Dr Yunwen Lei

Dr Yunwen Lei

School of Computer Science
Lecturer in Computer Science

Contact details

Address
School of Computer Science
University of Birmingham
Edgbaston
Birmingham
B15 2TT
UK
Yunwen Lei is Lecturer in Computer Science working in Statistical Learning Theory, Machine Learning and Optimization.

 For more information please visit Yunwen’s personal webpage.

Qualifications

  • PhD in Computer Science, Wuhan University, 2014
  • Bsc in Mathematics, Hunan University, 2008

Postgraduate supervision

Machine Learning, Statistical Learning Theory, Optimization

Research

My research interests lie in the areas of machine learning and learning theory, with emphasis on the following topics: online learning, deep learning, optimization and extreme classification. In particular, I am interested in developing and analyzing scalable optimization methods for large-scale learning problems.

Publications

Recent publications

Article

Lei, Y, Hu, T & Tang, K 2021, 'Generalization performance of multi-pass stochastic gradient descent with convex loss functions', Journal of Machine Learning Research, vol. 22, 25. <https://jmlr.org/papers/v22/19-716.html>

Lei, Y & Tang, K 2021, 'Learning rates for stochastic gradient descent with nonconvex objectives', IEEE Transactions on Pattern Analysis and Machine Intelligence . https://doi.org/10.1109/TPAMI.2021.3068154

Lei, Y & Ying, Y 2021, 'Stochastic proximal AUC maximization', Journal of Machine Learning Research, vol. 22, 61. <https://jmlr.org/papers/volume22/19-418/19-418.pdf>

Lei, Y & Zhou, D-X 2020, 'Convergence of Online Mirror Descent', Applied and Computational Harmonic Analysis, vol. 48, no. 1, pp. 343-373.

Lei, Y, Hu, T, Li, G & Tang, K 2020, 'Stochastic Gradient Descent for Nonconvex Learning without Bounded Gradient Assumptions', IEEE Transactions on Neural Networks and Learning Systems, pp. 4394-4400. https://doi.org/10.1109/TNNLS.2019.2952219

Lin, S-B, Lei, Y & Zhou, D-X 2019, 'Boosted Kernel Ridge Regression: Optimal Learning Rates and Early Stopping', Journal of Machine Learning Research, vol. 20, no. 46, pp. 1-36.

Lei, Y, Dogan, U, Zhou, D-X & Kloft, M 2019, 'Data-dependent Generalization Bounds for Multi-class Classification', IEEE Transactions on Information Theory, vol. 65, no. 5, pp. 2995-3021.

Conference contribution

Wu, L, Ledent, A, Lei, Y & Kloft, M 2021, Fine-grained generalization analysis of vector-valued learning. in AAAI'21 Proceedings of the Thirty-fifth AAAI Conference on Artificial Intelligence. Proceedings of the AAAI Conference on Artificial Intelligence, no. 12, vol. 35, AAAI Press, pp. 10338-10346, 35th AAAI Conference on Artificial Intelligence, Vancouver, Canada, 2/02/21. <https://ojs.aaai.org/index.php/AAAI/article/view/17238>

Ledent, A, Mustafa, W, Lei, Y & Kloft, M 2021, Norm-based generalisation bounds for deep multi-class convolutional neural networks. in AAAI'21 Proceedings of the Thirty-fifth AAAI Conference on Artificial Intelligence. Proceedings of the AAAI Conference on Artificial Intelligence, no. 9, vol. 35, AAAI Press, pp. 8279-8287, 35th AAAI Conference on Artificial Intelligence, Vancouver, Canada, 2/02/21. <https://ojs.aaai.org/index.php/AAAI/article/view/17007>

Lei, Y & Ying, Y 2021, Sharper generalization bounds for learning with gradient-dominated objective functions. in International Conference on Learning Representations: ICLR 2021. OpenReview.net, pp. 1-23, The Ninth International Conference on Learning Representations, 3/05/21. <https://openreview.net/forum?id=r28GdiQF7vM>

Yang, Z, Lei, Y, Lyu, S & Ying, Y 2021, Stability and differential privacy of stochastic gradient descent for pairwise learning with non-smooth loss. in A Banerjee & K Fukumizu (eds), Proceedings of The 24th International Conference on Artificial Intelligence and Statistics. Proceedings of Machine Learning Research, vol. 130, pp. 2026-2034, The 24th International Conference on Artificial Intelligence and Statistics, 13/04/21. <http://proceedings.mlr.press/v130/yang21c.html>

Lei, Y, Yang, Z, Yang, T & Ying, Y 2021, Stability and generalization of stochastic gradient methods for minimax problems. in M Meila & T Zhang (eds), Proceedings of ICML 2021. Proceedings of Machine Learning Research, vol. 139, JMLR , pp. 6175-6186, The Thirty-eighth International Conference on Machine Learning , 18/07/21. <http://proceedings.mlr.press/v139/lei21a.html>

Lei, Y & Ying, Y 2020, Fine-Grained Analysis of Stability and Generalization for Stochastic Gradient Descent. in International Conference on Machine Learning.

Lei, Y, Ledent, A & Kloft, M 2020, Sharper Generalization Bounds for Pairwise Learning. in Advances in Neural Information Processing Systems.

Lei, Y, Yang, P, Tang, K & Zhou, D-X 2019, Optimal Stochastic and Online Learning with Individual Iterates. in Advances in Neural Information Processing Systems. pp. 5416-5426.

View all publications in research portal