Learning to Explore for Stochastic Gradient MCMC

• URL: http://arxiv.org/abs/2408.09140v1
• Date: Sat, 17 Aug 2024 08:36:42 GMT
• Title: Learning to Explore for Stochastic Gradient MCMC
• Authors: SeungHyun Kim, Seohyeon Jung, Seonghyeon Kim, Juho Lee,
• Abstract summary: We propose a meta-learning strategy to build glssgmcmc which can efficiently explore the multi-modal target distributions. Our algorithm allows the learned SGMCMC to quickly explore the high-density region of the posterior landscape.
• Score: 15.286308920219446
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Bayesian Neural Networks(BNNs) with high-dimensional parameters pose a challenge for posterior inference due to the multi-modality of the posterior distributions. Stochastic Gradient MCMC(SGMCMC) with cyclical learning rate scheduling is a promising solution, but it requires a large number of sampling steps to explore high-dimensional multi-modal posteriors, making it computationally expensive. In this paper, we propose a meta-learning strategy to build \gls{sgmcmc} which can efficiently explore the multi-modal target distributions. Our algorithm allows the learned SGMCMC to quickly explore the high-density region of the posterior landscape. Also, we show that this exploration property is transferrable to various tasks, even for the ones unseen during a meta-training stage. Using popular image classification benchmarks and a variety of downstream tasks, we demonstrate that our method significantly improves the sampling efficiency, achieving better performance than vanilla \gls{sgmcmc} without incurring significant computational overhead.

Related papers

• Multimodal Learned Sparse Retrieval with Probabilistic Expansion Control [66.78146440275093]
  Learned retrieval (LSR) is a family of neural methods that encode queries and documents into sparse lexical vectors. We explore the application of LSR to the multi-modal domain, with a focus on text-image retrieval. Current approaches like LexLIP and STAIR require complex multi-step training on massive datasets. Our proposed approach efficiently transforms dense vectors from a frozen dense model into sparse lexical vectors.
  arXiv  Detail & Related papers  (2024-02-27T14:21:56Z)
• Scalable Meta-Learning with Gaussian Processes [11.528128570533273]
  We develop ScaML-GP, a modular GP model for meta-learning that is scalable in the number of tasks. Our core contribution is a carefully designed multi-task kernel that enables hierarchical training and task scalability. In synthetic and real-world meta-learning experiments, we demonstrate that ScaML-GP can learn efficiently both with few and many meta-tasks.
  arXiv  Detail & Related papers  (2023-12-01T17:25:10Z)
• A Probabilistic Approach to Self-Supervised Learning using Cyclical Stochastic Gradient MCMC [8.027994148508844]
  We present a practical self-supervised learning method with Cyclical Gradient Hamiltonian Monte Carlo (cSGHMC) Within this framework, we place a prior over the parameters of a self-supervised learning model and use cSGHMC to approximate the high dimensional and multimodal posterior distribution over the embeddings. We provide experimental results on multiple classification tasks on four challenging datasets.
  arXiv  Detail & Related papers  (2023-08-02T16:52:56Z)
• Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP [81.00800920928621]
  We study representation learning in partially observable Markov Decision Processes (POMDPs) We first present an algorithm for decodable POMDPs that combines maximum likelihood estimation (MLE) and optimism in the face of uncertainty (OFU) We then show how to adapt this algorithm to also work in the broader class of $gamma$-observable POMDPs.
  arXiv  Detail & Related papers  (2023-06-21T16:04:03Z)
• Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo [104.9535542833054]
  We present a scalable and effective exploration strategy based on Thompson sampling for reinforcement learning (RL) We instead directly sample the Q function from its posterior distribution, by using Langevin Monte Carlo. Our approach achieves better or similar results compared with state-of-the-art deep RL algorithms on several challenging exploration tasks from the Atari57 suite.
  arXiv  Detail & Related papers  (2023-05-29T17:11:28Z)
• Multitask Adaptation by Retrospective Exploration with Learned World Models [77.34726150561087]
  We propose a meta-learned addressing model called RAMa that provides training samples for the MBRL agent taken from task-agnostic storage. The model is trained to maximize the expected agent's performance by selecting promising trajectories solving prior tasks from the storage.
  arXiv  Detail & Related papers  (2021-10-25T20:02:57Z)
• Memory-Based Optimization Methods for Model-Agnostic Meta-Learning and Personalized Federated Learning [56.17603785248675]
  Model-agnostic meta-learning (MAML) has become a popular research area. Existing MAML algorithms rely on the episode' idea by sampling a few tasks and data points to update the meta-model at each iteration. This paper proposes memory-based algorithms for MAML that converge with vanishing error.
  arXiv  Detail & Related papers  (2021-06-09T08:47:58Z)
• ConCrete MAP: Learning a Probabilistic Relaxation of Discrete Variables for Soft Estimation with Low Complexity [9.62543698736491]
  ConCrete MAP Detection (CMD) is an iterative detection algorithm for large inverse linear problems. We show CMD to feature a promising performance complexity trade-off compared to SotA. Notably, we demonstrate CMD's soft outputs to be reliable for decoders.
  arXiv  Detail & Related papers  (2021-02-25T09:54:25Z)
• An adaptive Hessian approximated stochastic gradient MCMC method [12.93317525451798]
  We present an adaptive Hessian approximated gradient MCMC method to incorporate local geometric information while sampling from the posterior. We adopt a magnitude-based weight pruning method to enforce the sparsity of the network.
  arXiv  Detail & Related papers  (2020-10-03T16:22:15Z)
• Non-convex Learning via Replica Exchange Stochastic Gradient MCMC [25.47669573608621]
  We propose an adaptive replica exchange SGMCMC (reSGMCMC) to automatically correct the bias and study the corresponding properties. Empirically, we test the algorithm through extensive experiments on various setups and obtain the results.
  arXiv  Detail & Related papers  (2020-08-12T15:02:59Z)
• Improving Sampling Accuracy of Stochastic Gradient MCMC Methods via Non-uniform Subsampling of Gradients [54.90670513852325]
  We propose a non-uniform subsampling scheme to improve the sampling accuracy. EWSG is designed so that a non-uniform gradient-MCMC method mimics the statistical behavior of a batch-gradient-MCMC method. In our practical implementation of EWSG, the non-uniform subsampling is performed efficiently via a Metropolis-Hastings chain on the data index.
  arXiv  Detail & Related papers  (2020-02-20T18:56:18Z)

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.