Prediction and Solomonoff Pter Gcs Boston University Quantum - PowerPoint PPT Presentation

Feb 08, 2023 •476 likes •571 views

Prediction and Solomonoff Pter Gcs Boston University Quantum Foundations worshop, August 2014 Inductive inference Much of the discussion on the first day of the workshop dealt with the problem of inductive inference in generalquantum

Prediction and Solomonoff Péter Gács Boston University Quantum Foundations worshop, August 2014
Inductive inference Much of the discussion on the first day of the workshop dealt with the problem of inductive inference in general—quantum physics and cosmology did not seem relevant. There is an approach to inductive inference that I felt was ignored, and which can be seen a refinement of Occam’s Razor. In its generality, this approach is not trying to decide the “true” model to be used for prediction: it is just trying to be (nearly) as good as the best possible predictors that we humans (or computers) can produce. Solomonoff achieved (something like) this by chosing a universal prior in a Bayesian framework. It is related to the prior Charlie talked about yesterday, but is not the same.
The probabilities Turing machine T , one-way binary input tape. One-way output tape. Experiment: input is an infinite sequence of tosses of an independent unbiased coin. (Monkey at the keyboard.) M T ( x ) = P { outputted sequence begins with x } . The quantity M T ( x ) can be considered the algorithmic probability of the finite sequence x . Dependence on the choice of T : if T is universal of the type called optimal then this dependence is only minor (Charlie explained this). Fixing such an optimal machine U , write M ( x ) = M U ( x ) . This is (the best-known version of) Solomonoff’s prior.
The formula Given a sequence x of experimental results, M ( xy ) M ( x ) assigns a probability to the event that x will be continued by a sequence (or even just a symbol) y . Attractive: prediction power, combination of some deep principles. But: incomputable. So in applications, we must deal with the problem of approximating it.
Principle of indifference In Solomonoff’s theory, Laplace’s principle is revived in the following sense: all descriptions (inputs) of the same length are assigned the same probability.
The prediction theorem Solomonoff’s theorem restricts consideration to sources x 1 x 2 . . . with some computable probability distribution P . Let P ( x ) = the probability of the set of all infinite sequences starting with x . The theorem says that for all P , the expression M ( x 1 . . . x n b ) M ( x 1 . . . x n ) gets closer and closer to P ( x 1 ... x n b ) P ( x 1 ... x n ) (with very high P probability). The proof relies just on the fact that M ( x ) dominates all computable measures (even all lower semicomputable semimeasures, like itself).
All the usual measures considered by physicists are computable. Here is another example to illustrate the variety. Example Take a sequence x 1 x 2 . . . whose even-numbered binary digits are those of π , while its odd-numbered digits are random. Solomonoff’s formula will converge to 1 / 2 on the odd-numbered digits. On the even-numbered digits, it will get closer and closer to 1 if b equals the corresponding digit of π , and to 0 if it does not.

Recommend

Solomonoff Induction Violates Nicods Criterion Jan Leike and Marcus Hutter

Solomonoff Induction Violates Nicods Criterion Jan Leike and Marcus Hutter http://jan.leike.name/ Australian National University 23 June 2015 Outline The Paradox of Confirmation Solomonoff Induction Results Resolving the Paradox of

456 views • 33 slides

Making Solomonoff Induction Effective You Can Learn What You Can Bound J org Zimmermann and

Making Solomonoff Induction Effective You Can Learn What You Can Bound J org Zimmermann and Armin B. Cremers Institute of Computer Science University of Bonn, Germany 1 J org Zimmermann and Armin B. Cremers: Making Solomonoff Induction

425 views • 18 slides

Using Stata 16s lasso features for prediction and inference Di Liu StataCorp 1 / 50

Using Stata 16s lasso features for prediction and inference Di Liu StataCorp 1 / 50 Motivation I: Prediction What is a prediction? Prediction is to predict an outcome variable on new (unseen) data Good prediction minimizes mean-squared

763 views • 53 slides

Using lasso and related estimators for prediction Di Liu StataCorp July 12, 2019 1 / 20

Using lasso and related estimators for prediction Di Liu StataCorp July 12, 2019 1 / 20 Prediction What is a prediction? Prediction is to predict an outcome variable on new (unseen) data Good prediction minimizes mean-squared error (or other

217 views • 20 slides

Structured Prediction Introduction What is structured prediction? CS 6355: Structured Prediction

Structured Prediction Introduction What is structured prediction? CS 6355: Structured Prediction Our goal today To define a Structure and Structured Prediction 1 What are structures? 2 Examples of structured data? 3 Examples of structured

661 views • 34 slides

A prediction is not a decision -- it is only a component of a decision. Prediction

A prediction is not a decision -- it is only a component of a decision. Prediction Machines , Agarwal, et.al. ? Prediction + Judgement = Decision "Open the pod bay doors, Hal" 2001: A Space Odyssey How far should we go?

327 views • 6 slides

Summary of part I: prediction and RL Prediction is important for action selection The

Summary of part I: prediction and RL Prediction is important for action selection The problem: prediction of future reward The algorithm: temporal difference learning Neural implementation: dopamine dependent learning in BG A

939 views • 60 slides

Prediction and Odds 18.05 Spring 2017 Probabilistic Prediction Also called probabilistic

Prediction and Odds 18.05 Spring 2017 Probabilistic Prediction Also called probabilistic forecasting. Assign a probability to each outcome of a future experiment. Prediction: It will rain tomorrow. Probabilistic prediction: Tomorrow it

480 views • 26 slides

Prediction and Odds 18.05 Spring 2014 January 1, 2017 1 / 20 Probabilistic Prediction Also

Prediction and Odds 18.05 Spring 2014 January 1, 2017 1 / 20 Probabilistic Prediction Also called probabilistic forecasting. Assign a probability to each outcome of a future experiment. Prediction: It will rain tomorrow. Probabilistic

349 views • 20 slides

Prediction and Odds 18.05 Spring 2014 January 1, 2017 1 / 26 Probabilistic Prediction Also

Prediction and Odds 18.05 Spring 2014 January 1, 2017 1 / 26 Probabilistic Prediction Also called probabilistic forecasting. Assign a probability to each outcome of a future experiment. Prediction: It will rain tomorrow. Probabilistic

692 views • 26 slides

Prediction of RNA-RNA-Interaction 20 1 15 1 5 10 20 5 10 20 15 10 1 15 5 1 20 10

Prediction of RNA-RNA-Interaction 20 1 15 1 5 10 20 5 10 20 15 10 1 15 5 1 20 10 Can Alkan, Emre Karakoc, Joseph H. Nadeau, S. Cenk Sahinalp, Kaizhong Zhang. RNA-RNA interaction prediction and antisense RNA target search. JCB

627 views • 14 slides

Exposure Prediction and Exposure Prediction and Measurement Error in Air P ll ti Pollution and

Exposure Prediction and Exposure Prediction and Measurement Error in Air P ll ti Pollution and Health Studies d H lth St di Lianne Sheppard Adam A. Szpiro, Sun-Young Kim p g University of Washington CMAS Special Session, October 13, 2010

506 views • 16 slides

DBAASP Special prediction as a tool for the prediction of antimicrobial potency against particular

DBAASP Special prediction as a tool for the prediction of antimicrobial potency against particular target species Boris Vishnepolsky 1, *, Maya Grigolava 1 , George Zaalishvili 2 , Margarita Karapetian 2 and Malak Pirtskhalava 1, * 1 I.Beritashvili

987 views • 23 slides

Part-II Parametric Signal Modeling and Linear Prediction Theory 3. Linear Prediction Electrical

3 Linear Prediction Appendix: Detailed Derivations Part-II Parametric Signal Modeling and Linear Prediction Theory 3. Linear Prediction Electrical & Computer Engineering University of Maryland, College Park Acknowledgment: ENEE630 slides

392 views • 28 slides

Non parametric prediction and mapping of standing Non-parametric prediction and mapping of

Non parametric prediction and mapping of standing Non-parametric prediction and mapping of standing timber volume and biomass in a temperate forest Workshop IBS-Dre AGs Bayes Methodik, Rumliche Statistik, kologie und Umwelt Lbeck, Dez.

348 views • 23 slides

A story of two predictions Prediction A Uranus Prediction of additional, Orbital undiscovered

14.07.2016 ECT* Doctoral Training Program Timon Emken (CP 3 -Origins, University of Southern Denmark, Odense) Collaborators: Chris Kouvaris (CP 3 -Origins) A story of two predictions Prediction A Uranus Prediction of additional, Orbital

600 views • 35 slides

Improved Initialization and Prediction of Clouds in Numerical Weather Prediction Tom Aulign

Sixth Symposium on Data Assimilation. Washington, DC. Oct. 7-11, 2013 Improved Initialization and Prediction of Clouds in Numerical Weather Prediction Tom Aulign National Center for Atmospheric Research Acknowledgments: Gael Descombes,

255 views • 14 slides

CS 104 Computer Organization and Design Branch Prediction CS104:Branch Prediction 1 Branch

CS 104 Computer Organization and Design Branch Prediction CS104:Branch Prediction 1 Branch Prediction Quick Overview App App App Now that we know about SRAMs System software Mem CPU I/O CS104: Branch Prediction 2 Branch

677 views • 21 slides

Regulatory Motif Prediction in DNA Regulatory Motif Prediction in DNA Introduction: toward

Regulatory Motif Prediction in DNA Regulatory Motif Prediction in DNA Introduction: toward transcription regulatory networks Ab initio discovery of motifs by over-representation of regular expressions The weight matrix

1.19k views • 65 slides

Link prediction via matrix factorization Charles Elkan University of California, San Diego

Link prediction via matrix factorization Charles Elkan University of California, San Diego September 6, 2011 1 / 26 Outline Introduction: Three related prediction tasks 1 Link prediction in networks 2 Discussion 3 2 / 26 Link prediction

436 views • 27 slides

Bottom-up Estimation and Top-down Prediction for Multi-level Models: Solar Energy Prediction

Bottom-up Estimation and Top-down Prediction for Multi-level Models: Solar Energy Prediction Combining Information from Multiple Sources Jae-Kwang Kim Department of Statistics, Iowa State University Ross-Royall Symposium: Johns Hopkins

857 views • 37 slides

Prediction of Low Pressure Subcooled Burnout Test using General Prediction Methods Hyung Min Son a

Transactions of the Korean Nuclear Society Virtual Spring Meeting July 9-10, 2020 Prediction of Low Pressure Subcooled Burnout Test using General Prediction Methods Hyung Min Son a , Jonghark Park a a Korea Atomic Energy Research Institute,

177 views • 3 slides

Link prediction The link prediction space is vast and imbalanced : real approaches focus only in

Link prediction The link prediction space is vast and imbalanced : real approaches focus only in the 2-hop social neighborhood, i.e., friends-of- friends . A new source of promising candidates for link prediction: the places visited by each user.

764 views • 9 slides

Ethical challenges associated with prediction and early detection of dementia Dr Richard Milne

Ethical challenges associated with prediction and early detection of dementia Dr Richard Milne The promise of prediction The problems of prediction Right to know Right not to know Support ability to plan, manage Limited predictive power

377 views • 18 slides