature analysis.
result Our package outperforms existing methods for similar purposes.
PrototypeML simplifies neural network design and development.
problem Error-prone code and time-consuming model design.
method Visual interface for neural networks, abstracting PyTorch.
result Reduces model design and development time, easier debugging.
This work bridges two views of feature learning in neural networks.
problem The relationship between kernel scale changes and data-adaptive feature learning in neural networks remains unresolved.
method Using statistical mechanics, the work derives analytical expressions for network output statistics across scaling regimes.
result Kernel adaptation can be reduced to an effective kernel rescaling, but multi-scale adaptive approach provides richer insights.
Graph neural networks struggle with proving unsatisfiability in complex logical formulas.
problem Proving unsatisfiability in complex logical formulas.
method Investigating the limitations of graph neural networks in logical reasoning tasks.
result Graph neural networks may fail in certifying unsatisfiability in Boolean formulae.
Natural language processing (NLP) can be done using either top-down (theory driven) and bottom-up (data driven) approaches, which we call mechanistic and phenomenological respectively. The approaches are frequently considered to stand in opposition to each other. Examining some recent approaches in deep learning we arg…
Theoretical analysis of deep neural networks for time series data.
problem Theoretical development for deep neural networks on temporally dependent observations is lacking.
method Established non-asymptotic bounds for prediction error of deep neural networks under mixing-type assumptions.
result Deep neural networks can model non-linear time series data with additional logarithmic factors due to dependence.
A neural network learns relational representations from raw data.
problem Learning reusable representations from raw pixel data.
method Explicitly relational neural network architecture trained on visual relational tasks.
result The architecture outperforms baselines on unseen tasks.
Paper converts graph learning to lifelong learning.
problem Learning graphs in a streaming fashion.
method Feature graph topology, converting node classification to graph classification.
result FGN achieves superior performance in lifelong human action recognition and feature matching.
Algorithm improves blockchain bridge efficiency.
problem Efficient cross-chain wealth management.
method Dynamic algorithm to optimize bridge capacities.
result Optimized fund transfers across networks.
Draft proposes adapting neural networks to match naive Bayes classifiers.
problem Bridge between neural networks and naive Bayes classifiers.
method Class-conditional compression and disentanglement using variational bounds.
result Latent representations enable naive Bayes classifier performance.
Paper establishes bounds for RNN-TPPs, showing four-layer networks can achieve vanishing errors.
problem Understanding theoretical limits of RNN-TPPs.
method Characterized RNN complexity, constructed neural approximations, applied truncation technique.
result Four-layer RNN-TPPs can achieve vanishing generalization errors.
This work bridges competitive learning with gradient-based learning for faster feature extraction.
problem Lack of powerful feature extractors in competitive learning methods.
method Introduces gradient-based competitive layers for feature extraction.
result Demonstrates theoretical equivalence and faster convergence of gradient-based competitive layers.
RedEx improves neural network optimization with convex optimization guarantees.
problem Difficult optimization of neural networks.
method RedEx architecture using convex optimization with semi-definite constraints.
result RedEx can efficiently learn functions fixed methods cannot.
New approach uses negative controls to estimate causal parameters without completeness conditions.
problem Estimating causal parameters when not all confounders are observed.
method Identification strategy based on minimax learning formulations for general function classes.
result Avoids completeness conditions and uniqueness assumptions on bridge functions.
DRE combines DNN with random feature regression for efficient neural network design.
problem Designing and training deep neural networks (DNN) efficiently and effectively.
method DRE architecture with two-layer neural networks, randomly drawn input and output weights trained with linear ridge regression.
result DRE outperforms state-of-the-art DNN in many data sets with lower computational cost.
Feed-forward networks are widely used in cross-modal applications to bridge modalities by mapping distributed vectors of one modality to the other, or to a shared space. The predicted vectors are then used to perform e.g., retrieval or labeling. Thus, the success of the whole system relies on the ability of the mapping…