arXiv Machine Learning July 3, 2026 By Don Li, Dacian Daescu

A Unified Lyapunov-IQC Framework for Uniform Stability of Smooth Quadratic First-Order Accelerated Optimizers

Read the original on arXiv Machine Learning →

arXiv:2605. 08488v2 Announce Type: replace-cross Abstract: We develop a unified Lyapunov-integral quadratic constraint (IQC) framework for establishing uniform stability of first-order accelerated optimization algorithms in the $\beta$-smooth and $\gamma$-strongly convex regime.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

4d ago

High-Probability Convergence of Clipped SGD under Heavy-Tailed Noise and $(L_0,L_1)$-Smoothness

arXiv:2505.20817v3 Announce Type: replace-cross Abstract: Gradient clipping is widely used in language-model training to control heavy-tailed gradient noise and can improve convergence guarantees ove...

By Taha El Bakkali El Kadi, Savelii Chezhegov, Aleksandr Beznosikov, Samuel Horv\'ath, Eduard Gorbunov

safety

arXiv Machine Learning

Jun 11

Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity

arXiv:2606. 11431v1 Announce Type: new Abstract: Mirror Descent (MD) extends Gradient Descent (GD) beyond Euclidean geometry and has recently reappeared as a lens for KL-regularized policy optimization in reinforcement learning and LLM post-training.

By Shira Vansover-Hager, Matan Schliserman, Ofir Schlisselberg, Tomer Koren

llms reinforcement-learning

arXiv Machine Learning

Jul 13

Accelerated Fully First-Order Methods for Bilevel and Minimax Optimization

arXiv:2405. 00914v4 Announce Type: replace-cross Abstract: We present in this paper novel accelerated fully first-order methods in \emph{Bilevel Optimization} (BLO).

By Chris Junchi Li

benchmarks

arXiv Machine Learning

Sep 1

Generalization as a robust performance property of learning-enabled dynamical systems

arXiv:2608.30431v1 Announce Type: cross Abstract: By focusing on algorithmic stability as a means of establishing out-of-sample bounds, we provide a system-theoretic interpretation of generalization...

By Filippo Fabiani

arXiv Machine Learning

Jul 23

Any-Time Regret-Guaranteed Algorithm for Control of Linear Quadratic Systems

arXiv:2406. 07746v4 Announce Type: replace-cross Abstract: We propose a computationally efficient algorithm that achieves anytime regret of order $\mathcal{O}(\sqrt{t})$, with explicit dependence on the system dimensions and on the solution of the Discrete Algebraic Riccati Equation (DARE).

By Jafar Abbaszadeh Chekan, Cedric Langbort

arXiv Machine Learning

Sep 15

Equilibrium bias and convergence in augmented primal--dual dynamics with sampled constraints

arXiv:2609.13925v1 Announce Type: cross Abstract: This work studies the stability and convergence of augmented primal-dual dynamics when constraint values are estimated from samples. Unbiased constra...

By Kang Liu, Mengxiao Chen, Siqi Xiong, Yi Xia

safety

One email a morning, machine-written

Related stories

High-Probability Convergence of Clipped SGD under Heavy-Tailed Noise and $(L_0,L_1)$-Smoothness

Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity

Accelerated Fully First-Order Methods for Bilevel and Minimax Optimization

Generalization as a robust performance property of learning-enabled dynamical systems

Any-Time Regret-Guaranteed Algorithm for Control of Linear Quadratic Systems

Equilibrium bias and convergence in augmented primal--dual dynamics with sampled constraints