Related papers: The Bayesian Learning Rule

The Bayesian Learning Rule

URL: http://arxiv.org/abs/2107.04562v4
Date: Sat, 8 Jun 2024 04:07:38 GMT
Title: The Bayesian Learning Rule
Authors: Mohammad Emtiyaz Khan, Håvard Rue,
Abstract summary: We show that many machine-learning algorithms are specific instances of a single algorithm called the emphBayesian learning rule The rule, derived from Bayesian principles, yields a wide-range of algorithms from fields such as optimization, deep learning, and graphical models.
Score: 14.141964578853262
License: http://creativecommons.org/licenses/by/4.0/
Abstract: We show that many machine-learning algorithms are specific instances of a single algorithm called the \emph{Bayesian learning rule}. The rule, derived from Bayesian principles, yields a wide-range of algorithms from fields such as optimization, deep learning, and graphical models. This includes classical algorithms such as ridge regression, Newton's method, and Kalman filter, as well as modern deep-learning algorithms such as stochastic-gradient descent, RMSprop, and Dropout. The key idea in deriving such algorithms is to approximate the posterior using candidate distributions estimated by using natural gradients. Different candidate distributions result in different algorithms and further approximations to natural gradients give rise to variants of those algorithms. Our work not only unifies, generalizes, and improves existing algorithms, but also helps us design new ones.

Related papers

Bregman-divergence-based Arimoto-Blahut algorithm [53.64687146666141]
We generalize the Arimoto-Blahut algorithm to a general function defined over Bregman-divergence system. We propose a convex-optimization-free algorithm that can be applied to classical and quantum rate-distortion theory.
arXiv Detail & Related papers (2024-08-10T06:16:24Z)
Learning the Positions in CountSketch [49.57951567374372]
We consider sketching algorithms which first compress data by multiplication with a random sketch matrix, and then apply the sketch to quickly solve an optimization problem. In this work, we propose the first learning-based algorithms that also optimize the locations of the non-zero entries.
arXiv Detail & Related papers (2023-06-11T07:28:35Z)
Dual Algorithmic Reasoning [9.701208207491879]
We propose to learn algorithms by exploiting duality of the underlying algorithmic problem. We demonstrate that simultaneously learning the dual definition of these optimisation problems in algorithmic learning allows for better learning. We then validate the real-world utility of our dual algorithmic reasoner by deploying it on a challenging brain vessel classification task.
arXiv Detail & Related papers (2023-02-09T08:46:23Z)
Structure learning in polynomial time: Greedy algorithms, Bregman information, and exponential families [12.936601424755944]
We study a general greedy score-based algorithm for learning DAGs. We show how recent algorithm-time algorithms for learning DAG models are a special case of this algorithm. This observation suggests new score functions and optimality conditions based on the duality between Bregman divergences and exponential families.
arXiv Detail & Related papers (2021-10-10T06:37:51Z)
Approximate Newton policy gradient algorithms [18.032678371017198]
This paper proposes an approximate Newton method for the policy gradient algorithm with entropy regularization. We prove that all these algorithms enjoy Newton-type quadratic convergence and that the corresponding gradient flow converges globally to the optimal solution.
arXiv Detail & Related papers (2021-10-05T23:07:12Z)
Provably Faster Algorithms for Bilevel Optimization [54.83583213812667]
Bilevel optimization has been widely applied in many important machine learning applications. We propose two new algorithms for bilevel optimization. We show that both algorithms achieve the complexity of $mathcalO(epsilon-1.5)$, which outperforms all existing algorithms by the order of magnitude.
arXiv Detail & Related papers (2021-06-08T21:05:30Z)
Evolving Reinforcement Learning Algorithms [186.62294652057062]
We propose a method for meta-learning reinforcement learning algorithms. The learned algorithms are domain-agnostic and can generalize to new environments not seen during training. We highlight two learned algorithms which obtain good generalization performance over other classical control tasks, gridworld type tasks, and Atari games.
arXiv Detail & Related papers (2021-01-08T18:55:07Z)
Efficient Computation of Expectations under Spanning Tree Distributions [67.71280539312536]
We propose unified algorithms for the important cases of first-order expectations and second-order expectations in edge-factored, non-projective spanning-tree models. Our algorithms exploit a fundamental connection between gradients and expectations, which allows us to derive efficient algorithms.
arXiv Detail & Related papers (2020-08-29T14:58:26Z)
Model Selection in Contextual Stochastic Bandit Problems [51.94632035240787]
We develop a meta-algorithm that selects between base algorithms. We show through a lower bound that even when one of the base algorithms has $O(sqrtT)$ regret, in general it is impossible to get better than $Omega(sqrtT)$ regret.
arXiv Detail & Related papers (2020-03-03T18:46:34Z)

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