paper-with-me

홈 › Papers

Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality

2025-03-22 · Ruijia Zhang, Siliang Zeng, Chenliang Li, Alfredo Garcia, Mingyi Hong

The goal of the Inverse reinforcement learning (IRL) task is to identify the underlying reward function and the corresponding optimal policy from a set of expert demonstrations. While most IRL algorithms' theoretical guarantees rely on a linear reward structure, we aim to extend the theoretical understanding of IRL to scenarios where the reward function is parameterized by neural networks. Meanwhile, conventional IRL algorithms usually adopt a nested structure, leading to computational inefficiency, especially in high-dimensional settings. To address this problem, we propose the first two-timescale single-loop IRL algorithm under neural network parameterized reward and provide a non-asymptotic convergence analysis under overparameterization. Although prior optimality results for linear rewards do not apply, we show that our algorithm can identify the globally optimal reward and policy under certain neural network structures. This is the first IRL algorithm with a non-asymptotic convergence guarantee that provably achieves global optimality in neural network settings.

📄 PDF Abstract BibTeX arXiv:2503.17865

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
ADOPT Please enter a description about the method here

Similar Papers 제목 키워드 기반

Analysis of Overparameterization in Continual Learning under a Linear Model

2025-02-11 · Daniel Goldfarb, Paul Hand

Autonomous machine learning systems that learn many tasks in sequence are prone to the catastrophic forgetting problem. Mathematical theory is needed in order to understand the extent of forgetting during continual learn…

Continual Learningregression

Neural Networks and Quantum Field Theory

2020-08-19 · James Halverson, Anindita Maiti, Keegan Stoner

We propose a theoretical understanding of neural networks in terms of Wilsonian effective field theory. The correspondence relies on the fact that many asymptotic neural networks are drawn from Gaussian processes, the an…

Gaussian Processesvalid

Solving Inverse Problems with Deep Linear Neural Networks: Global Convergence Guarantees for Gradient Descent with Weight Decay

2025-02-21 · Hannah Laus, Suzanna Parkinson, Vasileios Charisopoulos, Felix Krahmer 외

Machine learning methods are commonly used to solve inverse problems, wherein an unknown signal must be estimated from few measurements generated via a known acquisition procedure. In particular, neural networks perform …

compressed sensing

Critical Influence of Overparameterization on Sharpness-aware Minimization

2023-11-29 · Sungbin Shin, Dongyeop Lee, Maksym Andriushchenko, Namhoon Lee

Sharpness-Aware Minimization (SAM) has attracted considerable attention for its effectiveness in improving generalization in deep neural network training by explicitly minimizing sharpness in the loss landscape. Its succ…

Attribute

Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks

2020-12-16 · Xiangyu Chang, Yingcong Li, Samet Oymak, Christos Thrampoulidis

Deep networks are typically trained with many more parameters than the size of the training dataset. Recent empirical evidence indicates that the practice of overparameterization not only benefits training large models, …

Model Compression