
Explore regularization techniques for optimal transport and dynamic time warping distances, focusing on smoothing strategies to enhance machine learning applications and Fréchet mean computation.

Explore Bayesian model selection strategies for automated data analysis and report generation, with insights on regression models, Gaussian processes, and computational resource allocation.

Explore privacy-preserving algorithms for decentralized collaborative learning, focusing on large-scale machine learning, distributed methods, and privacy protection in connected device data analysis.

Explore moment analysis and model reduction techniques for complex systems, with applications to London's bike-sharing system. Learn about PCTMCs, moment equations, and directed contribution graphs.

Explore neural networks as interacting particle systems, examining their mathematical foundations and applications in complex systems modeling across various scientific disciplines.

Explore universality classes in 1+1 dimensional systems, focusing on weak universality conjecture, graphical construction, and links to Brownian web. Gain insights into complex systems modeling.

Explore privacy-preserving techniques for secure information sharing, including two-party computation, private set intersection, and authorized PSI, with applications in collaborative anomaly detection.

Explore private set intersection protocols, including custom and generic MPC approaches, with a focus on Cuckoo hashing for efficient computation of PSI variants in cryptography and security.

Explore deep learning techniques for analyzing mobile network traffic, enhancing urban data interpretation and smart city development.

Explore urban modeling scenarios using AI, focusing on smart cities, deep learning for mobility data, and building resilient systems for future urban challenges.

Explore neural opinion dynamics for predicting user stance shifts in digital democracy platforms, enhancing citizen engagement and policy-making through machine learning techniques.

Explore efficient cross-validation techniques for large datasets using linear approximation and dimensionality reduction. Learn about error bounds, high-dimensional challenges, and practical applications in machine learning.

Explore benign overfitting in machine learning, focusing on linear regression, deep networks, and statistical implications. Gain insights into effective rank, regularization, and future research directions.

Explore function spaces of overparameterized neural networks, focusing on weight-bounded networks and their approximation capabilities. Insights from Radon transform analysis reveal novel perspectives on learning with ReLU networks.

Explore big data's low-rank structure, generalized low-rank models, and their applications in machine learning. Learn about dimensionality reduction, autoML, and latent variable models for efficient data analysis.

Exploring the necessity of memorization in learning algorithms, this talk delves into privacy concerns, long-tail distributions, and the role of memorization in achieving optimal generalization error in deep learning.

Explore unsupervised learning in generative art, reinforcement learning agents as image creators, and the potential of AI in artistic tools and creative processes.

Explore machine learning techniques for better decision-making, including ROC curves, calibration methods, and precision-recall-gain curves. Learn to adapt models to deployment contexts and measure ML performance.

Explore Spotify's approach to personalizing music recommendations using machine learning, focusing on user intents, relevance, diversity, and satisfaction to enhance the listening experience.

Explore the ethical implications of AI optimization strategies and their potential for unintended consequences in financial markets and AI regulation.

Exploring algorithmic accountability and human-centered oversight for safer AI systems. Emphasizes comprehensible, predictable, and controllable designs to prevent failures and improve safety in critical services.