Kullback-Leibler Divergence Courses and Certifications

Artem Kirsanov

The Key Equation Behind Probability - Entropy, Cross-Entropy, and KL Divergence

Explore probability theory fundamentals, from surprise to entropy, cross-entropy, and KL divergence. Learn key concepts applicable to neuroscience and machine learning.

• YouTube
• 26 minutes
• Self-Paced
• Free Video

Discover AI

FlowRL - A Reinforcement Learning Method for Enhancing LLM Reasoning Using GFlowNets

Discover FlowRL, a novel reinforcement learning method that enhances LLM reasoning through reward distribution matching instead of maximization, achieving 10% improvement over GRPO.

• YouTube
• 32 minutes
• Self-Paced
• Free Video

Pascal Poupart

Trust Region & Proximal Policy Optimization

Explore trust region methods and proximal policy optimization in reinforcement learning, focusing on policy gradients, KL divergence, and practical implementations like TRPO and PPO.

• YouTube
• 22 minutes
• Self-Paced
• Free Video

Discover AI

Model Stealing for Low-Rank Language Models Through Reverse Engineering

Discover groundbreaking mathematical techniques for reverse-engineering language models through conditional queries and barycentric spanners, exploring MIT's innovative approach to model extraction.

• YouTube
• 28 minutes
• Self-Paced
• Free Video

SNIAVideo

Optimizing Composite DNA Letters for High Density Information Encoding

Explore advanced DNA synthesis techniques using composite letters with mixed base ratios to dramatically increase information storage density beyond traditional 4-base systems.

• YouTube
• 20 minutes
• Self-Paced
• Free Video

Valence Labs

Calibrating Generative Models to Distributional Constraints

Discover how to fix generative model miscalibration using constrained optimization, with practical applications in protein design, image generation, and language modeling.

• YouTube
• 1 hour 9 minutes
• Self-Paced
• Free Video

UofU Data Science

Locality-Sensitive Hashing and Distribution Distances - Lecture 7

Discover LSH techniques for fast similarity search using hash functions and banding, plus explore distribution distances like KL, Hellinger, and Wasserstein metrics.

• YouTube
• 1 hour 21 minutes
• Self-Paced
• Free Video

Fields Institute

Algorithmic Learning Theory and Differential Privacy - Session 3

Explore cutting-edge research in algorithmic learning theory covering distributed testing, private estimation, differential privacy, and stochastic optimization methods.

• YouTube
• 1 hour 7 minutes
• Self-Paced
• Free Video

Association for Computing Machinery (ACM)

Evaluation of Adaptive Systems

Learn techniques for evaluating adaptive systems, including user modeling, personalization, and group-based approaches to improve search rankings and address data sparsity challenges.

• YouTube
• 2 hours 18 minutes
• Self-Paced
• Conference Talk

Applied Algebraic Topology Network

Topology of Surprisal - Information Theory and Vietoris-Rips Filtrations

Explore the fusion of information theory and Vietoris-Rips filtrations, focusing on Kullback-Leibler divergence and its applications in deep learning, with insights on overcoming non-symmetry challenges.

• YouTube
• 59 minutes
• Self-Paced
• Free Video

Probabilistic AI School

Variational Inference and Optimization - Lecture 1

Explore variational inference and optimization techniques in probabilistic AI, covering key concepts and applications for advanced machine learning.

• YouTube
• 1 hour 56 minutes
• Self-Paced
• Free Video

EDGE AI FOUNDATION

Multi-armed Bandit on System-on-Chip - Go Frequentist or Bayesian?

Explore multi-armed bandit algorithms for edge computing, focusing on UCB, KLUCB, and Thompson Sampling implementations on System-on-Chip for IoT, wireless radio, and robotics applications.

• YouTube
• 1 hour 8 minutes
• Self-Paced
• Free Video

BIMSA

Graphon Cross-Validation: Assessing Models on Network Data

Explore graphon cross-validation techniques for network data analysis, enhancing model accuracy and generalizability through innovative validation methods and theoretical insights.

• YouTube
• 1 hour 3 minutes
• Self-Paced
• Free Video

Centre de recherches mathématiques - CRM

An Exploration-Agnostic Characterization of the Ergodicity of Parallel Tempering

Explore non-reversible parallel tempering's ergodicity in complex distributions, examining its efficiency and comparing it to classical methods through theoretical analysis and simulations.

• YouTube
• 48 minutes
• Self-Paced
• Free Video

Valence Labs

Designing Losses for Data-Free Training of Normalizing Flows on Boltzmann Distributions

Explore advanced techniques for training normalizing flows on Boltzmann distributions without data, addressing mode collapse and optimizing high-dimensional distributions in molecular configuration generation.

• YouTube
• 1 hour 7 minutes
• Self-Paced
• Free Video