Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

2845678511,134 · Jun 202019922001200920172026
48 results for regularized neural networks

New algorithm adds Hessian regularization to improve neural network robustness.

problem Improving neural network robustness against adversarial attacks.
method Proposes an efficient algorithm to train neural networks with Hessian operator-norm regularization.
result Hessian operator-norm regularization increases neural network robustness over input gradient regularization.

The paper studies how regularization parameters affect sparsity in deep neural networks.

problem Reducing the complexity of deep neural networks by promoting sparsity.
method Derives 1\ell_1-norm sparsity-promoting models, characterizes sparsity levels, and develops algorithms for selecting optimal regularization parameters.
result Developed algorithms to select regularization parameters for desired sparsity levels in neural networks.

Fiedler regularization uses graph sparsity to improve neural network training.

problem Improving neural network training by respecting graph structure.
method Using the Fiedler value of the neural network's graph as a regularization tool.
result Fiedler regularization outperforms traditional methods like dropout and weight decay.

New regularizer improves neural network robustness and generalization.

problem Ineffective weight decay for networks with homogeneous activation functions.
method Proposes an invariant regularizer to penalize intrinsic weight norms.
result Improves generalization and adversarial robustness on various datasets.

Regularizers change the geometric properties of loss functions in neural networks.

problem Understanding how different regularizers affect the geometric properties of loss functions in neural networks.
method Examined several regularizers, including weight decay, to determine if the regularized loss function becomes Morse.
result For certain regularizers, the regularized loss function becomes Morse, indicating a change in geometric properties.

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.

Fiedler regularization uses spectral graph theory to improve neural network performance.

problem Improving neural network performance by penalizing weights based on connectivity.
method Uses the Fiedler value of the neural network's graph as a regularization tool, providing theoretical and computational methods.
result Demonstrates Fiedler regularization's effectiveness in improving neural network performance.

Regularization plays an important role in generalization of deep neural networks, which are often prone to overfitting with their numerous parameters. L1 and L2 regularizers are common regularization tools in machine learning with their simplicity and effectiveness. However, we observe that imposing strong L1 or L2 reg…

2018-11-20abs ↗pdf ↗

Two new regularization methods improve neural network performance and complexity control.

problem Improving neural network performance and complexity control with correlated or high-dimensional features.
method Two regularization strategies: covariance-aware ridge and covariance-aware lasso.
result Improves predictive performance and complexity control over standard penalties.

The paper explains implicit regularization in hierarchical tensor factorization and deep CNNs.

problem Understanding implicit regularization in complex neural network architectures.
method Theoretical analysis using dynamical systems to overcome challenges in hierarchy.
result Established implicit regularization towards low hierarchical tensor rank, equivalent to locality in CNNs.

Overparametrized neural networks can generalize well with proper regularization.

problem Generalization guarantee for noisy data in overparametrized neural networks.
method Nonparametric analysis of 2\ell_2-regularized GD trajectories.
result Achieving minimax optimal rate of L2L_2 estimation error with 2\ell_2 regularization.

MaxDropout removes most active neurons to prevent overfitting in deep neural networks.

problem Preventing overfitting in deep neural networks.
method MaxDropout removes the most active neurons in each hidden layer to enforce sparsity and prevent overfitting.
result MaxDropout improves neural network performance in image classification and achieves comparable results to existing regularizers.

A neural network solves logistic regression with 1\ell_1 regularization efficiently.

problem Efficiently solving logistic regression with 1\ell_1 regularization due to non-differentiability of 1\ell_1 norm.
method A simple projection neural network that avoids auxiliary variables and smooth approximations.
result The neural network converges to a solution of the problem with any initial value and outperforms existing methods.

Neural Ordinary Differential Equation (Neural ODE) has been proposed as a continuous approximation to the ResNet architecture. Some commonly used regularization mechanisms in discrete neural networks (e.g. dropout, Gaussian noise) are missing in current Neural ODE networks. In this paper, we propose a new continuous ne…

2019-06-05abs ↗pdf ↗

SNN architecture shows gradient descent converges to regularized solution in matrix sensing problems.

problem Understanding implicit regularization in neural networks for matrix sensing.
method Developed Spectral Neural Networks (SNN) for matrix learning problems, rigorously demonstrating implicit regularization.
result Gradient descent converges to the solution of a regularized learning problem in matrix sensing problems.

Deep networks adapt to function regularity and data distribution.

problem Understanding deep learning's adaptability to function regularity and data distribution.
method Developed nonparametric approximation and estimation theories for a broad class of functions using deep ReLU networks.
result Deep neural networks are adaptive to different regularity of functions and nonuniform data distributions.

New L1L_1 regularization controls neural network generalization error and sparsifies input dimensions.

problem Selecting the optimal number of hidden neurons in neural networks.
method Theoretical analysis of L1L_1 regularization in two-layer neural networks.
result Appropriate L1L_1 regularization leads to near minimax optimal generalization risk bounds.

Over-parameterized neural networks generalize well in practice without any explicit regularization. Although it has not been proven yet, empirical evidence suggests that implicit regularization plays a crucial role in deep learning and prevents the network from overfitting. In this work, we introduce the gradient gap d…

2019-03-05abs ↗pdf ↗

Paper analyzes NAC with neural networks for efficient policy optimization.

problem Improving sample and iteration complexity in policy optimization.
method Entropy regularization, averaging, neural network approximation, and optimization techniques.
result Entropy regularization and averaging ensure stability and sharp sample complexity bounds.

SeReNe prunes neurons with low sensitivity to reduce network size.

problem Large neural networks consume too many resources on resource-constrained devices.
method Exploits neural sensitivity as a regularizer to prune neurons with low sensitivity.
result Pruning neurons with low sensitivity achieves competitive compression ratios.

Two regularization techniques improve GCNN explainability and preference from chemists.

problem Difficulty in rationalizing molecular graph neural network predictions.
method Batch Representation Orthonormalization (BRO) and Gini regularization applied during GCNN training.
result Regularization improves GCNN attribution methods and preference from chemists.

New bounds on ReLU networks for low-regular functions.

problem Bounding approximation error for ReLU networks on low-regular functions.
method Complexity analysis of Fourier features residual networks to ReLU networks.
result Approximation error bound proportional to target function norm and inversely proportional to network width and depth.

The paper proposes a neural network method to estimate treatment effects by balancing treated and control distributions.

problem Estimating individual and average treatment effects from observational data.
method Balance regularization of multi-head neural network architectures to reduce confounding effects.
result The approach reduces bias-variance trade-off and improves treatment effect estimation.

New regularization techniques improve stability of deep neural networks.

problem Improving stability of deep neural networks in high-dimensional data.
method Apply manifold regularization to develop new regularizers based on graph Laplacian sparsification.
result Empirically, networks achieve high stability in various perturbation models, including adversarial attacks.

New method reduces over-parametrization in neural networks, ensuring sparsity and finite network size.

problem Over-parametrization leads to too many active neurons in neural networks, especially with large data.
method Investigates a nonconvex regularization method for shallow ReLU networks.
result Locally optimal networks are finite even with infinite data, maintaining approximation guarantees and network size bounds.

Neural networks learn the support of the target function through SGD's implicit regularization effect.

problem Learning the support of the target function in neural networks.
method Investigation of mini-batch SGD's ability to learn the support in the first layer of a neural network.
result Mini-batch SGD effectively learns the support in the first layer by shrinking irrelevant weights, while vanilla GD requires an explicit regularization term.

Improved TD learning with neural nets reduces sample complexity and overparameterization.

problem Temporal difference learning with neural networks in large state spaces.
method Projection-free and max-norm regularized Neural TD learning, with Lyapunov drift analysis.
result Max-norm regularization significantly improves TD learning's sample complexity and overparameterization.

Batch Normalization (BN) improves both convergence and generalization in training neural networks. This work understands these phenomena theoretically. We analyze BN by using a basic block of neural networks, consisting of a kernel layer, a BN layer, and a nonlinear activation function. This basic network helps us unde…

2018-09-04abs ↗pdf ↗

Proposes a variational approach to shallow neural networks, bypassing optimization.

problem Theoretical understanding and optimization of shallow neural networks.
method Replaces discrete training with a continuum variational surrogate, proving global well-posedness and regularity.
result Optimal parameter density can be obtained by solving a single linear system, achieving O(1/N)O(1/N) generalization error.