Lectures related to Applications of GAMP

Explains prefix-free codes for efficient data compression and the significance of uniquely decodable codes.

Probabilistic Models for Linear Regression

Covers the probabilistic model for linear regression and its applications in nuclear magnetic resonance and X-ray imaging.

Linear Regression: Statistical Inference and Regularization

Covers the probabilistic model for linear regression and the importance of regularization techniques.

Spike Wigner Model

Explores the Spike Wigner model, Bayesian denoising, state evolution, and spectral methods in matrix analysis.

Optimization Methods: Theory Discussion

Explores optimization methods, including unconstrained problems, linear programming, and heuristic approaches.

Neural Signal Compression

Explores analog-to-digital conversion, neural signal optimization, multichannel architectures, and on-chip compression techniques in neuroengineering.

Data Compression and Shannon-Fano Algorithm

Explores the Shannon-Fano algorithm for data compression and its efficiency in creating unique binary codes for letters.

Model Compression Techniques: Enhancing Neural Networks

Covers model compression techniques to enhance the efficiency of large language models in production settings.

Structures in Non-Convex Optimization

Covers non-convex optimization, deep learning training problems, stochastic gradient descent, adaptive methods, and neural network architectures.

Adaptive Gradient Methods: Theory and Applications

Explores adaptive gradient methods, their properties, convergence, and comparison with traditional optimization algorithms.

Proof Technique for the Spiked Model

Covers a proof technique for the spiked model using matrix-based calculations and state evolution.

Optimization with Constraints: KKT Conditions

Covers the KKT conditions for optimization with constraints, essential for solving constrained optimization problems efficiently.

Data Compression and Entropy 2: Entropy as 'Question Game'

Explores entropy as a 'question game' to guess letters efficiently and its relation to data compression.

Random Field Ising Model: Overview and Analysis

Provides an in-depth analysis of the Random Field Ising Model, covering model description, free entropy, and mean field algorithm.

Feed-forward Networks

Introduces feed-forward networks, covering neural network structure, training, activation functions, and optimization, with applications in forecasting and finance.

Optimality of Convergence Rates: Accelerated/Stochastic Gradient Descent

Covers the optimality of convergence rates in accelerated and stochastic gradient descent methods for non-convex optimization problems.

The Hidden Convex Optimization Landscape of Deep Neural Networks

Explores the hidden convex optimization landscape of deep neural networks, showcasing the transition from non-convex to convex models.

Information in Networked Systems: Functional Representation and Data Compression

Explores traditional information theory, data compression, data transmission, and functional representation lemmas in networked systems.

Flexible Guides: Design and Optimization

Explores the design and optimization of flexible guides, covering stiffness calculation, pivot designs, and stress considerations.

Stochastic Softmax Tricks

Explores stochastic softmax tricks, reparametrization, and argmax, addressing challenges in expectation estimation and gradient variance.