Lectures related to Least Mean Squares with Features

Complexity & Induction: Algorithms & Proofs

Covers worst-case complexity, algorithms, and proofs including mathematical induction and recursion.

Complexity & Induction: Algorithms & Proofs

Explores worst-case complexity, mathematical induction, and algorithms like binary search and insertion sort.

Elements of computational complexity

Covers classical and quantum computational complexity concepts and implications.

Numerical Methods: Runge-Kutta Approximation

Covers the Runge-Kutta method for approximating solutions of differential equations.

Linear Systems: Convergence and Methods

Explores linear systems, convergence, and solving methods with a focus on CPU time and memory requirements.

Naive Bayes: Gaussian Discriminant Analysis

Covers the Naive Bayes assumption, Gaussian Discriminant Analysis, ML estimates, and Kernel trick.

Belief propagation simplification

Explores simplifying belief propagation equations for pairwise models, reducing computational complexity from order n cubed to order n.

Kernel Ridge Regression: Equivalent Formulations and Representer Theorem

Explores Kernel Ridge Regression, equivalent formulations, Representer Theorem, Kernel trick, and predicting with kernels.

Learning from Probabilistic Models

Delves into challenges of learning from probabilistic models, covering computational complexity, data reconstruction, and statistical gaps.

Double Descent Curves: Overparametrization

Explores double descent curves and overparametrization in machine learning models, highlighting the risks and benefits.

Projection Pursuit Regression: Nonlinear Modeling and Interpretability

Explores Projection Pursuit Regression for nonlinear modeling and the trade-offs with interpretability in neural networks.

Optimal Power Flow Solvers: Next Generation Advancements

Explores advancements in optimal power flow solvers, focusing on multiperiod and security-constrained optimization.

State Space Models: Expressivity of Transformers

Covers state space models and the expressivity of transformers in sequence copying tasks.

Complexity of Algorithms

Explores algorithm complexity, analyzing efficiency and worst-case scenarios of sorting algorithms.

Subset Sum: LLL Algorithm

Covers the Subset Sum problem and the efficient LLL algorithm for finding solutions in lattice basis reduction.

Energy System Modelling: Overview and Optimization Problems

Covers energy system modelling, optimization, scenarios, predictions, complexities, and controversies in energy models.

Subquadratic Attention Mechanisms: State Space Models Overview

Covers subquadratic attention mechanisms and state space models, focusing on their theoretical foundations and practical implementations in machine learning.

Linear Systems: Direct Methods

Explores linear systems, direct methods, Gauss elimination, LU decomposition, and computational complexity.

Elements of Computational Complexity

Introduces computational complexity, decision problems, quantum complexity, and probabilistic algorithms, including NP-hard and NP-complete problems.

Kernel Ridge Regression: Equivalence, Representer Theorem, and Kernel Trick

Explores Kernel Ridge Regression, the Representer Theorem, and the Kernel Trick in machine learning.