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.

169,181 papers · 148 categories

Trend · papers per month

97195292389 · Jun 202019922001200920182026
48 results for Vanishing Gradients

The paper analyzes GANs focusing on Inception Score, label smoothing, gradient vanishing, and -log(D(x)).

problem Improving the quality and diversity of generated images in Generative Adversarial Networks (GANs).
method Mathematical analysis of Inception Score, label smoothing, gradient vanishing, and -log(D(x)) alternative in the context of GANs.
result Detailed mathematical insights into Inception Score, label smoothing, gradient vanishing, and -log(D(x)) alternative.

Channel normalization prevents vanishing gradients in convolutional neural networks.

problem Vanishing gradients in convolutional neural networks during optimization.
method Channel normalization, which centers and normalizes each channel individually.
result Channel normalization avoids vanishing gradients, enabling efficient optimization.

New classification of gradient steady Ricci solitons with vanishing D-tensor.

problem Classifying gradient steady Ricci solitons with specific properties.
method Extending Cao-Chen's work on Bach-flat gradient Ricci solitons, proving properties for DD-flat solitons.
result Any nn-dimensional complete noncompact gradient steady Ricci soliton with vanishing DD-tensor is either Ricci-flat or isometric to the Bryant soliton.

Vanishing gradients hinder reinforcement finetuning of language models.

problem Vanishing gradients impede the optimization of language models using reinforcement finetuning.
method The study identifies vanishing gradients as a fundamental optimization obstacle in reinforcement finetuning and proposes an initial supervised finetuning phase to mitigate this issue.
result An initial supervised finetuning phase is crucial for successful reinforcement finetuning of language models, as it helps prevent vanishing gradients and maximizes rewards.

Vanishing nodes cause hidden nodes to behave similarly, complicating deep neural network training.

problem Complicating deep neural network training due to hidden nodes behaving similarly.
method Introduced vanishing node indicator (VNI) to quantify node redundancy and correlated behavior.
result The effective number of nodes vanishes to one as VNI increases, indicating a challenging training scenario.

TSGO optimizes gradients in tensor networks to avoid vanishing/exploding issues.

problem Gradient vanishing and exploding problems in deep learning models.
method TSGO rotates parameters towards gradient direction in tangent space of normalized state.
result TSGO naturally determines learning rate based on angle between parameters and gradient.

Analysis shows exploding and vanishing gradients in neural nets with ReLU activations.

problem Exploding and vanishing gradients in neural nets with ReLU activations.
method Rigorous analysis of gradient behavior in randomly initialized fully connected networks with ReLU activations.
result Empirical variance of gradients is exponential in beta, the sum of reciprocals of hidden layer widths.

A new recurrent unit alleviates vanishing gradients for long-term dependencies.

problem Vanishing gradients in recurrent neural networks make long-term dependencies hard to model.
method Proposes a new NRU architecture that avoids saturating activation functions and gates.
result Demonstrates superior performance across various tasks with and without long-term dependencies.

Analyzes self-attention in recurrent networks, proving it mitigates vanishing gradients.

problem Vanishing gradients in recurrent networks when capturing long-term dependencies.
method Formal analysis of self-attention's effect on gradient propagation, proposing a relevancy screening mechanism.
result Self-attention mitigates vanishing gradients in recurrent networks, providing guarantees.

Gradient amplification boosts deep learning model performance without increasing training time.

problem Vanishing gradients in deep neural networks.
method Gradient amplification approach to prevent vanishing gradients and training strategy to enable/disable across epochs.
result Improves performance of deep learning models with reduced training time.

We classify complete gradient Ricci solitons satisfying a fourth-order vanishing condition on the Weyl tensor, improving previously known results. More precisely, we show that any nn-dimensional (n4n\geq 4) gradient shrinking Ricci soliton with fourth order divergence-free Weyl tensor is either Einstein, or a finite q…

2016-02-01abs ↗pdf ↗

Gradient boosts monomial-order-free basis construction algorithms.

problem Lack of theoretical properties in monomial-order-free basis construction algorithms.
method Exploits gradient to sidestep spurious vanishing, achieve consistent output, and remove redundant bases.
result Proposes methods that equip monomial-order-free algorithms with theoretical properties.

Graph manifolds' simplicial volume approximated by covering volumes.

problem Proving simplicial volume of graph manifolds is zero.
method Approximating simplicial volume of graph manifolds by integral simplicial volumes of their finite coverings.
result Uniform proof of rank, Betti number, and torsion homology gradients for graph manifolds.

Generative memory model avoids vanishing gradients to robustly retrieve patterns.

problem Robust retrieval of stored patterns in the presence of interference and noise.
method Training a generative distributed memory without explicitly simulating attractor dynamics, using a likelihood-based Lyapunov function.
result The model converges to correct patterns upon iterative retrieval and achieves competitive performance as a memory model and a generative model.

Paper proves properties of minimal hypersurfaces in specific solitons.

problem Characterizing minimal hypersurfaces in shrinking gradient Ricci solitons.
method Analyzes stable minimal hypersurfaces with specific curvature conditions.
result Minimal hypersurfaces in these solitons have zero second fundamental form and normal Ricci curvature.

Solves exploding and vanishing gradient problem in LSTMs.

problem Exploding and vanishing gradient problem in LSTM optimization.
method Introduces a simple stochastic algorithm (h-detach) to prevent suppression of gradient components through the cell state path in LSTM.
result Significant improvements in convergence speed, robustness, and generalization over vanilla LSTM training.

Paper analyzes if GANs with adversarial features outperform standard supervised learning.

problem Whether adversarial features improve performance over standard supervised learning.
method Theoretical analysis and empirical risk comparison.
result Supervised learning with adversarial features can outperform sole supervision under certain conditions.

This paper classifies solitons under specific tensor conditions.

problem Classifying solitons under vanishing conditions on the Weyl, Cotton, and Cao-Chen tensors.
method Analyzing complete conformal gradient solitons and using tensor conditions.
result Classification of complete nontrivial locally conformally flat conformal gradient solitons.

New findings on shrinking Ricci solitons with vanishing Bach-like tensors.

problem Characterizing gradient shrinking Ricci solitons with vanishing Bach-like tensors.
method Defining and analyzing Bach-like tensors, proving rigidity results, and deriving variational formulas.
result Vanishing Bach-like tensors force solitons to be either Einstein or isometric to the Gaussian soliton.

Maxout networks study gradients and propose initialization strategies.

problem Complexity in input-output Jacobian distribution complicates stable parameter initialization.
method Obtained bounds on moments of gradients and formulated initialization strategies.
result Parameter initialization strategies improve training of deep maxout networks.

LSTMs are explained as a weighted sum of context-independent functions.

problem Vanishing gradients in simple RNNs.
method Decouple LSTM gates from simple RNNs, computing an element-wise weighted sum of context-independent functions.
result Gating mechanism alone performs as well as an LSTM in most settings, suggesting more representational power.

Spectral normalization stabilizes GANs by controlling gradient explosion and vanishing.

problem Stability and sample quality issues in GAN training.
method Spectral normalization controls gradient explosion and vanishing, improving GAN training stability and sample quality.
result Bidirectional Scaled Spectral Normalization (BSSN) outperforms standard spectral normalization in sample quality and training stability.

Infinitesimal gradient boosting is a new algorithm derived from gradient boosting.

problem Improving the efficiency and smoothness of gradient boosting.
method Introduced a new class of randomized regression trees and used a limit process in vanishing-learning-rate asymptotic.
result Convergence of the stochastic algorithm and characterization of the limiting procedure as a unique solution of a nonlinear ODE.

Quantized Decentralized Gradient Descent (QDGD) solves distributed optimization with quantized communications.

problem Minimizing the sum of smooth and strongly convex functions over a network of distributed agents with quantized communications.
method Proposes QDGD algorithm combining quantized and local information for decentralized gradient descent.
result Achieves vanishing mean solution error under strong convexity and smoothness assumptions.

Gradient penalty improves GAN performance by inducing a large-margin classifier.

problem Improving GAN performance and addressing vanishing gradients.
method A unifying framework of expected margin maximization, showing gradient penalties induce large-margin classifiers.
result Gradient penalties reduce vanishing gradients and produce better generated outputs.

Study the properties of SGD in non-vanishing learning rate regime.

problem Understanding the noise and fluctuation in SGD with finite learning rates.
method Derive exact solvable results for discrete-time SGD in quadratic loss functions.
result Fluctuation caused by discrete-time dynamics is larger than continuous-time theory predicts.

We show that the only complete shrinking gradient Ricci solitons with vanishing Weyl tensor are quotients of the standard ones. This gives a new proof of the Hamilton-Ivey-Perel'man classification of 3-dimensional shrinking gradient solitons. We also prove a classification for expanding gradient Ricci solitons with con…

2007-12-08abs ↗pdf ↗

Study fluid spacetimes, proving shear-free implies vanishing expansion or vorticity.

problem Understanding shear and vorticity in perfect-fluid spacetimes.
method Analyzing perfect-fluid spacetimes using Weyl tensor and divergence.
result Proves shear-free implies vanishing expansion or vorticity for perfect fluids.

ERNNs evolve hidden states on an ODE's equilibrium manifold to mitigate vanishing and exploding gradients.

problem Vanishing and exploding gradients in RNNs.
method Develop a novel family of RNNs (ERNNs) that evolve hidden states on the equilibrium manifold of an ODE.
result ERNNs achieve state-of-the-art accuracy with 3-10x speedups and 1.5-3x model size reduction.

The paper studies topological properties of Ricci shrinkers using weighted L2L^2 cohomology.

problem Proving topological results for smooth gradient Ricci shrinkers.
method Weighted L2L^2 cohomology and extensions to mean curvature flow self-shrinkers.
result Establishes upper bounds for Betti numbers, vanishing theorem for cohomology, and dichotomy for ends.

Stagewise boosting improves gradient boosting for distributional regression.

problem Vanishing gradient in gradient boosting for distributional regression leads to suboptimal models.
method Proposes a stagewise boosting-type algorithm for distributional regression, combining stagewise regression ideas with gradient boosting and incorporating a novel regularization method, correlation filtering.
result The proposed algorithm provides better results, especially for complex distributions, by reducing the risk of being trapped in a local optimum.

In this paper, we introduce the concept of quasi Yamabe gradient solitons, which generalizes the concept of Yamabe gradient solitons. By using some ideas in [7,8], we prove that nn-dimensional (n3)(n\geq3) complete quasi Yamabe gradient solitons with vanishing Weyl curvature tensor and positive sectional curvature must …

2011-08-31abs ↗pdf ↗