DeepWeightFlow generates diverse neural network weights efficiently.
problem Generating complete neural network weights efficiently and accurately.
method Flow Matching in weight space with Git Re-Basin and TransFusion.
result DeepWeightFlow generates high-accuracy neural networks without fine-tuning.
We propose two neural network based mixture models in this article. The proposed mixture models are explicit in nature. The explicit models have analytical forms with the advantages of computing likelihood and efficiency of generating samples. Computation of likelihood is an important aspect of our models. Expectation-…
Survey on statistical theories of neural networks, focusing on approximation, training dynamics, and generative models.
problem Understanding the statistical properties and training dynamics of neural networks.
method Review of existing literature on neural networks from three perspectives: approximation, training dynamics, and generative models.
result Theoretical insights into neural network training dynamics and generative models.
Proposes Neural Complexity (NC) for predicting and explaining generalization in deep neural networks.
problem Challenges in specifying a suitable complexity measure for deep neural networks to predict and explain generalization.
method A meta-learning framework that learns a scalar complexity measure through interactions with many heterogeneous tasks.
result Trained NC model can be added to standard training loss to regularize any task learner.
Neural ODEs provide a framework for studying the training dynamics of neural networks.
problem Training dynamics of neural networks
method Dynamical mean field theory
result Derive learning curves in the high-dimensional limit
Model-based neural networks generalize better than ReLU networks for sparse recovery.
problem Understanding and quantifying the superior generalization of model-based neural networks.
method Using complexity measures like global and local Rademacher complexities, the paper provides theoretical bounds on generalization and estimation errors.
result Model-based neural networks exhibit higher generalization capabilities for sparse recovery problems compared to ReLU networks.
Generative neural samplers are probabilistic models that implement sampling using feedforward neural networks: they take a random input vector and produce a sample from a probability distribution defined by the network weights. These models are expressive and allow efficient computation of samples and derivatives, but …
NeSS combines neural and symbolic approaches for better compositional generalization.
problem Lack of compositional generalization in deep learning models.
method NeSS uses a neural network to generate traces, executed by a symbolic stack machine with sequence manipulation.
result Achieves 100% generalization performance across multiple domains.
The paper proves neural networks are almost always surjective, impacting model safety.
problem Ensuring neural networks can generate any output, including harmful content.
method Analyzing fundamental neural architectures and generative models.
result Many neural architectures are almost always surjective, allowing for arbitrary outputs.
Improved neural topic model for semi-supervised learning.
problem Representing textual data in an interpretable manner with limited labeled data.
method Label-Indexed Neural Topic Model (LI-NTM) that combines deep generative models with semi-supervised learning.
result LI-NTM outperforms existing models in document reconstruction and classifier performance.
A body of recent work in modeling neural activity focuses on recovering low-dimensional latent features that capture the statistical structure of large-scale neural populations. Most such approaches have focused on linear generative models, where inference is computationally tractable. Here, we propose fLDS, a general …
Study clarifies Bayesian generalization error in CBM for 3-layered linear neural networks.
problem Understanding the generalization error in concept bottleneck models.
method Mathematical analysis of Bayesian generalization error and free energy in CBM for 3-layered linear neural networks.
result CBM significantly alters the parameter region and Bayesian generalization error compared to standard models.
Neural SVEs model complex systems with memory, outperforming traditional methods.
problem Modeling systems with memory effects and irregular behavior.
method Introducing neural stochastic Volterra equations as a physics-inspired architecture.
result Neural SVEs outperform neural SDEs and DeepONets in various applications.
Sig-Splines model uses signatures and splines for time series data, achieving universality and convexity.
problem Creating a generative model for multivariate time series data.
method Combines linear transformations and signature transforms into a neural spline flow.
result Achieves universality and introduces convexity in model parameters.
A neural network model minimizes region-based free energy for faster inference in MRFs.
problem Efficient inference in complex Markov random fields (MRFs).
method Region-based Energy Neural Network (RENN) that directly minimizes region-based free energy.
result RENN outperforms other methods in marginal distribution estimation, partition function estimation, and MRF learning.
Consistent partial identification of causal effects proved for neural models.
problem Consistency of neural causal partial identification methods.
method Proving consistency for neural models with continuous and categorical variables, considering architecture design and Lipschitz regularization.
result Proven consistency of partial identification via neural causal models in a general setting.
Quadratic models explain neural network behavior during training.
problem Understanding neural network dynamics during training with large learning rates.
method Developed and tested Neural Quadratic Models.
result Neural Quadratic Models exhibit the 'catapult phase' similar to neural networks.
GraphMoE generates random graphs using neural networks and graphlets.
problem Learning generative models for random graphs.
method GraphMoE uses a neural network trained with graphlets and subgraph counts to match the distribution of random graphs.
result GraphMoE can generate graphs that mimic various real-world datasets and fool graph classifiers.
Neural Boltzmann Machines improve on CRBMs for modeling data.
problem Limited expressivity of CRBMs with noisy data.
method Convert CRBM parameters to neural networks.
result NBMs can approximate data likelihood better.
neuralGAM package interprets neural networks by fitting them to feature contributions.
problem difficulty understanding neural network decisions
method Generalized Additive Neural Networks (GAM)
result interpretable Deep Learning model with accurate feature contributions
Quantum neural networks generalize better due to flatter parameter space.
problem Generalization in quantum neural networks.
method Mapped feature data to a quantum state, applied unitary evolution, and measured for classification.
result Quantum neural networks have better generalization than classical networks.
Roundtrip uses deep generative models for flexible density estimation.
problem Density estimation in statistics and machine learning.
method Roundtrip is a deep generative neural density estimator that uses flexible mappings.
result Roundtrip achieves state-of-the-art performance in density estimation tasks.
Smartfluidnet accelerates Eulerian fluid simulation with neural networks.
problem Current neural network methods for Eulerian fluid simulation lack flexibility and generalization.
method Smartfluidnet automates model generation and dynamic switching to meet user requirements.
result Smartfluidnet achieves 1.46x and 590x speedup compared to state-of-the-art models, with better simulation quality.
CNN-F uses generative feedback to improve neural networks' robustness to perturbations.
problem Neural networks' vulnerability to input perturbations like noise and attacks.
method Enforces self-consistency in neural networks by incorporating generative recurrent feedback.
result CNN-F shows significantly improved adversarial robustness compared to conventional CNNs.
Deep networks become equivalent to linear models in large data regimes.
problem Understanding the behavior of deep neural networks in large data regimes.
method Information-theoretic analysis of fully-trained neural networks in proportional scaling regime.
result Proves deep Gaussian equivalence principle, showing deep networks can be simplified to linear models.
Gaussian process models simplify neural network behavior for easier understanding.
problem Understanding and predicting the behavior of deep learning systems.
method Constructing surrogate models using Gaussian processes from finite neural networks.
result Surrogate models capture phenomena like spectral bias and predict generalization well.
New model improves MCMC efficiency and multi-modal distribution exploration.
problem Inefficient and slow MCMC methods for complex distributions.
method Deep involutive generative models for Metropolis-Hastings updates.
result Deep involutive models can learn complex MCMC updates efficiently.
Modular neural causal models outperform other models in generalization and adaptation.
problem Robust out-of-distribution generalization and fast adaptation in machine learning.
method Factorizing data generating process into modules using only causal parents as predictors.
result Modular neural causal models offer robust generalization and fast adaptation, especially in low data regimes.
Hybrid model learns novel handwritten characters better than neural or symbolic models alone.
problem Generating novel yet structured concepts.
method Neuro-symbolic model combining neural networks and probabilistic programs.
result Hybrid model outperforms alternative models in learning and generalizing novel handwritten characters.
New method improves neural network robustness by identifying functions rather than parameters.
problem Neural networks' lack of robustness to distribution shifts.
method Identify the function represented by quadratic networks, not their parameters.
result Obtain robust generalization bounds for neural networks.
Generalization bounds derived for neural ODEs and deep residual networks.
problem Understanding the generalization capability of neural ODEs and deep residual networks.
method Lipschitz-based argument and analogy with deep residual networks.
result A generalization bound involving the magnitude of weight matrix differences.
Neural operators solve families of 2BSDEs efficiently.
problem Solving infinite families of 2BSDEs on bounded domains.
method Introduces a mild generative neural operator model to approximate solutions.
result Solution operators can be approximated by neural operators with polynomial parameters.
New insights into how overfitting affects neural networks' performance.
problem Understanding the generalization of overfitted two-layer neural networks.
method Analyzing the NTK model with ReLU activation, focusing on min ℓ2-norm solutions. result Generalization error of overfitted NTK models approaches a small limiting value, even with infinite neurons and samples.
New bound explains why high-rank neural nets generalize well.
problem Understanding why high-rank neural networks generalize well.
method Using Koopman operators, group representations, and RKHSs, a new Rademacher complexity bound is derived.
result Derives a bound for a wider range of realistic models.
Improved generative models using overparametrized shallow neural networks.
problem Improving generative models for data with hidden low-dimensional structure.
method Using energy-based models with overparametrized shallow neural networks as approximators.
result Models trained in the 'active' regime outperform those in the 'lazy' or kernel regime, leading to better adaptivity to hidden structure.
Customized-GNN generates model-specific for each graph.
problem Graphs in the same dataset have distinct structures.
method Proposes Customized-GNN framework to generate model-specific for each graph.
result Demonstrates effectiveness on various graph classification benchmarks.
New framework generalizes neural network parameters to C∗-algebra for more efficient feature learning.
problem Efficient feature learning and adaptability of neural network models.
method Generalizes neural network parameters to C∗-algebra-valued parameters and combines models continuously. result Shows improved feature learning with limited data using the new framework.
Neural Manifold ODEs improve manifold data modeling.
problem Adapting deep generative models to non-Euclidean spaces.
method Introducing Neural Manifold ODEs for manifold generalization and continuous probability computation.
result Improves density estimation and downstream tasks on arbitrary manifolds.
Paper proposes GrokTransfer to eliminate delayed generalization in neural networks.
problem Delayed generalization in neural networks, compromising predictability and efficiency.
method Trains a smaller, weaker model to reach a nontrivial test performance, then uses its learned input embedding to initialize the stronger model.
result GrokTransfer enables the target model to generalize directly without delay, across various tasks.
Neural model with parameterized algorithms improves graph CO problem solving.
problem Solving NP-hard graph combinatorial optimization problems efficiently and accurately.
method Combining neural models and parameterized algorithms to identify and handle hard and easy parts of CO instances.
result Framework produces superior solution quality and out-of-distribution generalization.
Study challenges neural models in compositional learning tasks.
problem Challenges in neural models for compositional and relational learning.
method Introduced ConceptWorld environment for generating images from compositional concepts, tested various neural architectures.
result Neural models struggle with longer compositional chains and substitutivity tests.
New algorithm explains neural network extrema for better model generalization.
problem Understanding and improving neural network generalization.
method Dynamic extremum mapping and solving linear equations.
result Number of extrema correlates with model parameters, and new algorithm simplifies gradient issues.
Neural model learns efficient, general algorithms for various problems.
problem Learning efficient algorithms that generalize well.
method Carefully designed neural model with imitation and reinforcement learning.
result Neural model outperforms custom solutions on sorting and knapsack problems.
New models improve machine learning accuracy and transparency in finance.
problem Black-box machine learning models lack interpretability in regulated industries.
method Introducing generalized groves of neural additive models with clear feature categories and interactions.
result Generalized groves of neural additive models achieve high accuracy with predominantly linear and sparse nonlinear components.
Enhances non-life insurance pricing models using transformer models.
problem Improving predictive power of non-life insurance pricing models.
method Enhances actuarial non-life models with transformer models for tabular data.
result Transformer models outperform benchmark models in claim frequency prediction.
Generative neural samplers estimate quantum spin system properties.
problem Estimating observables for quantum spin systems.
method Autoregressive models using Suzuki-Trotter transformation.
result Results for energy, specific heat, and susceptibility are in good agreement with Monte Carlo methods.
DDMI generates high-quality INRs by adapting positional embeddings.
problem Existing INR generative models fail to produce high-quality representations.
method DDMI uses adaptive positional embeddings and a D2C-VAE to enhance expressive power.
result DDMI outperforms existing models across multiple modalities and datasets.
Generative modeling on metric graphs using neural optimal transport
problem Deep generative modeling for continuous probability distributions on metric graphs
method Embedding graph into smooth ambient space, solving entropic Kantorovich problem, projecting back onto graph
result Generator is graph-supported