English
Related papers

Related papers: Understanding Lookahead Dynamics Through Laplace T…

200 papers

We study off-dynamics Reinforcement Learning (RL), where the policy training and deployment environments are different. To deal with this environmental perturbation, we focus on learning policies robust to uncertainties in transition…

Machine Learning · Computer Science 2024-10-01 Zhishuai Liu , Weixin Wang , Pan Xu

We use matrix iteration theory to characterize acceleration in smooth games. We define the spectral shape of a family of games as the set containing all eigenvalues of the Jacobians of standard gradient dynamics in the family. Shapes…

Machine Learning · Computer Science 2020-03-10 Waïss Azizian , Damien Scieur , Ioannis Mitliagkas , Simon Lacoste-Julien , Gauthier Gidel

We present a framework for edge-aware optimization that is an order of magnitude faster than the state of the art while having comparable performance. Our key insight is that the optimization can be formulated by leveraging properties of…

Computer Vision and Pattern Recognition · Computer Science 2018-05-15 Akash Bapat , Jan-Michael Frahm

A well-known approach to describe the dynamics of an open quantum system is to compute the master equation evolving the reduced density matrix of the system. This approach plays an important role in describing excitation transfer through…

Quantum Physics · Physics 2022-10-25 Kimara Naicker , Ilya Sinayskiy , Francesco Petruccione

Motion prediction is critical for autonomous vehicles to effectively navigate complex environments and accurately anticipate the behaviors of other traffic participants. As autonomous driving continues to evolve, the need to assimilate new…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Boqi Li , Haojie Zhu , Henry X. Liu

Deep learning is mainly based on utilizing gradient-based optimization for training Deep Neural Network (DNN) models. Although robust and widely used, gradient-based optimization algorithms are prone to getting stuck in local minima. In…

Neural and Evolutionary Computing · Computer Science 2024-08-15 Rasa Khosrowshahli , Shahryar Rahnamayan , Beatrice Ombuki-Berman

Reinforcement learning (RL) algorithms have proven transformative in a range of domains. To tackle real-world domains, these systems often use neural networks to learn policies directly from pixels or other high-dimensional sensory input.…

Machine Learning · Computer Science 2025-10-02 Nishil Patel , Sebastian Lee , Stefano Sarao Mannelli , Sebastian Goldt , Andrew Saxe

Learning algorithms are essential for the applications of game theory in a networking environment. In dynamic and decentralized settings where the traffic, topology and channel states may vary over time and the communication between agents…

Machine Learning · Computer Science 2011-03-15 Quanyan Zhu , Hamidou Tembine , Tamer Basar

We aim at computing the derivative of the solution to a parametric optimization problem with respect to the involved parameters. For a class broader than that of strongly convex functions, this can be achieved by automatic differentiation…

Optimization and Control · Mathematics 2019-10-15 Sheheryar Mehmood , Peter Ochs

We study multilevel techniques, commonly used in PDE multigrid literature, to solve structured optimization problems. For a given hierarchy of levels, we formulate a coarse model that approximates the problem at each level and provides a…

Optimization and Control · Mathematics 2025-05-19 Ferdinand Vanmaele , Yara Elshiaty , Stefania Petra

Ordinary differential equations (ODEs) provide a powerful framework for modeling dynamic systems arising in a wide range of scientific domains. However, most existing ODE methods focus on a single system, and do not adequately address the…

Methodology · Statistics 2026-04-08 Shuoxun Xu , Zijian Guo , Brooke R. Staveland , Robert T. Knight , Lexin Li

We analyze fast diagonal methods for simple bilevel programs. Guided by the analysis of the corresponding continuous-time dynamics, we provide a unified convergence analysis under general geometric conditions, including H\"olderian growth…

Optimization and Control · Mathematics 2025-05-21 Radu Ioan Boţ , Enis Chenchene , Ernö Robert Csetnek , David Alexander Hulett

This paper studies a new class of linear-quadratic mean field games and teams problem, where the large-population system satisfies a class of $N$ weakly coupled linear backward stochastic differential equations (BSDEs), and $z_i$ (a part of…

Optimization and Control · Mathematics 2025-01-10 Yu Si , Jingtao Shi

We present a novel algorithm for game-theoretic trajectory planning, tailored for settings in which agents can only observe one another in specific regions of the state space. Such problems arise naturally in the context of multi-robot…

Multiagent Systems · Computer Science 2024-06-18 Kushagra Gupta , David Fridovich-Keil

Inverse problems are the task of calibrating models to match data. They play a pivotal role in diverse engineering applications by allowing practitioners to align models with reality. In many applications, engineers and scientists do not…

Machine Learning · Computer Science 2026-03-05 Pengyu Zhang , Arnaud Vadeboncoeur , Alex Glyn-Davies , Mark Girolami

Reliable inference of system degradation from sensor data is fundamental to condition monitoring and prognostics in mechanical and infrastructural systems. Since degradation is rarely directly observable and measurable, it must be inferred…

Machine Learning · Computer Science 2026-03-13 Mengjie Zhao , Olga Fink

This paper proposes a frequency/time hybrid integral-equation method for the time dependent wave equation in two and three-dimensional spatial domains. Relying on Fourier Transformation in time, the method utilizes a fixed…

Numerical Analysis · Mathematics 2020-04-30 Thomas G. Anderson , Oscar P. Bruno , Mark Lyon

The cornerstone underpinning deep learning is the guarantee that gradient descent on an objective converges to local minima. Unfortunately, this guarantee fails in settings, such as generative adversarial nets, where there are multiple…

Machine Learning · Computer Science 2018-06-07 David Balduzzi , Sebastien Racaniere , James Martens , Jakob Foerster , Karl Tuyls , Thore Graepel

In this paper, we introduce a higher-order multiscale method for time-dependent problems with highly oscillatory coefficients. Building on the localized orthogonal decomposition (LOD) framework, we construct enriched correction operators to…

Numerical Analysis · Mathematics 2026-05-15 Balaje Kalyanaraman , Felix Krumbiegel , Roland Maier , Siyang Wang

We develop a flexible stochastic approximation framework for analyzing the long-run behavior of learning in games (both continuous and finite). The proposed analysis template incorporates a wide array of popular learning algorithms,…

Computer Science and Game Theory · Computer Science 2023-07-04 Panayotis Mertikopoulos , Ya-Ping Hsieh , Volkan Cevher