Smoothed Online Learning for Prediction in Piecewise Affine Systems
- URL: http://arxiv.org/abs/2301.11187v2
- Date: Tue, 19 Mar 2024 15:18:23 GMT
- Title: Smoothed Online Learning for Prediction in Piecewise Affine Systems
- Authors: Adam Block, Max Simchowitz, Russ Tedrake,
- Abstract summary: This paper builds on the recently developed smoothed online learning framework.
It provides the first algorithms for prediction and simulation in piecewise affine systems.
- Score: 43.64498536409903
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The problem of piecewise affine (PWA) regression and planning is of foundational importance to the study of online learning, control, and robotics, where it provides a theoretically and empirically tractable setting to study systems undergoing sharp changes in the dynamics. Unfortunately, due to the discontinuities that arise when crossing into different ``pieces,'' learning in general sequential settings is impossible and practical algorithms are forced to resort to heuristic approaches. This paper builds on the recently developed smoothed online learning framework and provides the first algorithms for prediction and simulation in PWA systems whose regret is polynomial in all relevant problem parameters under a weak smoothness assumption; moreover, our algorithms are efficient in the number of calls to an optimization oracle. We further apply our results to the problems of one-step prediction and multi-step simulation regret in piecewise affine dynamical systems, where the learner is tasked with simulating trajectories and regret is measured in terms of the Wasserstein distance between simulated and true data. Along the way, we develop several technical tools of more general interest.
Related papers
- Stochastic Online Optimization for Cyber-Physical and Robotic Systems [9.392372266209103]
We propose a novel online framework for solving programming problems in the context of cyber-physical and robotic systems.
Our problem formulation constraints model the evolution of a cyber-physical system, which has, in general, a continuous state and action space space is nonlinear.
We show that even rough estimates of the dynamics can significantly improve the convergence of our algorithms.
arXiv Detail & Related papers (2024-04-08T09:08:59Z) - An Analytic End-to-End Deep Learning Algorithm based on Collaborative
Learning [5.710971447109949]
This paper presents a convergence analysis for end-to-end deep learning of fully connected neural networks (FNN) with smooth activation functions.
The proposed method avoids any potential chattering problem, and it also does not easily lead to gradient vanishing problems.
arXiv Detail & Related papers (2023-05-26T08:09:03Z) - Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making [73.48977854003697]
This work introduces a new notion of complexity, the generalized bracketing numbers, which marries constraints on the adversary to the size of the space.
We then instantiate our bounds in several problems of interest, including online prediction and planning of piecewise continuous functions.
arXiv Detail & Related papers (2023-02-10T18:45:52Z) - On Robust Numerical Solver for ODE via Self-Attention Mechanism [82.95493796476767]
We explore training efficient and robust AI-enhanced numerical solvers with a small data size by mitigating intrinsic noise disturbances.
We first analyze the ability of the self-attention mechanism to regulate noise in supervised learning and then propose a simple-yet-effective numerical solver, Attr, which introduces an additive self-attention mechanism to the numerical solution of differential equations.
arXiv Detail & Related papers (2023-02-05T01:39:21Z) - Guaranteed Conservation of Momentum for Learning Particle-based Fluid
Dynamics [96.9177297872723]
We present a novel method for guaranteeing linear momentum in learned physics simulations.
We enforce conservation of momentum with a hard constraint, which we realize via antisymmetrical continuous convolutional layers.
In combination, the proposed method allows us to increase the physical accuracy of the learned simulator substantially.
arXiv Detail & Related papers (2022-10-12T09:12:59Z) - Learning to Control under Time-Varying Environment [18.48729114775298]
This paper investigates the problem of regret in linear time-varying (LTV) dynamical systems.
We propose the first computationally tractable online algorithm with regret guarantees.
arXiv Detail & Related papers (2022-06-06T11:40:46Z) - FEM-based Real-Time Simulations of Large Deformations with Probabilistic
Deep Learning [1.2617078020344616]
We propose a highly efficient deep-learning surrogate framework that is able to predict the response of hyper-elastic bodies under load.
The framework takes the form of special convolutional neural network architecture, so-called U-Net, which is trained with force-displacement data.
arXiv Detail & Related papers (2021-11-02T20:05:22Z) - Reinforcement Learning Policies in Continuous-Time Linear Systems [0.0]
We present online policies that learn optimal actions fast by carefully randomizing the parameter estimates.
We prove sharp stability results for inexact system dynamics and tightly specify the infinitesimal regret caused by sub-optimal actions.
Our analysis sheds light on fundamental challenges in continuous-time reinforcement learning and suggests a useful cornerstone for similar problems.
arXiv Detail & Related papers (2021-09-16T00:08:50Z) - Gone Fishing: Neural Active Learning with Fisher Embeddings [55.08537975896764]
There is an increasing need for active learning algorithms that are compatible with deep neural networks.
This article introduces BAIT, a practical representation of tractable, and high-performing active learning algorithm for neural networks.
arXiv Detail & Related papers (2021-06-17T17:26:31Z) - Information Theoretic Model Predictive Q-Learning [64.74041985237105]
We present a novel theoretical connection between information theoretic MPC and entropy regularized RL.
We develop a Q-learning algorithm that can leverage biased models.
arXiv Detail & Related papers (2019-12-31T00:29:22Z)
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.