Publications (sorted by topics)

Convex Optimization Formulation of Neural Networks

• Emi Zeger, Yifei Wang, Aaron Mishkin, Tolga Ergen, Emmanuel Candes, Mert Pilanci, A Library of Mirrors: Deep Neural Nets in Low Dimensions are Convex Lasso Models with Reflection Features, (paper)

• Yifei Wang, Mert Pilanci, Polynomial-Time Solutions for ReLU Network Training: A Complexity Classification via Max-Cut and Zonotopes, (paper)

• Yifei Wang, Tolga Ergen, Mert Pilanci, Parallel Deep Neural Networks Have Zero Duality Gap, International Conference on Learning Representations (ICLR) 2023 Poster, (paper)

• Yifei Wang, Yixuan Hua, Emmanuel Candes, Mert Pilanci, Overparameterized ReLU Neural Networks Learn the Simplest Models: Neural Isometry and Exact Recovery, (paper), (code)

• Yifei Wang, Peng Chen, Mert Pilanci, Wuchen Li, Optimal Neural Network Approximation of Wasserstein Gradient Direction via Convex Optimization, (paper), (slide), (talk video at SIAM MDS22)

• Yifei Wang, Mert Pilanci, The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program, International Conference on Learning Representations (ICLR) 2022 Poster, (paper), (poster), (slide)

• Yifei Wang, Jonathan Lacotte, Mert Pilanci, The Hidden Convex Optimization Landscape of Two-Layer ReLU Neural Networks: an Exact Characterization of the Optimal Solutions, International Conference on Learning Representations (ICLR) 2022 Oral, (paper), (poster), (slide)

Blockchains and decentralized consensus

• Ertem Nusret Tas, David Tse, Yifei Wang, A Circuit Approach to Constructing Blockchains on Blockchains, (paper)

Multi-Armed Bandits and Statisical Inference

• Yifei Wang, Tavor Baharav, Yanjun Han, Jiantao Jiao, David Tse, Beyond the Best: Distribution Functional Estimation in Infinite-Armed Bandits, Conference on Neural Information Processing Systems (NeurIPS) 2022, (paper), (slide), (poster)

Wasserstein Gradient Flow for Bayesian Inference

• Yifei Wang, Peng Chen, Mert Pilanci, Wuchen Li, Optimal Neural Network Approximation of Wasserstein Gradient Direction via Convex Optimization, (paper), (slide), (talk video at SIAM MDS22)

• Alex Leviyev, Joshua Chen, Yifei Wang, Omar Ghattas, Aaron Zimmerman, A stochastic Stein variational Newton Method, (paper), (code)

• Yifei Wang, Peng Chen, Wuchen Li, Projected Wasserstein gradient descent for high-dimensional Bayesian inference, SIAM on Uncertainty Quantification (2022) (paper), (code), (talk video at SIAM MDS22)

• Yifei Wang, Wuchen Li, Accelerated Information Gradient flow, Journal of Scientific Computing (2022), https:doi.org10.1007s10915-021-01709-3 (paper), (website), (code), (talk video at SIAM MDS22)

• Yifei Wang, Wuchen Li, Information Newton's flow: second-order optimization method in probability space, (paper), (code), (talk video at SIAM MDS22)

Efficient Optimization Algorithms

• Yifei Wang, Kangkang Deng, Haoyang Li, Zaiwen Wen, A Decomposition Augmented Lagrangian Method for Low-rank Semidefinite Programming, SIAM on Optimization (2023), (paper)

• Jonathan Lacotte, Yifei Wang, Mert Pilanci, Adaptive Newton Sketch: Linear-time Optimization with Quadratic Convergence and Effective Hessian Dimensionality, International Conference on Machine Learning (ICML) 2021 Poster, (paper), (code), (poster), (slide)

• Yifei Wang, Mert Pilanci, Sketching the Krylov Subspace: Faster Computation of the Entire Ridge Regularization path, to appear on Journal of Supercomputing 2023. (paper), (code)

• Yifei Wang, Zeyu Jia, Zaiwen Wen, Search Direction Correction with Normalized Gradient Makes First-Order Methods Faster, SIAM on Scientific Computing (2021), Vol. 43, No. 5, pp. A3184-A3211, (paper), (slide)