Fetching the paper…
Reading the bibliography…
Application of the replica exchange (i.e., parallel tempering) technique to Langevin Monte Carlo algorithms, especially stochastic gradient Langevin dynamics (SGLD), has scored great success in non-convex learning problems, but one potential limitation is the computational cost caused by running multiple chains.
Criteria for recurrence and existence of invariant measures for multidimensional diffusions
Bhattacharya, R., 1978 · 1978
Earlier work this paper cites.
Comments on “representations of knowledge in complex systems” by u. grenander and mi miller
Besag, J., 1994 · 1994
Earlier work this paper cites.
Exponential convergence of Langevin distributions and their discrete approximations
Roberts, G.O., Tweedie, R.L., 1996 · 1996
Earlier work this paper cites.
Optimal scaling of discrete approximations to Langevin diffusions
Roberts, G.O., Rosenthal, J.S., 1998 · 1998
Earlier work this paper cites.
Langevin diffusions and Metropolis-Hastings algorithms
Roberts, G.O., Stramer, O., 2002 · 2002
Earlier work this paper cites.
Preconditioning Markov chain Monte Carlo simulations using coarse-scale models
Efendiev, Y., Hou, T., Luo, W., 2006 · 2006
Earlier work this paper cites.
The pseudo-marginal approach for efficient Monte Carlo computations
Andrieu, C., Roberts, G.O., 2009 · 2009
Earlier work this paper cites.
Strengths and weaknesses of parallel tempering
Machta, J., 2009 · 2009
Earlier work this paper cites.
Importance tempering
Gramacy, R., Samworth, R., King, R., 2010 · 2010
Earlier work this paper cites.
Inverse problems: a Bayesian perspective
Stuart, A.M., 2010 · 2010
Earlier work this paper cites.
Multi-agent reinforcement learning accelerated MCMC on multiscale inversion problem
Chung, E., Efendiev, Y., Leung, W.T., Pun, S.M., Zhang, Z., 2020 · 2011
Cited alongside, same era.
Bayesian learning via stochastic gradient Langevin dynamics, in: Proceedings of the 28th international conference on machine learning (ICML-11), Citeseer. pp. 681–688
Welling, M., Teh, Y.W., 2011 · 2011
Cited alongside, same era.
On the infinite swapping limit for parallel tempering
Dupuis, P., Liu, Y., Plattner, N., Doll, J.D., 2012 · 2012
Cited alongside, same era.
Consistency and fluctuations for stochastic gradient Langevin dynamics
Teh, Y.W., Thiery, A.H., Vollmer, S.J., 2016 · 2016
Cited alongside, same era.
Exploration of the (non-)asymptotic bias and variance of stochastic gradient Langevin dynamics
Vollmer, S.J., Zygalakis, K.C., Teh, Y.W., 2016 · 2016
Cited alongside, same era.
Non-asymptotic analysis of fractional Langevin Monte Carlo for non-convex optimization, in: International Conference on Machine Learning, PMLR. pp. 4810–4819
Nguyen, T.H., Simsekli, U., Richard, G., 2019 · 2019
Later among the works it cites.
High-dimensional statistics: A non-asymptotic viewpoint. volume 48
Wainwright, M.J., 2019 · 2019
Later among the works it cites.
A hitting time analysis of stochastic gradient Langevin dynamics, in: Conference on Learning Theory, PMLR. pp. 1980–2022
Zhang, Y., Liang, P., Charikar, M., 2017 · 2019
Later among the works it cites.
Non-convex learning via replica exchange stochastic gradient MCMC, in: International Conference on Machine Learning, PMLR. pp. 2474–2483
Deng, W., Feng, Q., Gao, L., Liang, F., Lin, G., 2020 · 2020
Later among the works it cites.
Fractional underdamped Langevin dynamics: Retargeting sgd with momentum under heavy-tailed gradient noise, in: International Conference on Machine Learning, PMLR. pp. 8970–8980
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Further and stronger analogy between sampling and optimization: Langevin Monte Carlo and gradient descent, in: Conference on Learning Theory, PMLR. pp. 678–689
Dalalyan, A., 2017 · 2017
Cited alongside, same era.
Non-convex learning via stochastic gradient Langevin dynamics: a nonasymptotic analysis, in: Conference on Learning Theory, PMLR. pp. 1674–1703
Raginsky, M., Rakhlin, A., Telgarsky, M., 2017 · 2017
Cited alongside, same era.
Log-concave sampling: Metropolis-Hastings algorithms are fast!, in: Conference on learning theory, PMLR. pp. 793–797
Dwivedi, R., Chen, Y., Wainwright, M.J., Yu, B., 2018 · 2018
Cited alongside, same era.
Accelerating nonconvex learning via replica exchange Langevin diffusion, in: 7th International Conference on Learning Representations, ICLR 2019
Chen, Y., Chen, J., Dong, J., Peng, J., Wang, Z., 2019 · 2019
Cited alongside, same era.
User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
Dalalyan, A.S., Karagulyan, A., 2019 · 2019
Cited alongside, same era.
Simsekli, U., Zhu, L., Teh, Y.W., Gurbuzbalaban, M., 2020 · 2020
Later among the works it cites.
Lin, G., Moya, C., Zhang, Z., 2021 · 2021
Later among the works it cites.
Multi-variance replica exchange SGMCMC for inverse and forward problems via Bayesian PINN
Lin, G., Wang, Y., Zhang, Z., 2022 · 2022
Later among the works it cites.
Na, O., Zhang, Z., Lin, G., 2022 · 2022
Later among the works it cites.
Mixing of Hamiltonian Monte Carlo on strongly log-concave distributions: Continuous dynamics
Mangoubi, O., Smith, A., 2021 · 2045
Closest in time.