PAC-Bayesian theory for stochastic LTI systems

• URL: http://arxiv.org/abs/2103.12866v1
• Date: Tue, 23 Mar 2021 21:59:21 GMT
• Title: PAC-Bayesian theory for stochastic LTI systems
• Authors: Deividas Eringis and John Leth and Zheng-Hua Tan and Rafal Wisniewski and Mihaly Petreczky
• Abstract summary: We derive a PAC-Bayesian error bound for autonomous LTI state-space models. The motivation for deriving such error bounds is that they will allow deriving similar error bounds for more general dynamical systems.
• Score: 15.01136076871549
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper we derive a PAC-Bayesian error bound for autonomous stochastic LTI state-space models. The motivation for deriving such error bounds is that they will allow deriving similar error bounds for more general dynamical systems, including recurrent neural networks. In turn, PACBayesian error bounds are known to be useful for analyzing machine learning algorithms and for deriving new ones.

Related papers

• A PAC-Bayesian Perspective on the Interpolating Information Criterion [54.548058449535155]
  We show how a PAC-Bayes bound is obtained for a general class of models, characterizing factors which influence performance in the interpolating regime. We quantify how the test error for overparameterized models achieving effectively zero training error depends on the quality of the implicit regularization imposed by e.g. the combination of model, parameter-initialization scheme.
  arXiv  Detail & Related papers  (2023-11-13T01:48:08Z)
• PAC-Bayesian bounds for learning LTI-ss systems with input from empirical loss [13.251009291060992]
  We derive a Probably Approxilmately Correct(PAC)-Bayesian error bound for linear time-invariant (LTI) dynamical systems with inputs. Such bounds are widespread in machine learning, and they are useful for characterizing the predictive power of models learned from finitely many data points.
  arXiv  Detail & Related papers  (2023-03-29T16:06:07Z)
• PAC-Bayesian-Like Error Bound for a Class of Linear Time-Invariant Stochastic State-Space Models [13.251009291060992]
  We derive a PAC-Bayesian-Like error bound for a class of dynamical systems with inputs. We discuss various consequences of this error bound.
  arXiv  Detail & Related papers  (2022-12-30T17:37:33Z)
• Demystify Optimization and Generalization of Over-parameterized PAC-Bayesian Learning [20.295960197612743]
  PAC-Bayesian is an analysis framework where the training error can be expressed as the weighted average of the hypotheses in the posterior distribution. We show that when PAC-Bayes learning is applied, the convergence result corresponds to solving a kernel ridge regression. We further characterize the uniform PAC-Bayesian generalization bound which improves over the Rademacher complexity-based bound for non-probabilistic neural network.
  arXiv  Detail & Related papers  (2022-02-04T03:49:11Z)
• Consistency of mechanistic causal discovery in continuous-time using Neural ODEs [85.7910042199734]
  We consider causal discovery in continuous-time for the study of dynamical systems. We propose a causal discovery algorithm based on penalized Neural ODEs.
  arXiv  Detail & Related papers  (2021-05-06T08:48:02Z)
• Information Complexity and Generalization Bounds [0.0]
  We show a unifying picture of PAC-Bayesian and mutual information-based upper bounds on randomized learning algorithms. We discuss two practical examples for learning with neural networks, namely, Entropy- and PAC-Bayes- SGD.
  arXiv  Detail & Related papers  (2021-05-04T20:37:57Z)
• A General Framework for the Practical Disintegration of PAC-Bayesian Bounds [2.516393111664279]
  We introduce new PAC-Bayesian generalization bounds that have the originality to provide disintegrated bounds. Our bounds are easily optimizable and can be used to design learning algorithms.
  arXiv  Detail & Related papers  (2021-02-17T09:36:46Z)
• Relaxing the Constraints on Predictive Coding Models [62.997667081978825]
  Predictive coding is an influential theory of cortical function which posits that the principal computation the brain performs is the minimization of prediction errors. Standard implementations of the algorithm still involve potentially neurally implausible features such as identical forward and backward weights, backward nonlinear derivatives, and 1-1 error unit connectivity. In this paper, we show that these features are not integral to the algorithm and can be removed either directly or through learning additional sets of parameters with Hebbian update rules without noticeable harm to learning performance.
  arXiv  Detail & Related papers  (2020-10-02T15:21:37Z)
• An Ode to an ODE [78.97367880223254]
  We present a new paradigm for Neural ODE algorithms, called ODEtoODE, where time-dependent parameters of the main flow evolve according to a matrix flow on the group O(d) This nested system of two flows provides stability and effectiveness of training and provably solves the gradient vanishing-explosion problem.
  arXiv  Detail & Related papers  (2020-06-19T22:05:19Z)
• Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems [83.98774574197613]
  We take one of the simplest inference methods, a truncated max-product Belief propagation, and add what is necessary to make it a proper component of a deep learning model. This BP-Layer can be used as the final or an intermediate block in convolutional neural networks (CNNs) The model is applicable to a range of dense prediction problems, is well-trainable and provides parameter-efficient and robust solutions in stereo, optical flow and semantic segmentation.
  arXiv  Detail & Related papers  (2020-03-13T13:11:35Z)
• Local Propagation in Constraint-based Neural Network [77.37829055999238]
  We study a constraint-based representation of neural network architectures. We investigate a simple optimization procedure that is well suited to fulfil the so-called architectural constraints.
  arXiv  Detail & Related papers  (2020-02-18T16:47:38Z)

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.