Study finds incorporating fairness in healthcare models doesn't improve performance or net benefit.
problem Addressing health inequities in healthcare through algorithmic fairness.
method Empirical case study using models to estimate atherosclerotic cardiovascular disease risk.
result Incorporating fairness considerations into model training objective does not improve model performance or net benefit.
Paper optimizes neural network initialization using SMT solvers.
problem Improving neural network performance through better initialization.
method Reduces initialization to SMT problem solving.
result Proposed method achieves better performance than random initialization.
New method for better initial centers in clustering with improved accuracy and privacy.
problem Improving the quality of clustering centers in metric spaces.
method HST initialization based on metric embedding tree structure, combined with efficient search algorithm and DP extension.
result HST initialization produces better initial centers than k-median++ with comparable efficiency and improved privacy. Study shows different initialization schemes for LoRA finetuning impact performance.
problem The impact of initialization schemes on LoRA finetuning performance.
method Compared two initialization schemes: B=0, A=random vs. A=0, B=random.
result First initialization scheme yields better performance on average.
Orthogonal initialization speeds up convergence in deep linear networks.
problem The impact of initialization on convergence speed and model performance in deep neural networks.
method Analysis of orthogonal initialization in deep linear networks, proving its superiority over Gaussian initialization.
result Orthogonal initialization speeds up convergence relative to Gaussian initialization in deep networks.
New method learns good initialization for gradient descent from past solutions.
problem Challenges in solving non-convex optimization problems.
method Learning good initialization rules from previous solutions.
result Our approach performs better than random initialization in various non-convex problems.
Initial data for pp-wave spacetimes constructed in 4D.
problem Characterizing initial data for pp-wave spacetimes. method Constructs a vacuum initial data set with extra conditions related to CKID.
result Data development is a subset of a vacuum pp-wave. In this paper, we firstly give a brief introduction of expectation maximization (EM) algorithm, and then discuss the initial value sensitivity of expectation maximization algorithm. Subsequently, we give a short proof of EM's convergence. Then, we implement experiments with the expectation maximization algorithm (We im…
The paper establishes principles for initializing and designing GNNs with ReLU activations to avoid oversmoothing and correlation collapse.
problem Oversmoothing and correlation collapse in deep ReLU GNNs.
method The paper derives and validates three principles for initialization and architecture selection in finite width graph neural networks with ReLU activations.
result Correct initialization, residual aggregation operators, and residual connections significantly improve early training dynamics in deep ReLU GNNs.
The performance of the Self-Organizing Map (SOM) algorithm is dependent on the initial weights of the map. The different initialization methods can broadly be classified into random and data analysis based initialization approach. In this paper, the performance of random initialization (RI) approach is compared to that…
New distributed clustering algorithms show resilience to initialization issues.
problem Resilience of distributed gradient-based clustering algorithms to center initialization.
method Distributed gradient-based clustering algorithms with novel center initialization.
result The algorithms are more resilient to initialization compared to baseline methods.
Initializing the weights and the biases is a key part of the training process of a neural network. Unlike the subsequent optimization phase, however, the initialization phase has gained only limited attention in the literature. In this paper we discuss some consequences of commonly used initialization strategies for va…
Barren plateaus are not an average-case phenomenon, but a highly non-unique problem.
problem Avoiding barren plateaus in neural network training
method First-moment framework for initialization strategies
result Many families of inequivalent initialization strategies can avoid concentration
Standard practice in training neural networks involves initializing the weights in an independent fashion. The results of recent work suggest that feature "diversity" at initialization plays an important role in training the network. However, other initialization schemes with reduced feature diversity have also been sh…
Class I CR manifolds have initial G-structure a certain 4-dimensional subgroup of GL_3(C). Class II CR manifolds have initial G-structure a certain 10-dimensional subgroup of GL_4(C). Class III-1 CR manifolds have initial G-structure a certain 10-dimensional subgroup of GL_5(C). Class III-2 CR manifolds have initial G-…
The dying ReLU refers to the problem when ReLU neurons become inactive and only output 0 for any input. There are many empirical and heuristic explanations of why ReLU neurons die. However, little is known about its theoretical analysis. In this paper, we rigorously prove that a deep ReLU network will eventually die in…
FuseInit optimizes neural network initialization by fusing layers from deeper networks.
problem Initialization sensitivity of neural networks.
method Fusing neighboring layers from deeper networks trained with random initialization.
result Shallower networks initialized with FuseInit can perform as well as deeper networks.
New method for initializing RBM weights without datasets.
problem No dataset-free weight-initialization for RBMs.
method Statistical mechanical analysis to derive Gaussian distribution with optimized standard deviation.
result Optimal weight initialization improves learning efficiency in RBMs.
Paper proves rigidity of initial data sets with boundary and capillary MOTS.
problem Rigidity of initial data sets with boundary and capillary MOTS.
method Estimates area of MOTS, proves rigidity for 3D, extends to high dimensions using Yamabe constant.
result Rigidity results for initial data sets with boundary and capillary MOTS.
Deep networks retain initial bias after training, affecting generalization.
problem Understanding how much initial bias in neural networks survives training.
method Introduced initialization memory to measure initial bias's survival.
result SGD can preserve initial bias, while Adam-family methods erase it.
AutoInit automatically finds good neural network initialization.
problem Finding optimal neural network initialization is crucial but time-consuming.
method Uses Jacobian tuning to automatically adjust network hyperparameters.
result The method finds good initialization for various network architectures.
Residual networks (ResNet) and weight normalization play an important role in various deep learning applications. However, parameter initialization strategies have not been studied previously for weight normalized networks and, in practice, initialization methods designed for un-normalized networks are used as a proxy.…
Neural nets trained with linear discriminant initialization converge faster and more accurately.
problem Training feed-forward neural networks efficiently and accurately.
method Initialize first layer weights with linear discriminants.
result Asymptotic higher accuracy and faster convergence.
Study evaluates initialization strategies for infinite hidden Markov models.
problem Limited attention to initialization in infinite hidden Markov models.
method Systematically evaluated distance-based clustering, model-based, and uniform initializations.
result Distance-based clustering initializations consistently outperform other methods.
This paper presents a phase diagram for two-layer neural networks under different initialization scales.
problem Understanding the behavior of neural networks under varying scales of initialization.
method Analysis of a phase diagram for two-layer neural networks.
result Condensation of weight vectors on isolated orientations during training.
Proves density and mass theorems for specific initial data sets.
problem Initial data sets with boundary in spacetime.
method Harmonic asymptotics and dominant energy condition.
result Spacetime positive mass theorem for initial data sets with apparent horizon boundary.
A new neural network initialization method is proposed for faster and more accurate training.
problem Efficient initialization for training multi-layer feedforward neural networks.
method Initialization based on Stein's identity, using eigenvectors of cross-moment matrix.
result The SteinGLM method is faster and more accurate than other initialization methods.
When working with asymptotically hyperbolic initial data sets for general relativity it is convenient to assume certain simplifying properties. We prove that the subset of initial data sets with such properties is dense in the set of physically reasonable asymptotically hyperbolic initial data sets. More specifically, …
The success of lottery ticket initializations (Frankle and Carbin, 2019) suggests that small, sparsified networks can be trained so long as the network is initialized appropriately. Unfortunately, finding these "winning ticket" initializations is computationally expensive. One potential solution is to reuse the same wi…
Two new scalable K-means initialization methods proposed for large-scale clustering.
problem Efficient initialization for large-scale clustering problems.
method Divide-and-conquer approach and random projection method for multiple lower-dimensional subspaces.
result The proposed methods outperform state-of-the-art in large-scale clustering tasks.
Improves LSTM performance by initializing states via manifold learning.
problem Improving LSTM performance through better initialization.
method Learning an intrinsic data manifold to initialize LSTM internal states.
result Improved LSTM performance through consistent initialization.
Estimates bandwidth for CMC initial data sets.
problem Estimating bandwidth for constant mean curvature (CMC) initial data sets.
method Three independent proofs: stability of null expansion, spacetime harmonic function perturbation, Dirac operator.
result Generalized Gromov's band width estimate to CMC initial data sets.
Survey on preserving curvature bounds for non-smooth Ricci flow.
problem Preserving curvature bounds for non-smooth initial data in Ricci flow.
method Survey of various weak initial data and preservation of curvature bounds.
result Various curvature lower bounds preserved up to a constant for non-smooth initial data.
Article strengthens initial data rigidity theorem to show unique spacetime extension.
problem Initial data rigidity in spacetime geometry.
method Showed initial data sets carry a lightlike parallel vector field, leading to unique spacetime extension.
result Local uniqueness of spacetimes extending initial data sets under dominant energy condition.
This paper examines weight initialization for 1-Lipschitz networks to improve robustness against adversarial attacks.
problem Improving the robustness of deep neural networks against adversarial attacks.
method Examined weight parametrization of AOL and SLL networks, calculated weight variance bounds, and demonstrated weight decay.
result Weight initialization causes deep 1-Lipschitz networks to decay to zero, and weight variance does not affect output variance distribution.
In this paper, we present a novel approach for initializing deep neural networks, i.e., by turning PCA into neural layers. Usually, the initialization of the weights of a deep neural network is done in one of the three following ways: 1) with random values, 2) layer-wise, usually as Deep Belief Network or as auto-encod…
New method shows random, diverse initializations are not essential for deep neural networks.
problem The necessity of random, diverse initializations in deep neural networks.
method Constructed a deep convolutional network with identical features by initializing weights to 0, enabling signal propagation and stable gradients.
result Random, diverse initializations are not necessary for training neural networks.
Due to the iterative nature of most nonnegative matrix factorization (\textsc{NMF}) algorithms, initialization is a key aspect as it significantly influences both the convergence and the final solution obtained. Many initialization schemes have been proposed for NMF, among which one of the most popular class of methods…
Our study analyzes how neural network initialization affects privacy and utility in overparameterized models.
problem Privacy and utility trade-off in overparameterized neural networks.
method Analytical proof of KL divergence privacy bound, focusing on initialization, width, and depth.
result Privacy bound improvement with increasing depth under certain initializations, degradation under others.
Optimizes deep neural network initialization variance for better performance.
problem Improving deep neural network performance through optimal initialization variance.
method Using SGD dynamics and Fokker-Planck equations, we study the relationship between initialization and expected loss function.
result An optimal condition for initialization variance that leads to lower training loss and higher test accuracy.
Smooth dec initial data sets may not extend to smooth spacetimes.
problem Whether every dec initial data set can be extended to a smooth spacetime.
method Examined the converse of the dominant energy condition for initial data sets and spacelike hypersurfaces.
result Not all dec initial data sets can be extended to smooth spacetimes.
Re-initializing neural networks improves generalization but not as much as other techniques.
problem Understanding when and how re-initialization improves neural network performance.
method Empirical comparison of re-initialization with standard training and various regularization techniques.
result Re-initialization is beneficial for generalization but not as much as other techniques, especially when combined with careful tuning of hyperparameters.
New method stabilizes deep neural networks by setting Lyapunov exponent to zero.
problem Stability issues in deep neural networks with low width.
method Lyapunov initialization method to set Lyapunov exponent to zero.
result Lyapunov exponent governs stability of deep networks; standard methods fail for low width.
Geometrically interpolates rigid body motions with initial and terminal twists.
problem Finding spatial trajectories between prescribed initial and terminal poses.
method Derives solutions for k-IV-TIP and k-BV-TIP for k=1,...,4.
result Automatic cubic interpolation identical to minimum acceleration curve when twists are zero.
Stochastic variational inference is an established way to carry out approximate Bayesian inference for deep models. While there have been effective proposals for good initializations for loss minimization in deep learning, far less attention has been devoted to the issue of initialization of stochastic variational infe…
New method constructs flat initial data for Einstein's equations.
problem Constructing asymptotically flat initial data for Einstein's equations.
method Explicit solution operators with localization properties.
result Improved decay rate and nontrivial initial data construction.
We find necessary and sufficient conditions ensuring that the vacuum development of an initial data set of the Einstein's field equations admits a conformal Killing vector. We refer to these conditions as conformal Killing initial data (CKID) and they extend the well-known Killing initial data (KID) that have been know…
Constructs constant spacetime mean curvature surfaces for hyperboloidal initial data sets.
problem Creating a foliation of constant spacetime mean curvature surfaces for asymptotically hyperboloidal initial data sets.
method Long time limit of volume preserving spacetime mean curvature flow starting from a constant mean curvature foliation.
result Obtains a foliation of constant spacetime mean curvature surfaces as the long time limit.