Introduces zero-inflated Gaussian distributions for EDAs to jointly optimize sparsity patterns and active parameter values without bi-level schemes or custom operators.
SIAM Journal on Optimization , volume =
7 Pith papers cite this work. Polarity classification is still indexing.
years
2026 7verdicts
UNVERDICTED 7representative citing papers
Stochastic integer optimization has sample complexity that matches, undercuts, or exceeds the continuous case based on objective structure, with new tight bounds for nonconvex continuous problems.
Combining random reshuffling and Richardson-Romberg extrapolation yields cubic bias refinement and better MSE for constant-step SGD on structured non-monotone variational inequalities.
SGD on multiclass cross-entropy loss alternates between curvature-driven oscillations and stable regimes but self-stabilizes to enable best-iterate convergence with large learning rates for linear and two-layer models.
A general framework for parameter-free smooth nonconvex optimization via higher-order regularization yields algorithms with optimal complexity bounds without prior parameter knowledge.
FAR-SIGN achieves adversary-resilient fully asynchronous optimization via signed directional projections and two-timescale correction, with almost-sure convergence to stationary points at rates O(n^{-1/4+ε}) first-order and O(n^{-1/6+ε}) zeroth-order.
PhySwarm combines a multi-phase advection-diffusion-reaction density model with an equivalent microscopic motion model and a neural-physics controller trained via RL-PINN to generate and control multi-stage emergent behaviors in robot swarms.
citing papers explorer
-
Zero-Inflated Gaussian Distributions Enable Parameter-Space Sparsity in Estimation-of-Distribution Algorithms
Introduces zero-inflated Gaussian distributions for EDAs to jointly optimize sparsity patterns and active parameter values without bi-level schemes or custom operators.
-
Sample Complexity of Stochastic Optimization with Integer Variables
Stochastic integer optimization has sample complexity that matches, undercuts, or exceeds the continuous case based on objective structure, with new tight bounds for nonconvex continuous problems.
-
Shuffling the Data, Stretching the Step-size: Sharper Bias in constant step-size SGD
Combining random reshuffling and Richardson-Romberg extrapolation yields cubic bias refinement and better MSE for constant-step SGD on structured non-monotone variational inequalities.
-
SGD at the Edge of Stability: Stochastic Stabilization with Large Learning Rates
SGD on multiclass cross-entropy loss alternates between curvature-driven oscillations and stable regimes but self-stabilizes to enable best-iterate convergence with large learning rates for linear and two-layer models.
-
A General Recipe for Parameter-Free Nonconvex Optimization via Higher-Order Regularization
A general framework for parameter-free smooth nonconvex optimization via higher-order regularization yields algorithms with optimal complexity bounds without prior parameter knowledge.
-
Adversary-Robust Learning from Fully Asynchronous Directional Derivative Estimates
FAR-SIGN achieves adversary-resilient fully asynchronous optimization via signed directional projections and two-timescale correction, with almost-sure convergence to stationary points at rates O(n^{-1/4+ε}) first-order and O(n^{-1/6+ε}) zeroth-order.
-
Physics-Informed Modeling and Control of Emergent Behaviors in Robot Swarms
PhySwarm combines a multi-phase advection-diffusion-reaction density model with an equivalent microscopic motion model and a neural-physics controller trained via RL-PINN to generate and control multi-stage emergent behaviors in robot swarms.