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.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “pseudogradients”

Neural Networks with Structural Resistance to Adversarial Attacksstat.ML

New neural network units resist adversarial attacks effectively.

problem Adversarial attacks on neural networks that misclassify inputs.

method Introduced RBFI units with non-linear structure.

result RBFI units maintain high accuracy in adversarial attacks.

neural networks adversarial attacks resistance RBFI units pseudogradients

2018-09-25abs ↗pdf ↗

Near Optimal Heteroscedastic Regression with Symbiotic Learningstat.ML

Improved heteroscedastic regression with machine learning techniques.

problem Estimating weights in heteroscedastic linear regression with varying noise.

method Alternating minimization with weighted least squares and pseudogradient descent.

result Achieved a tighter error bound for estimating weights.

heteroscedastic regression machine learning weighted least squares pseudogradient descent phase retrieval

2023-06-25abs ↗pdf ↗

Morse theory and the resonant Q-curvature problemmath.DG

In this paper, we study the prescribed $Q$ -curvature problem on closed four-dimensional Riemannian manifolds when the total integral of the $Q$ -curvature is a positive integer multiple of the one of the four-dimensional round sphere. This problem has a variational structure with a lack of compactness. Using some topolo…

2014-09-28abs ↗pdf ↗

A game-theoretic approach for Generative Adversarial Networkscs.LG

Improves GANs training through game theory.

problem Hard training of GANs due to antagonistic networks.

method Rewrote GAN training as a variational inequality and introduced a stochastic relaxed forward-backward algorithm.

result Algorithm converges to an exact solution or a neighborhood of it under monotonicity.

Generative Adversarial Networks Game Theory Nash Equilibrium Variational Inequality Monotonicity

2020-03-30abs ↗pdf ↗

The role of optimization geometry in single neuron learningcs.LG

Optimization geometry affects deep learning performance.

problem The impact of optimization geometry on deep learning performance.

method Analysis of pseudogradient methods for learning generalized linear models.

result Non-asymptotic bounds on generalization error characterize model performance.

deep learning optimization geometry generalized linear models nonconvex optimization generalization error

2020-06-15abs ↗pdf ↗

The Nirenberg problem on high dimensional half spheres: The effect of pinching conditionsmath.AP

The paper solves the Nirenberg problem on high-dimensional half spheres with pinching conditions.

problem Finding conformal metrics of prescribed scalar curvature and zero boundary mean curvature on half spheres.

method Variational approach with pseudogradient and Morse theory to handle non-compactness.

result Existence results for the Nirenberg problem under various pinching conditions.

Nirenberg problem conformal metrics scalar curvature half spheres pinching conditions

2020-12-23abs ↗pdf ↗