13.01.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Yuan Cao (University of California, LA)
• Towards Understanding and Advancing the Generalization of Adam in Deep Learning
• see video

20.01.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Philipp Petersen (University of Vienna)
• Optimal learning in high-dimensional classification problems
• see video

20.01.2022, 18:30 Uhr, Deep Learning Theory Group Seminar

• Ruhui Jin (University of Texas at Austin)
• Tensor-structured sketching for constrained optimizations

21.01.2022, 17:00 Uhr, Deep Learning Theory Group Seminar

• Tiffany Vlaar (University of Edinburgh)
• to be announced

27.01.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Daniel Russo (Columbia University)
• Adaptivity and Confounding in Multi-armed Bandit Experiments
• see video

04.02.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Song Mei (University of California, Berkeley)
• The efficiency of kernel methods on structured datasets
• see video

10.02.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Hui Jin (University of California, Los Angeles)
• Learning curves for Gaussian process regression with power-law priors and targets
• see video

17.02.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Maksim Velikanov (Skolkovo Institute of Science and Technology)
• Spectral properties of wide neural networks and their implications to the convergence speed of different Gradient Descent algorithms

24.02.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Danijar Hafner (Google Brain & University of Toronto)
• General Infomax Agents through World Models
• see video

03.03.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Marco Mondelli (Institute of Science and Technology Austria)
• Gradient Descent for Deep Neural Networks: New Perspectives from Mean-field and NTK
• see slides

04.03.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Daniel McKenzie (UCLA)
• Implicit Neural Networks: What they are and how to use them.
• see video

10.03.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Gergely Neu (Universitat Pompeu Fabra, Barcelona)
• Generalization Bounds via Convex Analysis
• see video

11.03.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Uri Alon (CMU)
• Bottlenecks, over-squashing, and attention in Graph Neural Networks.
• see video

17.03.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Gabin Maxime Nguegnang (RWTH Aachen University)
• Convergence of gradient descent for learning deep linear neural networks
• see video

24.03.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Ohad Shamir (Weizmann Institute of Science)
• Implicit bias in machine learning
• see video

31.03.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Benjamin Eysenbach (Carnegie Mellon University & Google Brain)
• The Information Geometry of Unsupervised Reinforcement Learning
• see video

07.04.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Chaoyue Liu (Ohio State University)
• Transition to Linearity of Wide Neural Networks
• see video

14.04.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Christoph Lampert (Institute of Science and Technology, Austria)
• Robust and Fair Multisource Learning
• see video

21.04.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Berfin Şimşek (Ecole Polytechnique Fédérale de Lausanne (EPFL))
• The Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetry-Induced Saddles and Global Minima Manifold
• see video

05.05.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Noam Razin (Tel Aviv University)
• Generalization in Deep Learning Through the Lens of Implicit Rank Minimization
• see slides

12.05.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Zixiang Chen (UCLA)
• Benign Overfitting in Two-layer Convolutional Neural Networks
• see video

19.05.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Sayan Mukherjee (MPI MiS, Leipzig + Universität Leipzig)
• Inference in dynamical systems and the geometry of learning group actions
• see video

26.05.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Melikasadat Emami (UCLA)
• Asymptotics of Learning in Generalized Linear Models and Recurrent Neural Networks
• see video

02.06.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Tan Nguyen (UCLA)
• Principled Models for Machine Learning
• see video

09.06.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Guang Cheng (UCLA)
• Nonparametric Perspective on Deep Learning
• see video

16.06.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Jingfeng Wu (Johns Hopkins University)
• A Fine-Grained Characterization for the Implicit Bias of SGD in Least Square Problems
• see video

07.07.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Sebastian Kassing (Institute for Mathematical Stochastics, University of Muenster)
• to be announced
• Videobroadcast, registration required, check abstract for details

14.07.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Rong Ge (Duke University)
• to be announced
• Videobroadcast, registration required, check abstract for details

21.07.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Mark Schmidt (University of British Columbia)
• to be announced
• Videobroadcast, registration required, check abstract for details

28.07.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Arash A. Amini (UCLA)
• to be announced
• Videobroadcast, registration required, check abstract for details

25.08.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Melanie Weber (Mathematical Institute, University of Oxford)
• to be announced
• Videobroadcast, registration required, check abstract for details

22.09.2022, 17:00 Uhr, Math Machine Learning seminar MPI MIS + UCLA

• Gintare Karolina Dziugaite (Google Brain)
• to be announced
• Videobroadcast, registration required, check abstract for details