Sampling (statistics) | Mechanism design
A Prior-independent mechanism (PIM) is a mechanism in which the designer knows that the agents' valuations are drawn from some probability distribution, but does not know the distribution. A typical application is a seller who wants to sell some items to potential buyers. The seller wants to price the items in a way that will maximize his profit. The optimal prices depend on the amount that each buyer is willing to pay for each item. The seller does not know these values, but he assumes that the values are random variables with some unknown probability distribution. A PIM usually involves a random sampling process. The seller samples some valuations from the unknown distribution, and based on the samples, constructs an auction that yields approximately-optimal profits. The major research question in PIM design is: what is the sample complexity of the mechanism? I.e, how many agents it needs to sample in order to attain a reasonable approximation of the optimal welfare? (Wikipedia).
(ML 19.2) Existence of Gaussian processes
Statement of the theorem on existence of Gaussian processes, and an explanation of what it is saying.
From playlist Machine Learning
Powered by https://www.numerise.com/ Independent events
From playlist Multiple event probability
Definition of conjugate priors, and a couple of examples. For more detailed examples, see the videos on the Beta-Bernoulli model, the Dirichlet-Categorical model, and the posterior distribution of a univariate Gaussian.
From playlist Machine Learning
Probability of Successive Independent Events
"Successive independent events (including tree diagrams)."
From playlist Data Handling: Probability
Determine the probability of two events that are mutually exclusive
👉 Learn how to find the probability of mutually exclusive events. Two events are said to be mutually exclusive when the two events cannot occur at the same time. For instance, when you throw a coin the event that a head appears and the event that a tail appears are mutually exclusive becau
From playlist Probability of Mutually Exclusive Events
Introduction to Linearly Independent and Linearly Dependent Sets of Vectors
This video introduced the topic of linearly independent and dependent sets of vectors.
From playlist Linear Independence and Bases
(PP 6.2) Multivariate Gaussian - examples and independence
Degenerate multivariate Gaussians. Some sketches of examples and non-examples of Gaussians. The components of a Gaussian are independent if and only if they are uncorrelated.
From playlist Probability Theory
Using Variables in Science – The Foundations of Statistical Analysis and Scientific Testing (1-5)
Continuing our discussion about variables, you will learn how variables are used in science. Specifically, when we do statistics, we need independent and dependent variables. Independent variables are often categorical (groups) and dependent variables are typically measured on a scale. You
From playlist WK1 Numbers and Variables - Online Statistics for the Flipped Classroom
Nexus Trimester - Kamalika Chaudhuri (UC San Diego)
Privacy-preserving Analysis of Correlated data Kamalika Chaudhuri (UC San Diego) March 30, 2016 Abstract: Many modern machine learning applications involve private and sensitive data that are highly correlated. Examples are mining of time series of physical activity measurements, or minin
From playlist Nexus Trimester - 2016 - Secrecy and Privacy Theme
Jana de Wiljes: Sequential Bayesian Learning
Abstract: In various application areas it is crucial to make predictions or decisions based on sequentially incoming observations and previous existing knowledge on the system of interest. The prior knowledge is often given in the form of evolution equations (e.g., ODEs derived via first p
From playlist SMRI Seminars
Yoshua Bengio | From System 1 Deep Learning to System 2 Deep Learning | NeurIPS 2019
Slides: http://www.iro.umontreal.ca/~bengioy/NeurIPS-11dec2019.pdf Summary: Past progress in deep learning has concentrated mostly on learning from a static dataset, mostly for perception tasks and other System 1 tasks which are done intuitively and unconsciously by humans. However, in
From playlist AI talks
Priors for Semantic Variables - Yoshua Bengio
Seminar on Theoretical Machine Learning Topic: Priors for Semantic Variables Speaker: Yoshua Bengio Affiliation: Université de Montréal Date: July 23, 2020 For more video please visit http://video.ias.edu
From playlist Mathematics
Yoshua Bengio: From System 1 Deep Learning to System 2 Deep Learning (NeurIPS 2019)
This is a combined slide/speaker video of Yoshua Bengio's talk at NeurIPS 2019. Slide-synced non-YouTube version is here: https://slideslive.com/neurips/neurips-2019-west-exhibition-hall-c-b3-live This is a clip on the Lex Clips channel that I mostly use to post video clips from the Artif
From playlist AI talks
Intractability in Algorithmic Game Theory - Tim Roughgarden
Tim Roughgarden Stanford University March 11, 2013 We discuss three areas of algorithmic game theory that have grappled with intractability. The first is the complexity of computing game-theoretic equilibria, like Nash equilibria. There is an urgent need for new ideas on this topic, to ena
From playlist Mathematics
Statistical Rethinking 2022 Lecture 03 - Geocentric Models
Linear regression from a Bayesian perspective Slides and course materials: https://github.com/rmcelreath/stat_rethinking_2022 Music Intro: https://www.youtube.com/watch?v=4y33h81phKU Flow: https://www.youtube.com/watch?v=ip4n8zaTg1w Pause: https://www.youtube.com/watch?v=1f-NQAgm-YM Cha
From playlist Statistical Rethinking 2022
Statistical Rethinking Winter 2019 Lecture 02
Lecture 02 of the Dec 2018 through March 2019 edition of Statistical Rethinking: A Bayesian Course with R and Stan. This lectures covers the material in Chapters 2 and 3 of the book.
From playlist Statistical Rethinking Winter 2019
From Deep Learning of Disentangled Representations to Higher-level Cognition
One of the main challenges for AI remains unsupervised learning, at which humans are much better than machines, and which we link to another challenge: bringing deep learning to higher-level cognition. We review earlier work on the notion of learning disentangled representations and deep g
From playlist AI talks
Occam's Razor and Statistical Mechanics - Singular Learning Theory Seminar 38
Edmund Lau presents Balasubramanian's paper "Statistical Inference, Occam’s Razor, and Statistical Mechanics on the Space of Probability Distributions". This involves - The principle of Bayesian model selection - Local behaviour of KL divergence / infinitesimal metric / Fisher information
From playlist Singular Learning Theory
Statistical physics and statistical inference (Lecture 2) by Marc MĂ©zard
INFOSYS-ICTS TURING LECTURES ARTIFICIAL INTELLIGENCE: SUCCESS, LIMITS, MYTHS AND THREATS SPEAKER: Marc Mézard (Director of Ecole normale supérieure - PSL University ) DATE: 06 January 2020, 16:00 to 17:30 VENUE: Chandrasekhar Auditorium, ICTS-TIFR, Bengaluru Lecture 1 (Public Lecture)
From playlist Infosys-ICTS Turing Lectures
How to determine if two events are mutually exclusive or not
👉 Learn how to find the probability of mutually exclusive events. Two events are said to be mutually exclusive when the two events cannot occur at the same time. For instance, when you throw a coin the event that a head appears and the event that a tail appears are mutually exclusive becau
From playlist Probability of Mutually Exclusive Events