Learning, Approximation and Control in Dynamical Systems
Explore connections between machine learning, approximation theory, and control systems in this symposium talk by Qianxiao Li from the National University of Singapore.
Predicting Tipping Points with Reservoir Computing
Explore reservoir computing techniques for predicting critical transitions in complex systems, with applications in climate science and ecology.
Avoidance of Traps for Nonconvex Stochastic Optimization and Equilibrium Learning in Games
Explore strategies to overcome challenges in nonconvex stochastic optimization and game theory equilibrium learning, focusing on trap avoidance techniques.
Non-Euclidean Generative Modeling
Explore advanced generative modeling techniques beyond Euclidean spaces with Georgia Tech's Molei Tao, delving into innovative approaches for complex data structures.
Equivariant Learning Through Invariant Theory
Explore equivariant learning and its connection to invariant theory with Jeroen Lamb from Imperial College London in this symposium talk on machine learning and dynamical systems.
Learning Transfer Operators by Kernel Density Estimation
Explore kernel density estimation techniques for learning transfer operators in dynamical systems, enhancing understanding of complex system behaviors and predictions.
Provable Posterior Sampling with Score-Based Diffusion through Tilted Transport
Explore score-based diffusion methods for posterior sampling, focusing on tilted transport techniques and their applications in machine learning and dynamical systems.
Learning and Dynamical Systems - Perspectives from Optimization, Control, and Robotics
Explore perspectives on learning and dynamical systems through the lenses of optimization, control theory, and robotics in this insightful symposium presentation.
Ergodic Basis Pursuit for Robust Sparse Network Reconstruction
Explore robust sparse network reconstruction using Ergodic Basis Pursuit, a novel approach for enhancing accuracy and efficiency in complex system analysis.
Learning Port Hamiltonian Structures Using PINNs Architecture
Explore innovative techniques for learning Port Hamiltonian structures using Physics-Informed Neural Networks, enhancing understanding of dynamical systems and machine learning applications.
Simplicity Bias, Algorithmic Probability, and Time Series in Machine Learning
Explore simplicity bias, algorithmic probability, and time series in this symposium talk on machine learning and dynamical systems.
Algorithmic Information Theory and Machine Learning in Dynamical Systems
Explore the intersection of Algorithmic Information Theory and Machine Learning for Dynamical Systems in this symposium talk by Boumediene Hamzi from Caltech.
Operator Learning Without the Adjoint
Explore innovative techniques for operator learning without relying on adjoint methods, advancing machine learning in dynamical systems.
Phase Transition Theory for the Score Degradation of Machine Learning Models
Explore phase transition theory's application to machine learning model score degradation, examining its impact on performance and reliability in dynamic systems.
Data-Adaptive RKHS Regularization for Learning Kernels in Operators
Explore data-adaptive RKHS regularization techniques for learning kernels in operators, enhancing understanding of machine learning applications in dynamical systems.
Ensemble Forecasts in Reproducing Kernel Hilbert Space Family
Explore advanced techniques for ensemble forecasting using reproducing kernel Hilbert spaces, enhancing predictive accuracy in dynamical systems and machine learning applications.
Continuum Attention for Neural Operators
Explore innovative Continuum Attention techniques for Neural Operators, enhancing machine learning applications in dynamical systems and expanding the field's capabilities.
Anamnesic Neural Differential Equations with Orthogonal Polynomial Projections
Explore innovative neural differential equations using orthogonal polynomial projections for enhanced machine learning in dynamical systems.
Improved Precision Scaling for Simulating Coupled Quantum-Classical Dynamics
Explore advanced techniques for simulating quantum-classical dynamics, focusing on improved precision scaling methods and their applications in quantum information research.
A Computational Framework for Solving Wasserstein Lagrangian Flows
Explore a computational framework for solving Wasserstein Lagrangian flows, covering optimal transport variations and applications in single-cell trajectory inference.
Experimental Investigation of a Microring-Based Time-Delay Reservoir Computing
Explore microring-based time-delay reservoir computing through experimental investigation, delving into advanced concepts and practical applications in photonic computing.