Gradient Dynamics
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Gradient Dynamics in First-Price Auctions: Iterative Strategy Elimination via Cubic Potentials
arXiv:2606.05108v1 Announce Type: new Abstract: We show that in discretised first-price auctions with complete information, if the buyers learn to bid with online gradient ascent, in time-average the outcome is (almost) the efficient outcome of the second-price auction. Our proof rests on two novel innovations in the analysis of online gradient ascent in normal-form games, which may be useful in a wider range of applications. First, we develop a potential-function-based argument for the...
Dynamic Gradient-Based Calibration for Robust and Accurate Traffic Macrosimulation
arXiv:2605.19056v2 Announce Type: replace Abstract: Robust and accurate calibration of macroscopic traffic flow models such as METANET is critical for reliable prediction and effective control. While gradient-based methods are desirable for high-dimensional parameter spaces, their application to real-world traffic scenarios is hindered by highly nonconvex optimization landscapes. Consequently, standard static calibration frequently yields parameter sets that produce unstable, unrealistic...
Generative Modeling of Discrete Latent Structures via Dynamic Policy Gradients
arXiv:2606.07400v1 Announce Type: new Abstract: Many scientific problems require inferring unobserved mechanistic latent states from indirect observations. While classical approaches, including expectation maximization, do not scale to combinatorially large spaces, deep learning approaches such as variational autoencoders typically form artificial latent states rather than reconstructing the mechanistic ground-truth states.
Scalar gradient structure and dynamics in turbulent mixing at high Reynolds and Schmidt numbers
arXiv:2606.07858v1 Announce Type: new Abstract: How well turbulence mixes a scalar $\theta$ is governed by the scalar dissipation rate $\chi = 2D |\nabla\theta|^2$, making scalar gradients central to turbulent mixing. We study the structure and amplification of these gradients for passive scalars driven by a uniform mean-gradient in isotropic turbulence, using DNS at grid resolutions up to $8192^3$. The $Re_\lambda$ spans $140-1000$, and $Sc\equiv\nu/D$ spans $1-512$.
Gradient-Flow Optimization as Dynamic Random-Effects Inference: Testing and Early Stopping with Applications to Deep Learning
arXiv:2605.27991v2 Announce Type: replace-cross Abstract: Gradient-flow optimization is usually viewed as an algorithmic procedure for minimizing empirical loss, with training duration selected by validation or heuristic early-stopping rules. We develop a statistical inference framework for the gradient-flow training trajectory itself. The central object is fixed-operator squared-error gradient flow: whenever the fitted value evolves through a time-invariant positive semidefinite training...
Beyond Gradient Descent: Adam for Analog Ising Machines
Announce Type: cross Abstract: As Moore's law reaches its limits, Ising machines offer a promising alternative computing approach for difficult optimization problems. However, many analog, time-continuous Ising machines rely on gradient-descent-like dynamics to find solutions, which can limit speed and robustness.
Beyond Gradient Descent: Adam for Analog Ising Machines
Announce Type: new Abstract: As Moore's law reaches its limits, Ising machines offer a promising alternative computing approach for difficult optimization problems. However, many analog, time-continuous Ising machines rely on gradient-descent-like dynamics to find solutions, which can limit speed and robustness.
Neural Networks Provably Learn Spectral Representations for Group Composition
arXiv:2606.02993v1 Announce Type: new Abstract: Understanding how structured internal structure emerges during neural network training is central to the study of deep learning. We investigate this phenomenon through the group composition task, where a two-layer neural network is trained to predict $g_1 \star g_2$ for elements of a finite group $G$. By lifting the projected gradient flow to the Fourier domain, we demonstrate that the training dynamics are governed by a Riemannian gradient...
Zeroth-Order Non-Log-Concave Sampling with Variance Reduction and Applications to Inverse Problems
arXiv:2605.30573v1 Announce Type: new Abstract: Sampling from high-dimensional, non-log-concave distributions with unnormalized densities remains a fundamental challenge in machine learning, particularly in black-box settings where gradient information is inaccessible or computationally prohibitive. While Langevin dynamics provides a principled framework for sampling when gradients are accessible, its extension to the black-box settings suffers from high variance and lacks non-asymptotic...
Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data
Announce Type: replace Abstract: Transformers trained via Reinforcement Learning (RL) with outcome-based supervision can spontaneously develop the ability to generate intermediate reasoning steps (Chain-of-Thought). Yet the mechanism by which sparse rewards drive policy gradient to discover such systematic reasoning remains poorly understood. We address this by analyzing the policy gradient dynamics of single-layer Transformers on a synthetic graph traversal task that cannot be solved...