Derives ODE limits of Adam-DA showing that first- and second-order momentum parameters reverse their convergence roles in zero-sum games compared to minimization, validated on GAN experiments.
Title resolution pending
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 8verdicts
UNVERDICTED 8roles
background 2polarities
background 2representative citing papers
A reference-decoupled reformulation makes direct data-driven LQT equivalent to certainty-equivalence solutions and supports convergent offline and online DeePO algorithms.
A diameter criterion tied to a potential function certifies convergence of difference inclusions, enabling discrete proofs for first-order optimization methods with diminishing steps.
Derives contraction-based Q-value extensions for exponential utility and proves almost-sure convergence of two-timescale and one-timescale model-free algorithms in discounted MDPs.
A nonlinear observer on SL(3) achieves local exponential convergence for homography estimation by minimizing an image-intensity cost function with explicit non-degeneracy conditions.
DiMS is a physics-inspired dynamical sampler guaranteed to exactly sample reparameterization-invariant minimum level sets in neural network loss landscapes.
Derives LMI-based stability conditions and peak-to-peak gains for a GPSOL/DERL adaptive controller on first-order SISO nonlinear systems to enforce bounded output errors, verified in simulation and on a pneumatic test rig.
Vector-field guidance combined with distance-bearing repulsion and spacing-error velocity control achieves collision-free, uniformly spaced multi-UAV path following with proven convergence.
citing papers explorer
-
Understanding Dynamics of Adam in Zero-Sum Games: An ODE Approach
Derives ODE limits of Adam-DA showing that first- and second-order momentum parameters reverse their convergence roles in zero-sum games compared to minimization, validated on GAN experiments.
-
Direct Data-Driven Linear Quadratic Tracking via Policy Optimization
A reference-decoupled reformulation makes direct data-driven LQT equivalent to certainty-equivalence solutions and supports convergent offline and online DeePO algorithms.
-
Convergence of difference inclusions via a diameter criterion
A diameter criterion tied to a potential function certifies convergence of difference inclusions, enabling discrete proofs for first-order optimization methods with diminishing steps.
-
Reinforcement Learning for Exponential Utility: Algorithms and Convergence in Discounted MDPs
Derives contraction-based Q-value extensions for exponential utility and proves almost-sure convergence of two-timescale and one-timescale model-free algorithms in discounted MDPs.
-
Equivariant Observer Design on SL(3) for Image Intensity-Based Homography Estimation
A nonlinear observer on SL(3) achieves local exponential convergence for homography estimation by minimizing an image-intensity cost function with explicit non-degeneracy conditions.
-
Don't Stop Me Yet: Sampling Loss Minima via Dissipative Riemannian Mechanics
DiMS is a physics-inspired dynamical sampler guaranteed to exactly sample reparameterization-invariant minimum level sets in neural network loss landscapes.
-
Online Learning-Based Control with Guaranteed Error Bounds for a Class of Nonlinear Systems
Derives LMI-based stability conditions and peak-to-peak gains for a GPSOL/DERL adaptive controller on first-order SISO nonlinear systems to enforce bounded output errors, verified in simulation and on a pneumatic test rig.
-
Multi-UAV Path Following using Vector-Field Guidance
Vector-field guidance combined with distance-bearing repulsion and spacing-error velocity control achieves collision-free, uniformly spaced multi-UAV path following with proven convergence.