DeepCA combines neural networks with component analysis for improved performance.
problem Limited capacity of shallow component analysis in deep learning.
method Deep Component Analysis (DeepCA) with ADNNs for inference.
result Improved performance on various tasks, including depth prediction.
TSSM splits neural networks for parallel training with minimal accuracy loss.
problem Accuracy degradation in parallel training of deep neural networks.
method TSSM reformulates alternating minimization to achieve parallelism with minimal accuracy loss.
result TSSM achieves significant speedup without accuracy loss on multiple datasets.
SAG is a scalable method for adversarial attacks on GNNs.
problem Scalability and robustness of GNNs to adversarial attacks.
method Decomposing large graphs into smaller partitions, using ADMM for optimization.
result SAG reduces computation and memory overhead for large graphs.
Improved neural network training with ADMM for hardware compatibility.
problem Training scalable and parallelizable neural networks.
method Alternating Direction Method of Multipliers (ADMM) combined with iterative least-square methods.
result Achieved significant accuracy improvements over SGD and Adam.
AGF explains feature learning in neural networks through alternating steps.
problem Understanding what features neural networks learn and how they learn them.
method AGF is an algorithmic framework that approximates the dynamics of feature learning in two-layer networks.
result AGF provides a unified framework to understand feature learning in neural networks, matching experimental results across various architectures.
Direct neural network calibration outperforms indirect method for rough volatility models.
problem Calibrating volatility models with neural networks.
method Comparison of direct and indirect neural network approaches for volatility model calibration.
result Direct approach outperforms indirect approach for rough volatility models.
Hypermodels improve exploration efficiency and accuracy.
problem Efficiently approximating Thompson sampling with large ensembles.
method Introducing hypermodels as a generalization of ensembles, including linear and neural network hypermodels.
result Hypermodels enable more accurate exploration and performance gains over Thompson sampling.
Photonic co-processor speeds up training of large neural networks.
problem Training large neural networks with backpropagation is inefficient and communication is a bottleneck.
method Direct Feedback Alignment (DFA) with a photonic accelerator.
result Photonic accelerator can compute random projections with trillions of parameters.
Optical co-processor speeds up neural network training.
problem Expensive training costs for large neural networks.
method Direct feedback alignment, optical error projection.
result Optical co-processor trains neural networks for handwritten digit recognition.
Adversaries reprogram text classification models without changing the original network.
problem Reprogramming neural networks trained on discrete input spaces like text classification.
method Context-based vocabulary remapping model for white-box and black-box settings.
result Successfully repurposed various text-classification models for new tasks.
The paper tackles learning varying DAG structures based on contextual features.
problem Learning a single DAG for the entire population from observational data.
method A neural network that maps contextual features to a weighted adjacency matrix of a DAG, with a projection layer to ensure acyclicity.
result The new approach can recover context-specific DAGs where existing methods fail.
A new tensor-based layer reduces neural network dimensions without losing important features.
problem Reducing dimensionality in tensor-structured feature data for deep neural networks.
method TensorProjection layer that projects input tensors into output tensors with reduced dimensions through mode-wise projections.
result The TensorProjection layer outperforms traditional downsampling methods in tasks like medical image classification and segmentation.
Innovative PGMs match neural networks, revealing precise approximations during forward propagation.
problem Lack of precise semantics and probabilistic interpretation in neural networks.
method Constructing infinite tree-structured PGMs that correspond to neural networks.
result DNNs perform precise approximations of PGM inference during forward propagation.
Study shows Direct Feedback Alignment fails to offer more efficient scaling than backpropagation.
problem Understanding and optimizing training methods for neural networks.
method Use of scaling laws to compare Direct Feedback Alignment (DFA) and backpropagation.
result DFA fails to offer more efficient scaling than backpropagation.
This work improves neural network calibration using explicit regularization.
problem Improving predictive uncertainty in neural networks.
method Introducing a probabilistic calibration measure and exploring explicit regularization techniques.
result Explicit regularization improves log-likelihood and predictive uncertainty.
Graph neural networks speed up nonnegative matrix factorization.
problem Efficiently factorize nonnegative matrices for various applications.
method Developed a graph neural network that combines bipartite self-attention with ADMM updates.
result Significant acceleration achieved in nonnegative matrix factorization.
Paper presents an ADMM-based approach to efficiently integrate quadratic programming layers into neural networks.
problem Integrating quadratic programs into neural networks for optimization.
method An ADMM-based network layer architecture for solving quadratic programs efficiently.
result The ADMM layer is approximately an order of magnitude faster than existing methods for medium scaled problems.
Develops neural network for directed hypergraphs for node classification.
problem Irregular data structure, particularly directed graphs.
method Directed hypergraph neural network and semi-supervised learning method.
result Novel directed hypergraph neural network achieves highest accuracies on node classification tasks.
DANTE trains neural networks using an alternating minimization approach.
problem Training neural networks with mixed activation functions efficiently.
method DANTE uses alternating minimization and quasi-convexity to handle neural networks with both differentiable and non-differentiable activation functions.
result DANTE-trained neural networks are promising and competitive in terms of quality and training speed.
Deep neural network improves PET image quality using inter-patient information.
problem Challenges in PET image reconstruction due to ill-posedness and limited photon detection.
method Trained a deep residual convolutional neural network in an iterative PET image reconstruction framework using ADMM.
result Proposed method outperforms neural network denoising and conventional methods in quantification.
Characterizes a specific type of neural network for alternating group equivariance.
problem Understanding and characterizing neural networks with alternating group equivariance.
method Characterization of all possible An-equivariant neural networks using tensor powers of Rn. result Found a basis of matrices for learnable, linear An-equivariant layer functions. Graph neural networks improve molecular property prediction.
problem Efficiently predicting molecular properties with high accuracy and scalability.
method Gated Graph Recursive Neural Networks (GGNN) with skip connections.
result GGNN achieves state-of-the-art performance on molecular property prediction benchmarks.
Direct feedback alignment reduces data movement in neural networks.
problem Efficiency and energy-efficiency in training large neural networks.
method Sparse feedback matrix for local learning, reducing data movement and compute.
result Orders of magnitude improvement in data movement and 2x improvement in multiply-and-accumulate operations.
Proposes a neural network method to correct residual distortions in coordinate transformations.
problem Nonlinear and spatially dependent distortions in coordinate transformation models.
method Residual-based neural network approach focusing on systematic distortions.
result The method improves accuracy and stability in challenging conditions.
This work connects neural network training to convex optimization via the NTK.
problem Understanding and optimizing neural network training via convex programs.
method Interpreting gated ReLU network as MKL, showing NTK equivalence, and improving weights.
result The NTK cannot perform better than the optimal MKL kernel on the training set.
A new algorithm trains deep neural networks by adding neurons greedily.
problem Training deep neural networks efficiently and effectively.
method Neuron Pursuit (NP) algorithm, which alternates between neuron addition and loss minimization.
result The algorithm can train deep neural networks efficiently and effectively.
Alt-GNNs improve travel mode choice modeling by integrating graph neural networks with GEV models.
problem Capturing alternative dependence in discrete choice models with predefined, symmetric, and uniform dependence.
method Introducing Alternative Graph Neural Networks (Alt-GNNs) that embed alternative dependence within a unified framework.
result Alt-GNNs significantly improve predictive performance over benchmark models in travel mode choice datasets.
RNNs trained on head direction task mimic brain's compass and shifter neurons.
problem Modeling brain's head direction system using neural networks.
method Optimized recurrent neural networks trained on angular velocity integration.
result RNNs naturally emerge with compass and shifter neuron-like properties.
Neural network model predicts alternating event-free periods.
problem Dynamic prediction of alternating recurrent events with statistical nuance.
method Developed an online dynamic prediction framework using neural network theory.
result Outstanding performance in predicting alternating recurrent event-free time.
The paper explores how symmetries and noise in SGD influence parameter dynamics.
problem Understanding the dynamics of parameter updates in SGD with symmetries.
method Proved the existence of noise equilibria and showed their role in balancing gradient noise.
result Gradient noise creates a systematic motion of parameters to a unique fixed point, called noise equilibria.
A new KAN variant uses sinusoidal activations to approximate functions.
problem Approximating multivariable functions using neural networks.
method Replacing inner and outer functions in Kolmogorov-Arnold representation with weighted sinusoidal functions.
result The new KAN variant outperforms fixed-frequency Fourier transform and achieves comparable performance to MLPs.
Low complexity decentralized neural net with centralized performance.
problem Training large neural networks in distributed nodes without data sharing.
method Layer-wise learning using ADMM for low complexity and centralized performance.
result Equivalent learning performance to centralized training in distributed nodes.
Study reveals how neural network architectures bias their learning based on feature directions.
problem Understanding how neural network architectures bias their learning based on feature directions.
method Defined neural anisotropy directions (NADs) to encapsulate the directional inductive bias of architectures and provided an efficient method to identify them.
result NADs characterize the features used by CNNs to discriminate between different classes for the CIFAR-10 dataset.
Paper introduces a new optimisation method combining NG and Hessian Free for sequence training.
problem Overfitting and inefficiency in training DNNs with sequence criteria.
method Combines Natural Gradient and Hessian Free methods for better path traversal on parameter manifold.
result Achieves larger reductions in WER and lower WER compared to NG and HF methods.
Paper finds conditions for benign overfitting in neural networks.
problem Benign overfitting in leaky ReLU two-layer neural networks.
method Established directional convergence and classification error bounds.
result Benign overfitting occurs with high probability on mixture data.
New ADMM algorithm tackles nonconvex constraints from GANs for faster learning.
problem Learning with nonconvex constraints from neural network outputs.
method Linearized ADMM algorithm for convex objective with nonconvex constraint.
result Efficient algorithm with provable convergence rates for specific neural network architectures.
Neural networks with DAGs show linearity as width increases.
problem Understanding linearity in neural networks with arbitrary DAG structures.
method Analyzing the transition to linearity in networks with arbitrary DAGs, characterizing width by minimum in-degree.
result General neural networks with DAGs exhibit linearity as width approaches infinity.
MLDS dataset reveals hidden model behavior via weight-space analysis.
problem Neural networks' opacity makes them hard to evaluate.
method Presented MLDS dataset of trained neural networks.
result Weight-space analysis reveals meaningful divergence with small changes in training data.
The paper studies neural networks' convergence near origin and saddle points.
problem Directional convergence of neural networks near small initializations and saddle points.
method Gradient flow dynamics analysis of two-homogeneous neural networks.
result Neural networks' weights approximately converge in direction to KKT points for small initializations.
INDEQS: A Graph-Based Neural Controlled Differential Equation Framework for Forecasting
problem Forecasting time series with neural networks
method Incorporating prior knowledge of a directed graph
result Outer informedness consistently improves forecasting accuracy
PyTorch Geometric Signed Directed fills the gap for GNNs on signed and directed graphs.
problem Lack of unified software packages for GNNs on signed and directed networks.
method Developed a software package with GNN models, synthetic and real-world data, and evaluation metrics.
result Demonstrates the effectiveness of the implemented methods through experiments.
New method trains neural networks with local error signals, outperforming global methods.
problem Training neural networks with global error signals.
method Layer-wise training with local error signals.
result Layer-wise training with local error signals can approach state-of-the-art performance.
Extract symbolic models from deep learning with inductive biases.
problem Interpreting and discovering physical principles from deep neural networks.
method Introduce strong inductive biases in GNNs, encourage sparse latent representations, apply symbolic regression.
result Extracted symbolic equations from neural networks, including known force laws and new analytic formulas.
Predicts short-term futures contract direction using neural networks and order flow data.
problem Challenges in predicting short-term directional movement of futures contracts.
method Engineering features from technical analysis, order flow, and order-book data; training a Tabnet neural network.
result Achieved an accuracy of 0.601 in predicting directional change on the Silver Futures Contract.
Spatial information is not always necessary for spatio-temporal models.
problem The necessity of including spatial information in spatio-temporal models.
method Comparison of spatial agnostic neural networks with state-of-the-art models on ten datasets.
result Spatial information is not always needed in most spatio-temporal models.
Study shows directional convergence for neural networks under spherical symmetry.
problem Learning linear predictors with neural networks under spherically symmetric data.
method Analysis of gradient flow and gradient descent for two-layer and deep linear networks.
result Directional convergence guarantees with exact convergence rate for specific network architectures.
New Bayesian neural network model improves performance and compresses networks.
problem Improving predictive performance and compressing neural networks.
method Proposes a new variational family with radial and directional components.
result Improves predictive performance and yields compressed networks.
A new method constrains deep networks during fine-tuning to improve generalization.
problem Improving generalization of fine-tuned deep networks.
method A neural network generalisation bound based on distance from initial weights constrains the hypothesis class to a small sphere.
result Empirical evaluation shows superior generalization performance compared to existing methods.