no code implementations • 29 Feb 2024 • Pavel Dvurechensky, Jia-Jie Zhu
By choosing a suitable function space as the dual to the non-negative measure cone, we study in a unified framework a class of functional saddle-point optimization problems, which we term the Mixed Functional Nash Equilibrium (MFNE), that underlies several existing machine learning algorithms, such as implicit generative models, distributionally robust optimization (DRO), and Wasserstein barycenters.
no code implementations • 8 Feb 2024 • Ling Liang, Kim-Chuan Toh, Jia-Jie Zhu
The Halpern iteration for solving monotone inclusion problems has gained increasing interests in recent years due to its simple form and appealing convergence properties.
1 code implementation • 18 May 2023 • Heiner Kremer, Yassine Nemmour, Bernhard Schölkopf, Jia-Jie Zhu
We provide a variant of our estimator for conditional moment restrictions and show that it is asymptotically first-order optimal for such problems.
no code implementations • 27 Apr 2023 • Jia-Jie Zhu
This paper provides answers to an open problem: given a nonlinear data-driven dynamical system model, e. g., kernel conditional mean embedding (CME) and Koopman operator, how can one propagate the ambiguity sets forward for multiple steps?
1 code implementation • 11 Jul 2022 • Heiner Kremer, Jia-Jie Zhu, Krikamol Muandet, Bernhard Schölkopf
Important problems in causal inference, economics, and, more generally, robust machine learning can be expressed as conditional moment restrictions, but estimation becomes challenging as it requires solving a continuum of unconditional moment restrictions.
no code implementations • 26 Oct 2021 • Yassine Nemmour, Bernhard Schölkopf, Jia-Jie Zhu
We provide a functional view of distributional robustness motivated by robust statistics and functional analysis.
no code implementations • 24 Jun 2021 • Diego Agudelo-España, Yassine Nemmour, Bernhard Schölkopf, Jia-Jie Zhu
Random features is a powerful universal function approximator that inherits the theoretical rigor of kernel methods and can scale up to modern learning tasks.
no code implementations • 29 Mar 2021 • Hany Abdulsamad, Tim Dorau, Boris Belousov, Jia-Jie Zhu, Jan Peters
Trajectory optimization and model predictive control are essential techniques underpinning advanced robotic applications, ranging from autonomous driving to full-body humanoid control.
1 code implementation • 16 Feb 2021 • Jia-Jie Zhu, Christina Kouridi, Yassine Nemmour, Bernhard Schölkopf
We propose a scalable robust learning algorithm combining kernel smoothing and robust optimization.
2 code implementations • 12 Jun 2020 • Jia-Jie Zhu, Wittawat Jitkrittum, Moritz Diehl, Bernhard Schölkopf
We prove a theorem that generalizes the classical duality in the mathematical problem of moments.
no code implementations • 31 Mar 2020 • Jia-Jie Zhu, Wittawat Jitkrittum, Moritz Diehl, Bernhard Schölkopf
In order to anticipate rare and impactful events, we propose to quantify the worst-case risk under distributional ambiguity using a recent development in kernel methods -- the kernel mean embedding.
1 code implementation • L4DC 2020 • Jia-Jie Zhu, Moritz Diehl, Bernhard Schölkopf
We apply kernel mean embedding methods to sample-based stochastic optimization and control.
1 code implementation • 25 Nov 2019 • Jia-Jie Zhu, Krikamol Muandet, Moritz Diehl, Bernhard Schölkopf
This work presents the concept of kernel mean embedding and kernel probabilistic programming in the context of stochastic systems.
no code implementations • 20 Nov 2019 • Jia-Jie Zhu, Georg Martius
Today's fast linear algebra and numerical optimization tools have pushed the frontier of model predictive control (MPC) forward, to the efficient control of highly nonlinear and hybrid systems.
1 code implementation • NeurIPS 2019 • Sebastian Blaes, Marin Vlastelica Pogančić, Jia-Jie Zhu, Georg Martius
We present a novel intrinsically motivated agent that learns how to control the environment in the fastest possible manner by optimizing learning progress.
1 code implementation • 13 Sep 2018 • Dominik Baumann, Jia-Jie Zhu, Georg Martius, Sebastian Trimpe
Event-triggered control (ETC) methods can achieve high-performance control with a significantly lower number of samples compared to usual, time-triggered methods.
no code implementations • 25 Feb 2017 • Jia-Jie Zhu, José Bento
We propose a new active learning by query synthesis approach using Generative Adversarial Networks (GAN).