ConceptTheory & Algos
Expectation
Expectation or mean is the probability-weighted average of all values a random variable can take.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Opens up
Concepts that name this one as a prerequisite.
Lecturers
4Each in their own terms, from the easiest level.
Christopher Manning
An average over all context vectors weighted by their probabilities according to the model.Ankur Moitra
The expectation of a random variable is the weighted average over the probability space of the values the function takes.Ryan O'Donnell
The average value of a function over all possible inputs, assuming each input is chosen uniformly at random.
Lectures that assume it
92The first 12 are shown.
- Model-Free Control — ε-Greedy SARSA & Off-Policy Q-Learning
- Speculations on Test-Time Scaling for Large Language Models (o1)
- Generative Modeling by Estimating Gradients of the Data Distribution
- Boolean Fourier Formulas
- Analysis of Boolean Functions: Open Problems
- Approximate counting
- Value Function Approximation & Deep Q-Networks (DQN)
- Applications of Least-Squares Estimation: System Identification & Filtering
- The Linear Model II
- Financial Markets and Expectations
- Proof of the Chernoff Bound
- Natural Policy Gradients, Covariant Updates & The Fisher Information Matrix
Connections
107The lectures that define it or assume it, and the concepts next to it.
Concepts10
- Random variable
- Probability distribution
- Probability distribution function
- Probability mass function
- Probability space
- Linearity of expectation
Show 4 moreShow fewer
Lectures97
- The Fourier Expansion and Basic Formulas
- Central Limit Theorem
- Natural Language Processing with Deep Learning: Introduction & Word Vectors
- Probability Theory
- Independence and Conditioning
- Model-Free Control — ε-Greedy SARSA & Off-Policy Q-Learning
Show 91 moreShow fewer
- Speculations on Test-Time Scaling for Large Language Models (o1)
- Generative Modeling by Estimating Gradients of the Data Distribution
- Boolean Fourier Formulas
- Analysis of Boolean Functions: Open Problems
- Approximate counting
- Value Function Approximation & Deep Q-Networks (DQN)
- Applications of Least-Squares Estimation: System Identification & Filtering
- The Linear Model II
- Financial Markets and Expectations
- Proof of the Chernoff Bound
- Natural Policy Gradients, Covariant Updates & The Fisher Information Matrix
- Introduction to Individual Decision-Making
- Convex Optimization II: Stochastic Programming and Cutting-Plane Methods
- Order Statistics and Conditional Expectation
- Conditional Expectation Given a Random Variable (Statistics 110, Lecture 27)
- Spectral Graph Theory: Linear Algebra and Irregular Graphs
- Cheeger's Inequality
- Deep Reinforcement Learning
- Deep Reinforcement Learning
- Variational Inference, Part 2
- Poverty Traps: Graduation Programs
- Randomization: Universal & Perfect Hashing
- Normal Distribution
- Reinforcement Learning Part 1/2
- Dictionaries
- Majority, LTFs, and the CLT
- Inclusion-Exclusion
- Nash Equilibrium: Bad fashion and bank runs
- Bias-Variance Tradeoff
- Moment Generating Functions
- Probability Densities and BLR Linearity Testing
- Noise Stability and Arrow's Theorem
- Level-1 Inequality and the 2/π Theorem
- Håstad's Hardness Theorems
- The Hypercontractivity Theorem
- Dominance
- Conditional Expectation Continued: Two Envelope Paradox and Coin Flips (Statistics 110, Lecture 26)
- Chi-Square, Student-t, and Multivariate Normal Distributions
- CSP Approximability: Optimization and Certification
- Yao's Minimax Theorem and IP_2's Communication Complexity
- Exploration of fundamental concepts in deep reinforcement learning
- Deep Reinforcement Learning
- Sanders's Theorem (Analysis of Boolean Functions, CMU 15-859S, Lecture 22)
- Hardness Amplification
- Invariance Theorems
- Transmitting Information Reliably over a Noisy Channel & Shannon’s Noisy Coding Theorem
- Model-Free Prediction — Monte Carlo, TD(0) & TD(λ)
- Risk and Financial Crises
- Covariance and Correlation
- Generative Models
- Markov and Chebyshev Inequalities
- Privacy Amplification for Correlated-Noise Mechanisms via b-Min-Sep Subsampling
- Neural Networks I: Feedforward Architectures & Backpropagation
- Restrictions and the Goldreich-Levin Theorem
- Generative Models: Representation Learning Meets Generative Modeling
- Chernoff Bounds
- Beta Distribution
- Stochastic Gradient Descent
- Spectral Graph Theory: The Markov Transition Operator
- Spectral Graph Theory III: Mixing Time
- Mutual Information
- Foundational concepts in deep reinforcement learning
- Control as Inference, Part 3
- Hardness vs. Randomness I
- Hardness vs. Randomness II
- Quantum "Supremacy"
- Search with Other Agents: Expectimax, Utilities
- Definitions and Inequalities
- Five Thoughts in Place of a Sweeping Conclusion
- Itō Calculus
- Social Choice and Influences
- LTFs and Noise Stability
- Generalization: Out-of-Distribution (OOD)
- Tail Bounds
- Policy Gradient Methods
- Approximation and Fitting
- Deep Reinforcement Learning
- Multi-objective Learning: An Algorithmic Toolbox for Optimal Predictions Anytime Anywhere
- Generative Models: Basics
- UG-Hardness Results from Dictator Tests
- Introduction to Large Deviation Theory
- A Look Ahead
- Asset Pricing
- Pseudoexpectations
- Language Models: Prompting, Chain-of-Thought, and Instruction-Tuning
- Regression Analysis
- Time Series Analysis I
- Stable Estimators for Fast Private Statistics
- Majority Is Stablest Theorem
- Exploration of deep reinforcement learning architectures and algorithms
- Sequential Optimization of Dynamically Augmented Conditional Value-at-Risk