Towards Structural Risk Minimization for RL - Emma Brunskill
Explore structural risk minimization in reinforcement learning, focusing on efficient learning of risk-sensitive policies using conditional value at risk and optimistic exploration techniques.
Random Restrictions and Fourier Concentration - Part 2
Explore advanced concepts in Fourier analysis and random restrictions, focusing on their applications in theoretical computer science and mathematical analysis.
Random Restrictions and Fourier Concentration - Part 1
Explore random restrictions and Fourier concentration in analysis and theoretical computer science with MIT researcher Esty Kelman.
Gaussian Isoperimetry and Related Topics III
Explore Gaussian isoperimetry's applications in probability and analysis, including concentration inequalities, noise stability, and Sobolev-type inequalities. Learn proof methods from geometric measure theory.
Functional Inequalities and Concentration of Measure II
Explores concentration inequalities in probability and geometric analysis, focusing on functional inequalities like Poincaré and log-Sobolev. Covers properties, applications to Lipschitz functions, and various measure settings.
Gaussian Isoperimetry and Related Topics II
Explore Gaussian isoperimetry's applications in probability and analysis, including concentration inequalities, noise stability, and Sobolev-type inequalities. Learn proof methods from geometric measure theory.
Gaussian Isoperimetry and Related Topics I
Explore Gaussian isoperimetry's applications in probability and analysis, including concentration inequalities, noise stability, and Sobolev-type inequalities. Learn proof techniques using geometric measure theory.
Concentration Inequalities for Poisson U-Statistics
Explore concentration inequalities for Poisson U-statistics, their optimality, and applications in stochastic geometry models. Gain insights into Poisson functionals and their significance in geometric analysis.
Vector-Valued Concentration on the Symmetric Group
Explore vector-valued concentration inequalities for the symmetric group, examining implications for Banach space geometry and building on recent advancements in discrete hypercube analysis.
Operation on Concentration Inequalities and Conjugate of Parallel Sum
Explore advanced techniques in concentration inequalities, including operations on concentrated vectors and applications of the convex conjugate of parallel sum in measure theory.
Learning from Dependent Data - Lecture 2
Explores techniques for analyzing and learning from dependent data, focusing on probabilistic and optimization methods in data science.
Optimal Sampling in Weighted Least-Squares Methods - Application to High-Dimensional Approximation
Explore optimal sampling in weighted least-squares for high-dimensional approximation, focusing on mathematical foundations and modern approaches to overcome the curse of dimensionality.
Learning from Dependent Data - Lecture 1
Explore techniques for learning from dependent data, focusing on probabilistic and optimization methods in data science. Gain insights into handling interconnected information effectively.
Rotationally Invariant First Passage Percolation: Scaling Relations and Chaos - ICBS 2024
Explore rotationally invariant first passage percolation, scaling relations, and chaos in KPZ universality class through multi-scale analysis and geodesic behavior.
Metastability of Glauber Dynamics with Inhomogeneous Coupling Disorder
Explore metastability in mean-field-like spin systems with random couplings, focusing on Glauber dynamics and quantitative estimates in large volumes at fixed temperatures.
Concentration on HDX: Derandomization Beyond Chernoff - Lecture
Explore advanced derandomization techniques beyond Chernoff's bound, focusing on high-dimensional expanders and their applications in theoretical computer science and complexity theory.
Bounded Differences Inequality and Azuma-Hoeffding Inequality
Master probabilistic analysis through the Bounded Differences Inequality, exploring its applications in coupon collection and random graph coloring, with focus on Lipschitz functions and concentration bounds.