The paper investigates how target normalization and momentum affect dying ReLUs in neural networks.
problem Understanding and mitigating the dying ReLU problem in neural networks.
method Empirical analysis and theoretical modeling of a discrete-time linear autonomous system.
result Target variance plays a crucial role in the dying ReLU phenomenon, and momentum exacerbates this issue.
Deep ReLU networks can be simplified to a three-layer model.
problem Understanding the behavior of deep neural networks.
method Constructive proof and algorithm to transform deep networks into shallow ones.
result Deep ReLU networks can be represented by a simpler three-layer structure.
Bayesian ReLU nets fix asymptotic overconfidence with infinite features.
problem Bayesian ReLU nets can be asymptotically overconfident far from training data.
method Extend finite ReLU BNNs with infinite ReLU features via a Gaussian process.
result The resulting model is asymptotically maximally uncertain far from the data.
Single ReLU neuron's gradient dynamics reveal support vectors as key to generalization.
problem Understanding the generalization capability of ReLU networks.
method Examined gradient flow dynamics and support vectors in single ReLU neuron training.
result Support vectors play a crucial role in the generalization of ReLU networks.
Random ReLU features are shown to be a universally consistent learning algorithm but struggle with complex functions.
problem Approximating complex functions with random ReLU features.
method Study of random ReLU features through their RKHS and composition of functions.
result Random ReLU features can efficiently approximate complex functions but not as well as multi-layer ReLU networks.
Study shows efficient neural network approach for stochastic bandits.
problem Optimizing decisions in uncertain environments with neural network models.
method OFU-ReLU algorithm that balances exploration and exploitation, using a transformed feature space.
result Achieves i l d e O ( T ) ilde{O}(\sqrt{T}) i l d e O ( T ) regret guarantee for stochastic bandits with ReLU neural networks. PHP connects to ReLU neural networks for scalable Bayesian inference.
problem Scalability and Bayesian inference in two-layer ReLU neural networks.
method PHP with Gaussian prior, decomposition propositions, annealed sequential Monte Carlo.
result PHP provides an alternative scalable representation for two-layer ReLU neural networks.
The paper explores how ReLU DNNs can represent MPC policies and vice versa.
problem Representing MPC policies as ReLU DNNs and vice versa.
method Developed an approximate method for identifying input-space in ReLU nets resulting in PWA functions over polyhedral regions. Studied inverse multiparametric linear or quadratic programs for reconstruction of constraints and cost functions given a PWA function.
result Identification and representation of MPC policies as ReLU DNNs and vice versa.
Transformers use ReLUs to approximate softmax efficiently.
problem Analyzing resource usage in softmax transformer models.
method Translating ReLU approximation results to softmax attention mechanisms.
result Economic resource bounds for softmax attention mechanisms.
A new neural network model for optimal treatment assignment.
problem Learning optimal treatment assignment from observational data.
method Prescriptive ReLU network (P-ReLU) model that balances performance and interpretability.
result P-ReLU can be converted into an equivalent prescriptive tree with hyperplane splits for interpretability.
ReLU units can 'die' in neural networks, causing slower convergence.
problem ReLU units sometimes produce near-zero outputs during training.
method Simulation and statistical analysis of a simplified ReLU unit model.
result Activation probability decreases as training progresses, leading to slower convergence.
Study on ReLU regression with Massart noise, achieving exact parameter recovery.
problem Efficiently fitting ReLUs to data in the presence of Massart noise.
method Developed an efficient algorithm for exact parameter recovery under mild assumptions.
result Achieved exact parameter recovery in ReLU regression with Massart noise.
This study connects ReLU neural networks to toric geometry to analyze function realization.
problem Determining which continuous piecewise linear functions can be realized by ReLU neural networks.
method Established a connection between toric geometry and ReLU neural networks, defining key structures like the ReLU fan, toric variety, and Cartier divisor.
result Proved a criterion for functions realizable by unbiased shallow ReLU networks using intersection numbers.
ReLU networks learn simple models even with many parameters, overcoming traditional wisdom.
problem Generalization of overparameterized neural networks.
method Convex optimization and sparse recovery perspective applied to two-layer ReLU networks with standard weight decay.
result ReLU networks learn simple models that explain the data, analogous to sparse recovery in compressed sensing.
The paper proves deep ReLU networks can die and proposes a new initialization method to prevent it.
problem Dying ReLU neurons in deep neural networks.
method The paper rigorously proves the dying ReLU problem and proposes a new randomized asymmetric initialization method.
result The new initialization method effectively prevents the dying ReLU problem.
Paper analyzes GLM-tron for high-dimensional ReLU regression, providing upper and lower bounds.
problem Learning a single ReLU neuron in high-dimensional settings with overparameterization.
method Perceptron-type algorithm GLM-tron, with finite-sample analysis.
result Sharp characterization of high-dimensional ReLU regression problems via GLM-tron, contrasting with SGD.
The paper examines topological features of ReLU networks and their relation to decision boundaries and training loss.
problem Understanding the topological structure of ReLU neural network activation patterns.
method Polytope decomposition of feature space, Fiedler partition of dual graph, homology computation of cellular decomposition.
result The Fiedler partition of the dual graph correlates with decision boundaries in binary classification tasks, and similar patterns in training loss and polyhedral cell-count emerge in regression tasks.
New method reveals properties of ReLU-networks via invertibility.
problem Understanding the behavior of deep neural networks.
method Deriving a theory on invertibility of ReLU-layers and exploring mechanisms affecting stability.
result Numerical results show characteristic properties of ReLU-networks.
This study examines how reward scaling impacts non-saturating ReLU networks in reinforcement learning.
problem The impact of reward scaling on non-saturating ReLU networks in reinforcement learning.
method Proposes an Adaptive Network Scaling framework to find a suitable reward scale during learning.
result Empirical studies justify the effectiveness of the Adaptive Network Scaling framework.
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.
Large deviation principle for deep neural networks with ReLU activation.
problem Understanding the behavior of deep neural networks with ReLU activation.
method Proving a large deviation principle for networks with Gaussian weights and ReLU activation functions.
result Simplified expressions and power-series expansions for the ReLU case.
The paper reveals how clustering in ReLU networks enhances interpretability.
problem Improving interpretability of deep learning models.
method Clustering of ReLU neuron patterns to reveal underlying affine maps.
result The network's predictions can be explained by feature importance within clusters.
A new method for optimizing regression problems with ReLU units converges.
problem Optimizing regression problems involving ReLU units in large language models.
method Introduced a greedy algorithm based on approximate Newton method, proving convergence in terms of the distance to optimal solution.
result The method converges in the sense of the distance to optimal solution under certain assumptions.
Novel approach analyzes ReLU networks' training dynamics and proposes GmP for improved optimization.
problem Stochastic optimization instability in ReLU networks impedes convergence and generalization.
method Characteristic activation boundaries analysis and Geometric Parameterization (GmP) technique.
result GmP resolves instability, leading to better optimization, convergence, and generalization.
Paper improves confidence intervals and variance estimation for deep learning models.
problem Improving confidence intervals and variance estimation in deep learning models.
method Residual-based framework for conditional variance estimation; robust bootstrap procedure for confidence intervals.
result First non-asymptotic bounds for variance estimation using ReLU networks.
Researchers use statistical physics to model neural network learning dynamics.
problem Understanding the learning dynamics of ReLU neural networks.
method Developed a system of differential equations using statistical physics techniques.
result ReLU networks exhibit distinct learning behavior compared to sigmoidal networks.
This paper simplifies deep ReLU networks into local linear models for better interpretability.
problem Limited transparency and interpretability of deep neural networks, especially ReLU networks.
method Local linear representation and equivalent set of local linear models (LLMs).
result Simplified deep ReLU networks for better interpretability and diagnostics.
Hard to learn ReLU with Gaussian data, but can approximate efficiently.
problem Learning a ReLU with Gaussian marginals under arbitrary labels.
method Proved hardness and developed an efficient approximation algorithm.
result Efficient approximation algorithm for best-fitting ReLU with error O ( o p t 2 / 3 ) O(\mathsf{opt}^{2/3}) O ( opt 2/3 ) . The paper analyzes deep ReLU CNNs' approximation properties in 2D space.
problem Establishing L 2 L^2 L 2 approximation properties for deep ReLU CNNs. method Analysis based on decomposition theorem for convolutional kernels, properties of ReLU activation, and connections with one-hidden-layer ReLU NNs.
result Universal approximation theorem for deep ReLU CNNs with classic structure.
Quantile regression with ReLU networks achieves minimax rates for various function types.
problem Estimating quantiles from covariates with neural networks.
method Quantile regression with rectified linear unit (ReLU) neural networks.
result ReLU networks achieve minimax rates for broad collections of function types.
Proves existence of optimal shallow neural networks with ReLU activation.
problem Proving the existence of optimal shallow feedforward networks with ReLU activation.
method Proves existence of global minima in the loss landscape for continuous target functions using shallow feedforward neural networks with ReLU activation.
result Existence of global minima in the loss landscape for shallow feedforward networks with ReLU activation.
Gradient descent and SGD can converge to max-margin directions in ReLU models.
problem Understanding the implicit bias of gradient methods in ReLU models.
method Characterization of loss function landscape, analysis of GD and SGD convergence, exploration of multi-neuron network learning.
result Gradient descent and SGD can converge to max-margin directions in ReLU models.
Gradient descent learns ReLU functions with non-zero bias efficiently.
problem Learning ReLU functions with non-zero bias under Gaussian distributions.
method Gradient descent starting from random initialization.
result Gradient descent achieves near-optimal error with high probability.
The paper studies ReLU layers, introducing new tools to understand their singular values and Gaussian mean width.
problem Understanding the role of ReLU layers in neural networks and their impact on network performance.
method Introducing ReLU singular values and Gaussian mean width of operators to study ReLU layers.
result ReLU singular values and Gaussian mean width provide metrics for distinguishing correctly and incorrectly classified data.
Deep neural networks classify unbounded Gaussian mixture data without dimensionality issues.
problem Binary classification of unbounded Gaussian mixture data.
method Deep ReLU neural networks with non-asymptotic upper bounds and convergence rates.
result Deep ReLU networks can classify unbounded Gaussian mixture data without dimensionality constraints.
This article concerns the expressive power of depth in neural nets with ReLU activations and bounded width. We are particularly interested in the following questions: what is the minimal width w min ( d ) w_{\text{min}}(d) w min ( d ) so that ReLU nets of width w min ( d ) w_{\text{min}}(d) w min ( d ) (and arbitrary depth) can approximate any continuous functio…
Injectivity of ReLU networks is characterized for generative models and inverse problems.
problem Injectivity in ReLU networks for generative models and inverse problems.
method Layerwise analysis, worst-case Lipschitz constants, differential topology, random projections.
result Global injectivity of ReLU networks requires expansivity between 3.4 and 10.5 for Gaussian matrices.
ReLU activations lead to smoother learning curves compared to sigmoidal activations in neural networks.
problem Comparing the performance of ReLU and sigmoidal activations in neural networks.
method Analytical computation of learning curves in shallow networks with different activation functions.
result ReLU networks exhibit continuous transitions in performance, while sigmoidal networks show discontinuous transitions.
Modified ReLU networks improve regression estimation rates.
problem Regression estimation with smooth functions.
method Using modified ReLU neural networks with specific weight modifications.
result Empirical risk minimizers achieve minimax rate of prediction.
Proves SQ lower bounds for learning two-hidden-layer neural networks.
problem Learning two-hidden-layer ReLU networks with Gaussian inputs.
method Refined lifting procedure to reduce Boolean PAC learning to Gaussian.
result Superpolynomial SQ lower bounds for Gaussian inputs.
Improved bounds on neural network expressivity.
problem Understanding neural network expressivity and approximation capabilities.
method Improved bounds on the maximal number of linear regions of ReLU-networks.
result New insights into the expressivity of neural networks.
Optimal rates for shallow ReLU networks in nonparametric regression.
problem Approximating smooth and non-smooth functions with shallow ReLU networks.
method Analysis of shallow ReLU k ^k k neural networks, using variation norms and deep learning theory. result Optimal approximation rates for shallow ReLU networks in nonparametric regression.
New activation function BrownianReLU improves LSTM network performance on financial time series.
problem Gradient instability in noisy financial time series data.
method Introduces BrownianReLU, a stochastic activation function based on Brownian motion.
result Significantly improved predictive accuracy and generalization on financial datasets.
Paper tackles learning ReLU networks for binary classification with linearly separable data.
problem Learning two-layer ReLU networks for binary classification with linearly separable data.
method Stochastic gradient descent (SGD) algorithm with random noise perturbation.
result Proves global optimality of SGD for training any single-hidden-layer ReLU network.
Geometric insights reveal transferable adversarial directions across classifiers and models.
problem Adversarial perturbations transfer between different inputs, models, and architectures.
method Geometric analysis of linear classifiers and two-layer ReLU networks.
result Transferable adversarial directions exist for linear separators and ReLU networks with high probability.
The paper proves deep ReLU networks avoid spurious local minima in NTK regime.
problem The existence of spurious local minima in deep ReLU neural networks.
method Theoretical proof under Neural Tangent Kernel regime.
result Deep ReLU networks do not lie in spurious local minima in NTK regime.
Gradient descent converges to minimum Bayes risk for two-layer ReLU networks in mean field regime.
problem Training two-layer ReLU networks using gradient descent in the mean field regime.
method Describes a condition for convergence to minimum Bayes risk, extending previous results to ReLU-activated networks.
result The condition for convergence does not depend on initialization and concerns weak convergence of network realization.
This paper introduces PSI-flatness to better understand ReLU neural networks' flatness and generalization.
problem Existing flatness definitions fail to account for ReLU neural networks' Positively Scale-Invariant (PSI) property.
method Formalizes PSI-flatness on basis path values, proving its relation to generalization.
result Minimums with balanced basis path values are flatter and generalize better.