| Your time | Speaker | Title | |
| Thu | Jun 06 | 16:00 | Kathryn Hess | Of mice and men | |
| Thu | Feb 15 | 17:00 | Pedro Domingos | Deep Networks Are Kernel Machines | |
| Thu | Jan 11 | 17:00 | Francisco Förster Burón | The ALeRCE astronomical alert broker | |
| Fri | Sep 22 | 13:00 | Olga Mula | Optimal State and Parameter Estimation Algorithms and Applications to Biomedical Problems | |
| Thu | Jun 22 | 16:00 | Artemy Kolchinsky | Information geometry for nonequilibrium processes | |
| Thu | Jun 15 | 16:00 | Mário Figueiredo | Causal Discovery from Observations: Introduction and Some Recent Advances | |
| Thu | Jun 08 | 16:00 | Sara Magliacane | Causal vs causality-inspired representation learning | |
| Thu | Jun 01 | 16:00 | Andreas Döpp | Machine-learning strategies in laser-plasma physics | |
| Thu | May 18 | 16:00 | Rui Castro | Anomaly detection for a large number of streams: a permutation/rank-based higher criticism approach | |
| Thu | May 11 | 16:00 | Harry Desmond | Exhaustive Symbolic Regression (or how to find the best function for your data) | |
| Thu | May 04 | 16:00 | Diogo Gomes | Mathematics for data science and AI - curriculum design, experiences, and lessons learned | |
| Thu | Apr 27 | 16:00 | Paulo Rosa | Deep Reinforcement Learning based Integrated Guidance and Control for a Launcher Landing Problem | |
| Thu | Apr 20 | 16:00 | Rongjie Lai | Learning Manifold-Structured Data using Deep Neural Networks: Theory and Applications | |
| Thu | Mar 23 | 17:00 | Memming Park | On learning signals in recurrent networks | |
| Thu | Mar 16 | 17:00 | Valentin De Bortoli | Diffusion models, theory and methodology | |
| Thu | Mar 09 | 17:00 | Gonçalo Correia | Learnable Sparsity and Weak Supervision for Data-Efficient, Transparent, and Compact Neural Models | |
| Thu | Mar 02 | 17:00 | Sara A. Solla | Low Dimensional Manifolds for Neural Dynamics | |
| Thu | Feb 09 | 17:00 | Ben Edelman | Studies in feature learning through the lens of sparse boolean functions | |
| Thu | Feb 02 | 17:00 | Yang-Hui He | COLLOQUIUM: Universes as Bigdata: Physics, Geometry and Machine-Learning | |
| Thu | Jan 19 | 17:00 | Alhussein Fawzi | Discovering faster matrix multiplication algorithms with deep reinforcement learning | |
| Thu | Jan 12 | 17:00 | Sebastian Engelke | Machine learning beyond the data range: extreme quantile regression | |
| Thu | Dec 15 | 17:00 | Bruno Loureiro | Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks | |
| Thu | Nov 24 | 17:00 | Markus Reichstein | Integrating Machine Learning with System Modelling and Observations for a better understanding of the Earth System | |
| Thu | Nov 17 | 17:00 | Tom Goldstein | Building (and breaking) neural networks that think fast and slow | |
| Thu | Nov 10 | 17:00 | João Sacramento | The least-control principle for learning at equilibrium | |
| Thu | Nov 03 | 17:00 | Frederico Fiuza | Accelerating the understanding of nonlinear dynamical systems using machine learning | |
| Thu | Oct 27 | 16:00 | Robert Nowak | The Neural Balance Theorem and its Consequences | |
| Fri | Oct 14 | 13:30 | José Miguel Urbano | Semi-Supervised Learning and the infinite-Laplacian (Lectures 1 & 2) | |
| Fri | Oct 14 | 08:30 | Diogo Gomes | From Calculus of Variations to Reinforcement Learning (Lectures 1 & 2) | |
| Thu | Sep 29 | 16:00 | Petar Veličković | Geometric Deep Learning: Grids, Graphs, Groups, Geodesics and Gauges | |
| Thu | Sep 08 | 16:00 | Inês Hipólito | The Free Energy Principle in the Edge of Chaos | |
| Thu | Jul 14 | 16:00 | Joseph Bakarji | Dimensionally Consistent Learning with Buckingham Pi | |
| Thu | Jul 07 | 16:00 | Audrey Durand | Interactive learning for Neurosciences - Between Simulation and Reality | |
| Thu | Jun 30 | 16:00 | Dario Izzo | Geodesy of irregular small bodies via neural density fields: geodesyNets | |
| Thu | Jun 16 | 17:00 | John Baez | Shannon Entropy from Category Theory | |
| Thu | Jun 09 | 16:00 | Paulo Tabuada | Deep neural networks, universal approximation, and geometric control | |
| Thu | Jun 02 | 16:00 | Anja Butter | Machine Learning and LHC Event Generation | |
| Thu | May 26 | 16:00 | Yongji Wang | Physics-informed neural networks for solving 3-D Euler equation | |
| Thu | May 19 | 16:00 | Stanley Osher | Conservation laws and generalized optimal transport | |
| Thu | May 05 | 16:00 | Andrea L. Bertozzi | Graph based models in semi-supervised and unsupervised learning | |
| Thu | Apr 28 | 09:00 | Emtiyaz Khan | The Bayesian Learning Rule for Adaptive AI | |
| Thu | Apr 21 | 16:00 | Rianne van den Berg | Generative models for discrete random variables | |
| Thu | Apr 14 | 16:00 | Dmitry Krotov | Modern Hopfield Networks in AI and Neurobiology | |
| Thu | Mar 31 | 16:00 | Josef Urban | Machine Learning and Theorem Proving | |
| Thu | Mar 24 | 17:00 | Fernando E. Rosas | Towards a deeper understanding of high-order interdependencies in complex systems | |
| Thu | Mar 03 | 17:00 | Jan Kieseler | The MODE project | |
| Thu | Feb 24 | 16:30 | André F. T. Martins | From Sparse Modeling to Sparse Communication | |
| Thu | Feb 03 | 17:00 | Joosep Pata | Machine learning for data reconstruction at the LHC | |
| Thu | Jan 20 | 17:00 | Anders Hansen | Why things don’t work — On the extended Smale's 9th and 18th problems (the limits of AI) and methodological barriers | |
| Thu | Jan 13 | 17:00 | Dan Roberts | The Principles of Deep Learning Theory | |
| Thu | Dec 09 | 17:00 | Pier Luigi Dragotti | Computational Imaging for Art investigation and for Neuroscience | |
| Thu | Dec 02 | 17:00 | Soledad Villar | Equivariant machine learning structure like classical physics | |
| Thu | Nov 25 | 17:00 | Suman Ravuri | Skilful precipitation nowcasting using deep generative models of radar | |
| Thu | Nov 11 | 17:00 | Michael Arbel | Annealed Flow Transport Monte Carlo | |
| Thu | Nov 04 | 17:00 | George Em Karniadakis | Operator regression via DeepOnet: Theory, Algorithms and Applications | |
| Thu | Oct 21 | 16:00 | Constantino Tsallis | Statistical mechanics for complex systems | |
| Thu | Oct 14 | 16:00 | Clément Hongler | Neural Tangent Kernel | |
| Thu | Sep 30 | 16:00 | Volkan Cevher | Optimization Challenges in Adversarial Machine Learning | |
| Thu | Sep 23 | 09:00 | Leong Chuan Kwek | Machine Learning and Quantum Technology | |
| Thu | Sep 16 | 16:00 | J. Nathan Kutz | Deep learning for the discovery of parsimonious physics models | |
| Wed | Jul 28 | 16:00 | Simon Du | Provable Representation Learning | |
| Fri | Jul 09 | 13:00 | Usman Khan | Distributed ML: Optimal algorithms for distributed stochastic non-convex optimization | |
| Fri | Jul 02 | 13:00 | Ard Louis | Deep neural networks have an inbuilt Occam's razor | |
| Fri | Jun 25 | 13:00 | Yuejie Chi | Policy Optimization in Reinforcement Learning: A Tale of Preconditioning and Regularization | |
| Fri | Jun 18 | 13:00 | Ruth Misener | Partition-based formulations for mixed-integer optimization of trained ReLU neural networks | |
| Fri | Jun 11 | 13:00 | Ulugbek Kamilov | Computational Imaging: Reconciling Physical and Learned Models | |
| Fri | Jun 04 | 13:00 | Mathieu Blondel | Efficient and Modular Implicit Differentiation | |
| Fri | May 28 | 13:00 | Gustau Camps-Valls | Physics Aware Machine Learning for the Earth Sciences | |
| Fri | May 21 | 13:00 | Kyriakos Vamvoudakis | Learning-Based Actuator Placement and Receding Horizon Control for Security against Actuation Attacks | |
| Fri | May 07 | 13:00 | Rebecca Willett | Machine Learning and Inverse Problems: Deeper and More Robust | |
| Wed | Apr 28 | 17:00 | Mikhail Belkin | Two mathematical lessons of deep learning | |
| Fri | Apr 23 | 13:00 | Jan Peters | Robot Learning - Quo Vadis? | |
| Wed | Apr 14 | 17:00 | Gabriel Peyré | Scaling Optimal Transport for High dimensional Learning | |
| Fri | Apr 09 | 13:00 | Pedro A. Santos | Two-time scale stochastic approximation for reinforcement learning with linear function approximation | |
| Wed | Mar 31 | 17:00 | Steve Brunton | Machine learning for Fluid Mechanics | |
| Mon | Mar 22 | 17:00 | Markus Heyl | Quantum many-body dynamics in two dimensions with artificial neural networks | |
| Wed | Mar 17 | 18:00 | Hsin Yuan Huang, (Robert) | Information-theoretic bounds on quantum advantage in machine learning | |
| Wed | Mar 03 | 18:00 | A. Pedro Aguiar | Model based control design combining Lyapunov and optimization tools: Examples in the area of motion control of autonomous robotic vehicles | |
| Mon | Feb 22 | 17:00 | Maciej Koch-J8anusz | Statistical physics through the lens of real-space mutual information | |
| Wed | Feb 17 | 18:00 | Mário Figueiredo | Dealing with Correlated Variables in Supervised Learning | |
| Wed | Feb 10 | 18:00 | Caroline Uhler | Causal Inference and Overparameterized Autoencoders in the Light of Drug Repurposing for SARS-CoV-2 | |
| Wed | Feb 03 | 18:00 | Miguel Couceiro | Making ML Models fairer through explanations, feature dropout, and aggregation | |
| Wed | Jan 27 | 11:00 | Xavier Bresson | Benchmarking Graph Neural Networks | |
| Wed | Jan 20 | 18:00 | James Halverson | Neural Networks and Quantum Field Theory | |
| Wed | Jan 13 | 18:00 | Anna C. Gilbert | Metric representations: Algorithms and Geometry | |
| Wed | Jan 06 | 18:00 | Sanjeev Arora | The quest for mathematical understanding of deep learning | |
| Wed | Dec 16 | 18:00 | René Vidal | From Optimization Algorithms to Dynamical Systems and Back | |
| Wed | Dec 09 | 18:00 | Samantha Kleinberg | Data, Decisions, and You: Making Causality Useful and Usable in a Complex World | |
| Wed | Dec 02 | 18:00 | Gitta Kutyniok | Deep Learning meets Physics: Taking the Best out of Both Worlds in Imaging Science | |
| Wed | Nov 25 | 18:00 | Tommaso Dorigo | Dealing with Systematic Uncertainties in HEP Analysis with Machine Learning Methods | |
| Fri | Nov 20 | 15:00 | Carola-Bibiane Schönlieb | Combining knowledge and data driven methods for solving inverse imaging problems - getting the best from both worlds | |
| Wed | Nov 11 | 11:00 | Bin Dong | Learning and Learning to Solve PDEs | |
| Wed | Nov 04 | 18:00 | Joan Bruna | Mathematical aspects of neural network learning through measure dynamics | |
| Wed | Oct 28 | 18:00 | Florent Krzakala | Some exactly solvable models for statistical machine learning | |
| Wed | Oct 21 | 17:00 | Mauro Maggioni | Learning Interaction laws in particle- and agent-based systems | |
| Wed | Oct 14 | 17:00 | Lindsey Gray | Graph Neural Networks for Pattern Recognition in Particle Physics | |
| Wed | Oct 07 | 10:00 | Weinan E | Machine Learning and Scientific Computing | |
| Wed | Sep 30 | 17:00 | Gunnar Carlsson | Topological Data Analysis and Deep Learning | |
| Thu | Jul 30 | 16:30 | Masoud Mohseni | TensorFlow Quantum: An open source framework for hybrid quantum-classical machine learning. | |
| Thu | Jul 23 | 16:30 | Marylou Gabrié | Progress and hurdles in the statistical mechanics of deep learning | |
| Thu | Jul 16 | 16:30 | João Miranda Lemos | Reinforcement learning and adaptive control | |
| Thu | Jul 09 | 16:30 | Francisco C. Santos | Climate action and cooperation dynamics under uncertainty | |
| Thu | Jul 02 | 16:30 | Kyle Cranmer | On the Interplay between Physics and Deep Learning. | |
| Thu | Jun 25 | 16:30 | Csaba Szepesvári | Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting | |
| Thu | Jun 18 | 16:30 | João Xavier | Learning from distributed datasets: an introduction with two examples | |
| Thu | Jun 11 | 16:30 | Marcelo Pereyra | Efficient Bayesian computation by proximal Markov chain Monte Carlo: when Langevin meets Moreau | |
| Thu | Jun 04 | 16:30 | Afonso Bandeira | Computation, statistics, and optimization of random functions | |
| Thu | May 28 | 16:30 | Hilbert Johan Kappen | Path integral control theory | |
| Thu | May 21 | 16:30 | André David Mendes | How we discovered the Higgs ahead of schedule - ML's role in unveiling the keystone of elementary particle physics | |
| Thu | May 14 | 16:30 | Cláudia Soares | The learning machine and beyond: a tour for the curious | |
