Some remarks on gradient dominance and LQR policy optimization

• URL: http://arxiv.org/abs/2507.10452v2
• Date: Wed, 16 Jul 2025 02:38:14 GMT
• Title: Some remarks on gradient dominance and LQR policy optimization
• Authors: Eduardo D. Sontag,
• Abstract summary: Polyak-Lojasiewicz Inequality (PLI) is used to establish an exponential rate of convergence.<n>PLI-like conditions motivate the search for various generalized PLI-like conditions.<n>These generalizations are key to understanding the transient and effects of errors.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Solutions of optimization problems, including policy optimization in reinforcement learning, typically rely upon some variant of gradient descent. There has been much recent work in the machine learning, control, and optimization communities applying the Polyak-{\L}ojasiewicz Inequality (PLI) to such problems in order to establish an exponential rate of convergence (a.k.a. ``linear convergence'' in the local-iteration language of numerical analysis) of loss functions to their minima under the gradient flow. Often, as is the case of policy iteration for the continuous-time LQR problem, this rate vanishes for large initial conditions, resulting in a mixed globally linear / locally exponential behavior. This is in sharp contrast with the discrete-time LQR problem, where there is global exponential convergence. That gap between CT and DT behaviors motivates the search for various generalized PLI-like conditions, and this talk will address that topic. Moreover, these generalizations are key to understanding the transient and asymptotic effects of errors in the estimation of the gradient, errors which might arise from adversarial attacks, wrong evaluation by an oracle, early stopping of a simulation, inaccurate and very approximate digital twins, stochastic computations (algorithm ``reproducibility''), or learning by sampling from limited data. We describe an ``input to state stability'' (ISS) analysis of this issue. The second part discusses convergence and PLI-like properties of ``linear feedforward neural networks'' in feedback control. Much of the work described here was done in collaboration with Arthur Castello B. de Oliveira, Leilei Cui, Zhong-Ping Jiang, and Milad Siami.

Related papers

• Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum [78.27945336558987]
  Decentralized server (DFL) eliminates reliance on client-client architecture.<n>Non-smooth regularization is often incorporated into machine learning tasks.<n>We propose a novel novel DNCFL algorithm to solve these problems.
  arXiv  Detail & Related papers  (2025-04-17T08:32:25Z)
• Remarks on the Polyak-Lojasiewicz inequality and the convergence of gradient systems [0.3277163122167434]
  This work explores generalizations of the Polyak-Lojasiewicz inequality (PLI)<n>This work shows that while weaker conditions are sufficient for global convergence to, and optimality of the set of critical points of the cost function, the "profile" of the gradient flow solution can change significantly depending on which "flavor" of inequality the cost satisfies.
  arXiv  Detail & Related papers  (2025-03-31T00:59:56Z)
• Error Feedback under $(L_0,L_1)$-Smoothness: Normalization and Momentum [56.37522020675243]
  We provide the first proof of convergence for normalized error feedback algorithms across a wide range of machine learning problems. We show that due to their larger allowable stepsizes, our new normalized error feedback algorithms outperform their non-normalized counterparts on various tasks.
  arXiv  Detail & Related papers  (2024-10-22T10:19:27Z)
• Full error analysis of policy gradient learning algorithms for exploratory linear quadratic mean-field control problem in continuous time with common noise [0.0]
  We study policy gradient (PG) learning and first demonstrate convergence in a model-based setting. We prove the global linear convergence and sample complexity of the PG algorithm with two-point gradient estimates in a model-free setting. In this setting, the parameterized optimal policies are learned from samples of the states and population distribution.
  arXiv  Detail & Related papers  (2024-08-05T14:11:51Z)
• Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time [45.72323731094864]
  In this paper, we study the optimality gap between two-layer ReLULU networks regularized with weight decay and their convex relaxations. Our study sheds new light on understanding why local methods work well.
  arXiv  Detail & Related papers  (2024-02-06T01:29:35Z)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• Can Decentralized Stochastic Minimax Optimization Algorithms Converge Linearly for Finite-Sum Nonconvex-Nonconcave Problems? [56.62372517641597]
  Decentralized minimax optimization has been actively studied in the past few years due to its application in a wide range machine learning. This paper develops two novel decentralized minimax optimization algorithms for the non-strongly-nonconcave problem.
  arXiv  Detail & Related papers  (2023-04-24T02:19:39Z)
• Convergence Rates of Two-Time-Scale Gradient Descent-Ascent Dynamics for Solving Nonconvex Min-Max Problems [2.0305676256390934]
  We characterize the finite-time performance of the continuous-time variant of simultaneous gradient descent-ascent algorithm. Our results on the behavior of continuous-time algorithm may be used to enhance the convergence properties of its discrete-time counterpart.
  arXiv  Detail & Related papers  (2021-12-17T15:51:04Z)
• Acceleration in Distributed Optimization Under Similarity [72.54787082152278]
  We study distributed (strongly convex) optimization problems over a network of agents, with no centralized nodes. An $varepsilon$-solution is achieved in $tildemathcalrhoObig(sqrtfracbeta/mu (1-)log1/varepsilonbig)$ number of communications steps. This rate matches (up to poly-log factors) for the first time lower complexity communication bounds of distributed gossip-algorithms applied to the class of problems of interest.
  arXiv  Detail & Related papers  (2021-10-24T04:03:00Z)
• Physics-informed neural network simulation of multiphase poroelasticity using stress-split sequential training [0.0]
  We present a framework for solving problems governed by partial differential equations (PDEs) based on elastic networks. We find that the approach converges to solve problems of porosci, Barry-Scier's injection-production problem, and a two-phase drainage problem.
  arXiv  Detail & Related papers  (2021-10-06T20:09:09Z)
• On the Convergence Rate of Projected Gradient Descent for a Back-Projection based Objective [58.33065918353532]
  We consider a back-projection based fidelity term as an alternative to the common least squares (LS) We show that using the BP term, rather than the LS term, requires fewer iterations of optimization algorithms.
  arXiv  Detail & Related papers  (2020-05-03T00:58:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.