no code implementations • ICLR 2019 • Huizhuo Yuan, Chris Junchi Li, Yuhao Tang, Yuren Zhou
In this paper, we propose the StochAstic Recursive grAdient Policy Optimization (SARAPO) algorithm which is a novel variance reduction method on Trust Region Policy Optimization (TRPO).
no code implementations • 22 Apr 2024 • Chris Junchi Li
Stochastic versions of the alternating direction method of multiplier (ADMM) and its variants play a key role in many modern large-scale machine learning problems.
no code implementations • 30 Jun 2023 • Haikuo Yang, Luo Luo, Chris Junchi Li, Michael I. Jordan
We present a method for solving general nonconvex-strongly-convex bilevel optimization problems.
no code implementations • 31 Oct 2022 • Chris Junchi Li, Angela Yuan, Gauthier Gidel, Quanquan Gu, Michael I. Jordan
AG-OG is the first single-call algorithm with optimal convergence rates in both deterministic and stochastic settings for bilinearly coupled minimax optimization problems.
no code implementations • 30 Sep 2022 • Zixiang Chen, Chris Junchi Li, Angela Yuan, Quanquan Gu, Michael I. Jordan
With the increasing need for handling large state and action spaces, general function approximation has become a key technique in reinforcement learning (RL).
no code implementations • 10 Aug 2022 • Chris Junchi Li, Dongruo Zhou, Quanquan Gu, Michael I. Jordan
We consider learning Nash equilibria in two-player zero-sum Markov Games with nonlinear function approximation, where the action-value function is approximated by a function in a Reproducing Kernel Hilbert Space (RKHS).
no code implementations • 17 Jun 2022 • Simon S. Du, Gauthier Gidel, Michael I. Jordan, Chris Junchi Li
We consider the smooth convex-concave bilinearly-coupled saddle-point problem, $\min_{\mathbf{x}}\max_{\mathbf{y}}~F(\mathbf{x}) + H(\mathbf{x},\mathbf{y}) - G(\mathbf{y})$, where one has access to stochastic first-order oracles for $F$, $G$ as well as the bilinear coupling function $H$.
no code implementations • 29 Dec 2021 • Chris Junchi Li, Michael I. Jordan
Motivated by the problem of online canonical correlation analysis, we propose the \emph{Stochastic Scaled-Gradient Descent} (SSGD) algorithm for minimizing the expectation of a stochastic function over a generic Riemannian manifold.
no code implementations • 30 Jun 2021 • Chris Junchi Li, Yaodong Yu, Nicolas Loizou, Gauthier Gidel, Yi Ma, Nicolas Le Roux, Michael I. Jordan
We study the stochastic bilinear minimax optimization problem, presenting an analysis of the same-sample Stochastic ExtraGradient (SEG) method with constant step size, and presenting variations of the method that yield favorable convergence.
no code implementations • 28 Dec 2020 • Chris Junchi Li, Michael I. Jordan
For estimating one component, we provide a dynamics-based analysis to prove that our online tensorial ICA algorithm with a specific choice of stepsize achieves a sharp finite-sample error bound.
no code implementations • 28 Aug 2020 • Chris Junchi Li, Wenlong Mou, Martin J. Wainwright, Michael. I. Jordan
We study the problem of solving strongly convex and smooth unconstrained optimization problems using stochastic first-order algorithms.
no code implementations • 9 Apr 2020 • Wenlong Mou, Chris Junchi Li, Martin J. Wainwright, Peter L. Bartlett, Michael. I. Jordan
When the matrix $\bar{A}$ is Hurwitz, we prove a central limit theorem (CLT) for the averaged iterates with fixed step size and number of iterations going to infinity.
no code implementations • 7 Mar 2020 • Xiang Zhou, Huizhuo Yuan, Chris Junchi Li, Qingyun Sun
In this work, we put different variants of stochastic ADMM into a unified form, which includes standard, linearized and gradient-based ADMM with relaxation, and study their dynamics via a continuous-time model approach.
no code implementations • NeurIPS 2019 • Huizhuo Yuan, Xiangru Lian, Chris Junchi Li, Ji Liu, Wenqing Hu
Stochastic compositional optimization arises in many important machine learning tasks such as reinforcement learning and portfolio management.
no code implementations • 29 Dec 2018 • Haishan Ye, Zhichao Huang, Cong Fang, Chris Junchi Li, Tong Zhang
Zeroth-order optimization is an important research topic in machine learning.
no code implementations • NeurIPS 2018 • Cong Fang, Chris Junchi Li, Zhouchen Lin, Tong Zhang
Specially, we prove that the SPIDER-SFO algorithm achieves a gradient computation cost of $\mathcal{O}\left( \min( n^{1/2} \epsilon^{-2}, \epsilon^{-3} ) \right)$ to find an $\epsilon$-approximate first-order stationary point.
no code implementations • 6 Sep 2018 • Chris Junchi Li
We present novel martingale concentration inequalities for martingale differences with finite Orlicz-$\psi_\alpha$ norms.
no code implementations • NeurIPS 2017 • Chris Junchi Li, Mengdi Wang, Han Liu, Tong Zhang
In this paper, we propose to adopt the diffusion approximation tools to study the dynamics of Oja's iteration which is an online stochastic gradient descent method for the principal component analysis.
no code implementations • NeurIPS 2016 • Chris Junchi Li, Zhaoran Wang, Han Liu
Despite the empirical success of nonconvex statistical optimization methods, their global dynamics, especially convergence to the desirable local minima, remain less well understood in theory.
no code implementations • NeurIPS 2018 • Cong Fang, Chris Junchi Li, Zhouchen Lin, Tong Zhang
For stochastic first-order method, combining SPIDER with normalized gradient descent, we propose two new algorithms, namely SPIDER-SFO and SPIDER-SFO\textsuperscript{+}, that solve non-convex stochastic optimization problems using stochastic gradients only.
no code implementations • 2 Sep 2017 • Wenqing Hu, Chris Junchi Li
By introducing a separation of fast and slow scales of the two equations, we show that the limit of the slow motion is given by an averaged ordinary differential equation.
no code implementations • ICML 2017 • Zhehui Chen, Lin F. Yang, Chris Junchi Li, Tuo Zhao
Multiview representation learning is popular for latent factor analysis.
no code implementations • 22 May 2017 • Wenqing Hu, Chris Junchi Li, Lei LI, Jian-Guo Liu
In addition, we discuss the effects of batch size for the deep neural networks, and we find that small batch size is helpful for SGD algorithms to escape unstable stationary points and sharp minimizers.
no code implementations • 16 Mar 2016 • Chris Junchi Li, Mengdi Wang, Han Liu, Tong Zhang
We prove for the first time a nearly optimal finite-sample error bound for the online PCA algorithm.