Talks, Poster

  • J.-J. Zhu, Distributionally robust chance constrained programs using maximum mean discrepancy, SafeRL2021 in the framework of the Conference NeurIPS2021 (Online Event), University of California at Berkeley, USA, December 13, 2021.

External Preprints

  • H. Abdulsamad, T. Dorau, B. Belousov, J.-J. Zhu, J. Peters, Distributionally robust trajectory optimization under uncertain dynamics via relative-entropy trust regions, Preprint no. arXiv:2103.15388, Cornell University Library,, 2021.

  • D. Agudelo-España, Y. Nemmour, B. Schölkopf, J.-J. Zhu, Shallow representation is deep: Learning uncertainty-aware and worst-case random feature dynamics, Preprint no. arXiv:2106.13066, Cornell University Library,, 2021.

  • A. Beznosikov, P. Dvurechensky, A. Koloskova, V. Samokhin, S.U. Stich, A. Gasnikov, Decentralized local stochastic extra-gradient for variational inequalities, Preprint no. arXiv:2106.08315, Cornell University, 2021.
    We consider decentralized stochastic variational inequalities where the problem data is distributed across many participating devices (heterogeneous, or non-IID data setting). We propose a novel method - based on stochastic extra-gradient - where participating devices can communicate over arbitrary, possibly time-varying network topologies. This covers both the fully decentralized optimization setting and the centralized topologies commonly used in Federated Learning. Our method further supports multiple local updates on the workers for reducing the communication frequency between workers. We theoretically analyze the proposed scheme in the strongly monotone, monotone and non-monotone setting. As a special case, our method and analysis apply in particular to decentralized stochastic min-max problems which are being studied with increased interest in Deep Learning. For example, the training objective of Generative Adversarial Networks (GANs) are typically saddle point problems and the decentralized training of GANs has been reported to be extremely challenging. While SOTA techniques rely on either repeated gossip rounds or proximal updates, we alleviate both of these requirements. Experimental results for decentralized GAN demonstrate the effectiveness of our proposed algorithm.

  • Y. Nemmour, B. Schölkopf, J.-J. Zhu, Distributional robustness regularized scenario optimization with application to model predictive control, Preprint no. arXiv:2110.13588, Cornell University Library,, 2021.

  • J.-J. Zhu, Ch. Kouridi, Y. Nemmour, B. Schölkopf, Adversarially robust kernel smoothing, Preprint no. arXiv:2102.08474, Cornell University Library,, 2021.