paper-with-me

홈 › Papers

Exponential Reduction in Sample Complexity with Learning of Ising Model Dynamics

2021-04-02 · Arkopal Dutt, Andrey Y. Lokhov, Marc Vuffray, Sidhant Misra

The usual setting for learning the structure and parameters of a graphical model assumes the availability of independent samples produced from the corresponding multivariate probability distribution. However, for many models the mixing time of the respective Markov chain can be very large and i.i.d. samples may not be obtained. We study the problem of reconstructing binary graphical models from correlated samples produced by a dynamical process, which is natural in many applications. We analyze the sample complexity of two estimators that are based on the interaction screening objective and the conditional likelihood loss. We observe that for samples coming from a dynamical process far from equilibrium, the sample complexity reduces exponentially compared to a dynamical process that mixes quickly.

📄 PDF Abstract BibTeX arXiv:2104.00995

Code (1)

lanl-ansi/learning-ising-dynamics 공식 구현

Similar Papers 제목 키워드 기반

A Unified Approach to Learning Ising Models: Beyond Independence and Bounded Width

2023-11-15 · Jason Gaitonde, Elchanan Mossel

We revisit the problem of efficiently learning the underlying parameters of Ising models from data. Current algorithmic approaches achieve essentially optimal sample complexity when given i.i.d. samples from the stationa…

regression

MoCoDA: Model-based Counterfactual Data Augmentation

2022-10-20 · Silviu Pitis, Elliot Creager, Ajay Mandlekar, Animesh Garg

The number of states in a dynamic process is exponential in the number of objects, making reinforcement learning (RL) difficult in complex, multi-object domains. For agents to scale to the real world, they will need to r…

counterfactualData AugmentationmodelOffline RL+1

Mean-Field Langevin Dynamics for Signed Measures via a Bilevel Approach

2024-06-24 · Guillaume Wang, Alireza Mousavi-Hosseini, Lénaïc Chizat

Mean-field Langevin dynamics (MLFD) is a class of interacting particle methods that tackle convex optimization over probability measures on a manifold, which are scalable, versatile, and enjoy computational guarantees. H…

Replicable Learning of Large-Margin Halfspaces

2024-02-21 · Alkis Kalavasis, Amin Karbasi, Kasper Green Larsen, Grigoris Velegkas 외

We provide efficient replicable algorithms for the problem of learning large-margin halfspaces. Our results improve upon the algorithms provided by Impagliazzo, Lei, Pitassi, and Sorrell [STOC, 2022]. We design the first…

Mixing Time of the Proximal Sampler in Relative Fisher Information via Strong Data Processing Inequality

2025-02-08 · Andre Wibisono

We study the mixing time guarantee for sampling in relative Fisher information via the Proximal Sampler algorithm, which is an approximate proximal discretization of the Langevin dynamics. We show that when the target pr…