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.
It is well-known that neural networks are computationally hard to train. On the other hand, in practice, modern day neural networks are trained efficiently using SGD and a variety of tricks that include different activation functions (e.g. ReLU), over-specification (i.e., train networks which are larger than needed), a…
Improved neural network approximates analytic and L^p functions efficiently.
problem Efficiently approximating analytic and L^p functions using neural networks.
method Three-dimensional ReLU network architecture for sawtooth functions, improving approximation rates.
result Substantially improved exponential approximation rates for analytic functions and general L^p functions.
Rational neural networks approximate functions more efficiently with less depth.
problem Choosing optimal nonlinear activation functions in neural networks.
method Rational activation functions with optimal bounds and efficiency proofs.
result Rational neural networks approximate smooth functions more efficiently than ReLU networks with exponentially smaller depth.
Meta-learning neural networks to solve diverse PDEs efficiently.
problem Efficiently solving new PDE problems with minimal training.
method Neural network meta-learning of PDE problem representations.
result Meta-learned neural networks predict PDE solutions with high accuracy.
Graph Metanetworks process diverse neural architectures efficiently.
problem Processing diverse neural architectures efficiently.
method Builds metanetworks using graph neural networks to process graphs representing input neural networks.
result Proves GMNs are expressive and equivariant to parameter permutation symmetries.
Taking inspiration from biological evolution, we explore the idea of "Can deep neural networks evolve naturally over successive generations into highly efficient deep neural networks?" by introducing the notion of synthesizing new highly efficient, yet powerful deep neural networks over successive generations via an ev…
Efficient PI for neural networks without distributional assumptions.
problem No distributional assumptions for efficient predictive inference.
method Differential privacy and linear approximation for leave-one-out models.
result Rigorous coverage guarantees with reduced computation.
Neural network MCMC sampler maximizes proposal entropy for efficient sampling.
problem Inefficient sampling from complex probability distributions.
method Proposes a neural network MCMC sampler that maximizes proposal entropy.
result Significantly higher efficiency in various sampling tasks.
Improved sample efficiency with normalized RBF kernels in neural networks.
problem Learning more with less data in deep learning models.
method Two-phase method to train neural networks with normalized RBF kernels as output layer.
result Normalized RBF kernel networks achieve higher sample efficiency, compactness, and separability.
Bayesian neural networks improve likelihood-free inference efficiency.
problem Efficient parameter inference from simulation models with uncertainty.
method Bayesian neural networks for summary statistics, adaptive sampling.
result More robust and efficient posterior estimation.
Examines learning efficiency in neural networks and related models.
problem Analyzing efficiency in deep learning models with singular learning coefficients.
method Examined learning coefficients in neural networks and three-layer neural networks with ReLU units.
result Extended results to include Softmax function, providing a broader understanding of learning efficiency.
Review of efficient neural networks for TinyML on resource-constrained devices.
problem Resource constraints on ultra-low power MCUs for deep learning models.
method Model compression, quantization, low-rank factorization, model pruning, hardware acceleration, algorithm-architecture co-design.
result Optimized neural network architectures for minimal resource utilization on MCUs.
Neural networks and deep learning are changing the way that artificial intelligence is being done. Efficiently choosing a suitable network architecture and fine-tune its hyper-parameters for a specific dataset is a time-consuming task given the staggering number of possible alternatives. In this paper, we address the p…
Deep networks can learn functions approximated by shallow networks, but not all functions.
problem The learnability of functions by deep neural networks and the approximation capacity of simpler classes.
method Study the connection between learnability and approximation capacity of functions by deep neural networks and simpler classes.
result A necessary condition for a function to be learnable by deep neural networks is to be approximable by shallow networks.
Neural architecture search (NAS) has been proposed to automatically tune deep neural networks, but existing search algorithms, e.g., NASNet, PNAS, usually suffer from expensive computational cost. Network morphism, which keeps the functionality of a neural network while changing its neural architecture, could be helpfu…
Develops a binarized GNN for more efficient graph embeddings.
problem Real-valued GNN parameters limit efficiency and scalability.
method Integrates binarization into GNN-based graph embedding approaches.
result Binarized graph neural network (BGN) achieves state-of-the-art performance with significant efficiency gains.
FastCPH efficiently predicts survival times using neural networks.
problem Improving efficiency and accuracy of Cox proportional hazards models in neural networks.
method Developed FastCPH, a linear-time method supporting Breslow and Efron methods for tied events.
result Outperforms existing CoxPH approaches and selects useful covariates.
The use of artificial neural networks as models of chaotic dynamics has been rapidly expanding. Still, a theoretical understanding of how neural networks learn chaos is lacking. Here, we employ a geometric perspective to show that neural networks can efficiently model chaotic dynamics by becoming structurally chaotic t…
Proposes RBGP framework for efficient block sparse neural networks.
problem Efficiently exploit structured sparsity patterns for sparse neural networks on GPU.
method Uses Ramanujan Bipartite Graph Product to generate structured multi-level block sparse neural networks.
result Achieves 5-9x and 2-5x runtime gains over unstructured and block sparsity patterns respectively, while maintaining accuracy.
We show that a collection of Gaussian mixture models (GMMs) in Rn can be optimally classified using O(n) neurons in a neural network with two hidden layers (deep neural network), whereas in contrast, a neural network with a single hidden layer (shallow neural network) would require at least O(exp(n)) neurons …
This paper uses neural networks to predict stock prices more accurately.
problem Current stock analysis methods are inaccurate.
method Dynamic neural networks to identify stock price patterns.
result Neural networks outperform traditional stock analysis methods.
Securely trains neural networks remotely with deep learning's flaws.
problem Secure and efficient training of neural networks over unsecured channels.
method Leverages deep learning's weaknesses for secure training.
result Efficient and secure training of neural networks remotely.
A new neural network for efficient density estimation.
problem Efficient density estimation for high-dimensional data.
method Triangular neural network implementation of neural autoregressive flow (NAF).
result Achieves state-of-the-art bits-per-dimension indices on MNIST and CIFAR-10.
In this work we perform outlier detection using ensembles of neural networks obtained by variational approximation of the posterior in a Bayesian neural network setting. The variational parameters are obtained by sampling from the true posterior by gradient descent. We show our outlier detection results are comparable …
This work improves sample efficiency in neural function approximation for reinforcement learning.
problem Improving sample efficiency in reinforcement learning with neural function approximation.
method Study of function approximation with two-layer neural networks (ReLU and polynomial activations) under generative and realizability models.
result Significant improvement in sample complexity compared to linear methods.
New KWS neural networks improve accuracy and power efficiency.
problem Maximizing accuracy and power efficiency in KWS systems.
method Hardware Aware Training (HAT) for LMU-based neural networks.
result Achieved state-of-the-art accuracy and low parameter counts.
Proposes SE(3) equivariant graph neural networks with local frames for efficient geometric approximation.
problem Equivariance in deep learning for arbitrary transformations, especially in physics.
method Introduces SE(3) equivariant graph neural networks with complete local frames to efficiently approximate geometric quantities.
result Achieves best or competitive performance in Newton mechanics modeling and equilibrium molecule conformation generation.
Simplified NAS for GNN architectures improves efficiency and expressiveness.
problem Efficient and effective discovery of optimal GNN architectures.
method SNAG framework with a novel search space and reinforcement learning.
result SNAG framework outperforms human-designed and existing NAS methods.
Efficient neural network for audio source separation.
problem End-to-end general purpose audio source separation.
method SuDoRMRF structure with simple one-dimensional convolutions for feature aggregation.
result SuDoRMRF achieves high quality audio source separation with minimal computational resources.
Monotone neural networks can approximate and interpolate functions efficiently.
problem Understanding the efficiency and expressiveness of monotone neural networks.
method Solving the monotone interpolation problem using depth-4 networks and comparing size bounds with arbitrary networks.
result Monotone neural networks can approximate and interpolate functions efficiently, but may require exponential size in high dimensions.
We derive scaling laws for optimizing neural networks in hardware.
problem Optimizing the large parameter space of neural networks in hardware.
method Analytical derivation of scaling laws for Coordinate Descent optimization.
result Convergence is exponential and scales linearly with the number of neurons.
Efficiently quantifies uncertainty in subsurface flow using neural networks guided by theory.
problem Uncertainty in dynamic subsurface flow predictions.
method Theory-guided Neural Network (TgNN) for efficient uncertainty quantification.
result TgNN surrogate improves efficiency of uncertainty quantification compared to MC method.
GENNI visualises neural network symmetries for better identifiability.
problem Identifying functionally equivalent parameters in neural networks.
method Proposes GENNI, an algorithm to efficiently visualise equivalence classes.
result Allows better exploration of identifiability questions in neural networks.
Delta Variances efficiently estimate epistemic uncertainty in neural networks.
problem Mitigating uncertainty in neural networks with limited data.
method Delta Variances, a computationally efficient algorithm for epistemic uncertainty quantification.
result Empirically competitive results with a single gradient computation.
Neural network approximates weakly efficient frontier of convex vector optimization problems.
problem Approximating the weakly efficient frontier of convex vector optimization problems.
method Designing a neural network architecture to approximate the weakly efficient frontier of convex vector optimization problems (CVOP) satisfying Slater's condition.
result The proposed algorithm effectively approximates the true weakly efficient frontier of CVOPs, even for large problems.
New neural network designs learn contact dynamics efficiently.
problem Learning contact dynamics in robotics from noisy data.
method Physically structured neural networks.
result Data-efficient learning of discontinuous contact events.
Neural networks can learn from higher-order cumulants efficiently, requiring quadratic samples.
problem Learning from higher-order cumulants in high-dimensional data.
method Spiked cumulant model, polynomial time algorithms, neural networks, random features.
result Neural networks require quadratic samples to learn from higher-order cumulants efficiently, while random features require more samples.
The success of deep neural networks in many real-world applications is leading to new challenges in building more efficient architectures. One effective way of making networks more efficient is neural network compression. We provide an overview of existing neural network compression methods that can be used to make neu…
Deep quantum neural networks applied to finance for efficient risk management.
problem Efficiently solving numerical problems in finance, especially risk management.
method Application of deep quantum neural networks to finance, focusing on implied volatilities, option prices, and Greeks.
result Deep quantum neural networks can compute Greeks analytically and efficiently solve financial numerical problems.
Proposes a neural network for contextual regression.
problem Improving model efficiency and interpretability in regression with contextual features.
method Simple contextual neural network (SCtxtNN) that separates context identification from context-specific regression.
result SCtxtNN achieves lower excess mean squared error and more stable performance than feed-forward neural networks.
NeuroMatch efficiently matches subgraphs in large graphs using neural networks.
problem Determining the presence and location of a query graph in a large target graph.
method NeuroMatch decomposes graphs into subgraphs, embeds them using graph neural networks, and matches them directly in the embedding space.
result NeuroMatch is 100x faster and 18% more accurate than existing methods.
Physics-informed neural networks simulate radiative transfer efficiently.
problem Simulating radiative transfer accurately and efficiently.
method Physics-informed neural networks trained to minimize radiative transfer equations.
result PINNs provide an easy-to-implement, robust, and accurate method for radiative transfer simulation.
NNs can learn efficient algorithms for certain problems.
problem Learning efficient algorithms for specific problems.
method Recurrent Convolutional Neural Networks (RCNNs) that learn efficiently.
result RCNNs can learn as well as efficient algorithms described by a constant-sized program.
New neural network approach solves Poisson equations efficiently.
problem Approximating solutions to Poisson equations with Dirichlet boundary conditions.
method Using shallow ReLUα-networks to solve Laplace operator equations. result Neural networks can approximate solutions to the Laplace operator with Dirichlet boundary conditions efficiently.
Wavelets help compress neural networks efficiently.
problem Efficiently compressing linear layers in neural networks.
method Learnable wavelet transforms to compress RNNs.
result Wavelet compressed RNNs have fewer parameters and perform competitively.
KM method reduces ConvNet parameters to 9% higher accuracy with minimal additional memory.
problem Expensive memory usage for training ConvNets on embedded devices.
method Kernel Modulation (KM) method that adapts all network parameters for each task.
result KM delivers up to 9% higher accuracy than other parameter-efficient methods.
A promising paradigm for achieving highly efficient deep neural networks is the idea of evolutionary deep intelligence, which mimics biological evolution processes to progressively synthesize more efficient networks. A crucial design factor in evolutionary deep intelligence is the genetic encoding scheme used to simula…