If you made any changes in Pure, your changes will be visible here soon.

Research Output 2013 2019

  • 7 Conference article
  • 5 Conference contribution
  • 4 Paper
  • 2 Article
2019

Dynamic programming for POMDP with jointly discrete and continuous state-spaces

Lee, D., He, N. & Hu, J., Jul 2019, 2019 American Control Conference, ACC 2019. Institute of Electrical and Electronics Engineers Inc., p. 1250-1255 6 p. 8815313. (Proceedings of the American Control Conference; vol. 2019-July).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Dynamic programming
Stochastic systems
Reinforcement learning
Learning algorithms
Linear systems

Point Process Estimation with Mirror Prox Algorithms

He, N., Harchaoui, Z., Wang, Y. & Song, L., Jan 1 2019, (Accepted/In press) In : Applied Mathematics and Optimization.

Research output: Contribution to journalArticle

Point Process
Mirror
Mirrors
Process Model
Saddle Point Problems

Stochastic primal-dual Q-learning algorithm for discounted mdps

Lee, D. & He, N., Jul 2019, 2019 American Control Conference, ACC 2019. Institute of Electrical and Electronics Engineers Inc., p. 4897-4902 6 p. 8815275. (Proceedings of the American Control Conference; vol. 2019-July).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Reinforcement learning
Learning algorithms
Hinges
Linear programming

Target-based temporal-difference learning

Lee, D. & He, N., Jan 1 2019, 36th International Conference on Machine Learning, ICML 2019. International Machine Learning Society (IMLS), p. 6619-6628 10 p. (36th International Conference on Machine Learning, ICML 2019; vol. 2019-June).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Learning algorithms
Reinforcement learning
learning
reinforcement
simulation
2018

Boosting the actor with dual critic

Dai, B., Shaw, A., He, N., Li, L. & Song, L., Jan 1 2018.

Research output: Contribution to conferencePaper

critic
Concretes
learning
performance

Coupled variational bayes via optimization embedding

Dai, B., Dai, H., He, N., Liu, W., Liu, Z., Chen, J., Xiao, L. & Song, L., Jan 1 2018, In : Advances in Neural Information Processing Systems. 2018-December, p. 9690-9700 11 p.

Research output: Contribution to journalConference article

Backpropagation

Predictive approximate Bayesian computation via saddle points

Yang, Y., Dai, B., Kiyavash, N. & He, N., Jan 1 2018, In : Advances in Neural Information Processing Systems. 2018-December, p. 10260-10270 11 p.

Research output: Contribution to journalConference article

Sampling
Experiments

Quadratic decomposable submodular function minimization

Li, P., He, N. & Milenkovic, O., Jan 1 2018, In : Advances in Neural Information Processing Systems. 2018-December, p. 1054-1064 11 p.

Research output: Contribution to journalConference article

Supervised learning
Convex optimization
Cones
Experiments

SBEED: Convergent reinforcement learning with nonlinear function approximation

Dai, B., Shaw, A., Li, L., Xiao, L., He, N., Liu, Z., Chen, J. & Song, L., Jan 1 2018, 35th International Conference on Machine Learning, ICML 2018. Krause, A. & Dy, J. (eds.). International Machine Learning Society (IMLS), p. 1809-1818 10 p. (35th International Conference on Machine Learning, ICML 2018; vol. 3).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Reinforcement learning
2017

Learning from conditional distributions via dual embeddings

Dai, B., He, N., Pan, Y., Boots, B. & Song, L., Jan 1 2017.

Research output: Contribution to conferencePaper

Reinforcement learning
Conditional Distribution
Invariance
Learning algorithms
Learning systems

Online learning for multivariate hawkes processes

Yang, Y., Etesami, J., He, N. & Kiyavash, N., Jan 1 2017, In : Advances in Neural Information Processing Systems. 2017-December, p. 4938-4947 10 p.

Research output: Contribution to journalConference article

Learning algorithms
Hilbert spaces

Stochastic generative hashing

Dai, B., Guo, R., Kumar, S., He, N. & Song, L., Jan 1 2017, 34th International Conference on Machine Learning, ICML 2017. International Machine Learning Society (IMLS), p. 1522-1538 17 p. (34th International Conference on Machine Learning, ICML 2017; vol. 2).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hash functions
Learning algorithms
Experiments
2016

Provable Bayesian inference via particle mirror descent

Dai, B., He, N., Dai, H. & Song, L., Jan 1 2016, p. 985-994. 10 p.

Research output: Contribution to conferencePaper

Bayesian inference
Descent
Mirror
Mirrors
Bayes Rule
2015

Mirror Prox algorithm for multi-term composite minimization and semi-separable problems

He, N., Juditsky, A. & Nemirovski, A., Jun 26 2015, In : Computational Optimization and Applications. 61, 2, p. 275-319 45 p., 9723.

Research output: Contribution to journalArticle

Mirror
Mirrors
Composite
Saddlepoint
Composite materials

Semi-Proximal Mirror-Prox for nonsmooth composite minimization

He, N. & Harchaoui, Z., Jan 1 2015, In : Advances in Neural Information Processing Systems. 2015-January, p. 3411-3419 9 p.

Research output: Contribution to journalConference article

Mirrors
Composite materials
Mathematical operators

Time-sensitive recommendation from recurrent user activities

Du, N., Wang, Y., He, N. & Song, L., Jan 1 2015, In : Advances in Neural Information Processing Systems. 2015-January, p. 3492-3500 9 p.

Research output: Contribution to journalConference article

Convex optimization
Recommender systems
Web services
2014

Scalable kernel methods via doubly stochastic gradients

Dai, B., Xie, B., He, N., Liang, Y., Raj, A., Balcan, M. F. & Song, L., Jan 1 2014, In : Advances in Neural Information Processing Systems. 4, January, p. 3041-3049 9 p.

Research output: Contribution to journalConference article

Neural networks
Convex optimization
Hilbert spaces
Convolution
2013

Stochastic alternating direction method of multipliers

Ouyang, H., He, N., Tran, L. Q. & Gray, A., Jan 1 2013, p. 80-88. 9 p.

Research output: Contribution to conferencePaper

multiplier
Learning systems
demand
Composite materials
learning