Wenbo Gao
PhD student, Department of Industrial Engineering and Operations Research, Columbia University
Contact: wg2279 (at) columbia (dot) edu
Publications
* denotes equal contribution
- Wenbo Gao*, Laura Graesser*, Krzysztof Choromanski*, Xingyou Song, Nevena Lazic, Pannag Sanketi, Vikas Sindhwani, and Navdeep Jaitly. Robotic Table Tennis with Model-Free Reinforcement Learning. [pdf][arXiv]
To appear in IROS 2020.
- Xingyou Song, Yuxiang Yang, Krzysztof Choromanski, Ken Caluwaerts, Wenbo Gao, Chelsea Finn, and Jie Tan. Rapidly Adaptable Legged Robots via Evolutionary Meta-Learning. [arXiv]
To appear in IROS 2020.
- Wenbo Gao, Donald Goldfarb, and Frank E. Curtis. ADMM for Multiaffine Constrained Optimization. [pdf][arXiv]
Optimization Methods and Software, 35-2 (2020), pp. 257-303.
- Xingyou Song*, Wenbo Gao*, Yuxiang Yang, Krzysztof Choromanski, Aldo Pacchiano, and Yunhao Tang. ES-MAML: Simple Hessian-Free Meta Learning. [arXiv][OpenReview]
ICLR 2020.
Short version accepted as a spotlight in NeurIPS Workshop on Meta-Learning 2019.
- Yunfei Teng*, Wenbo Gao*, Francois Chalus, Anna Choromanska, Donald Goldfarb, and Adrian Weller. Leader Stochastic Gradient Descent for Distributed Training of Deep Learning Models. [pdf][arXiv][nips.cc]
Advances in Neural Information Processing Systems (NeurIPS) 32, 2019.
- Wenbo Gao and Donald Goldfarb. Block BFGS Methods. [pdf][arXiv][code]
SIAM Journal on Optimization 28-2 (2018), pp. 1205-1231.
- Wenbo Gao and Donald Goldfarb. Quasi-Newton Methods: Superlinear Convergence Without Line Searches for Self-Concordant Functions. [pdf][arXiv][code]
Optimization Methods and Software, 34-1 (2018), pp.194-217.
- Chaoxu Zhou*, Wenbo Gao*, and Donald Goldfarb. Stochastic Adaptive Quasi-Newton Methods for Minimizing Expected Values. [pdf][supplementary][PMLR]
Proceedings of the 34th ICML, PMLR 70:4150-4159, 2017.
Submitted
Preprints
- Wenbo Gao and David Wagner. Highly symmetric matroids, the strong Rayleigh property, and sums of squares. [arXiv]
Miscellaneous
- Dishonest Stopping, or: Bayesians and Bad Experiments [pdf]
A discussion of a Bayesian inference problem discussed by David Speyer here. Mostly for self-edification.
- A Complicated Solution to an Easy Problem [pdf]
Why everyone should learn combinatorics /sarc.
- Equivalent Simplicial Polytopes with Integer Vertices [pdf]
A proof of a folklore result in polytope theory.
- Cycles in Random Permutations [pdf]
Some double counting proofs of identities from this post of Terry Tao.
- Understanding the Primal and Dual Simplex Method [pdf]
Expository note for IEOR students learning about linear programming.