COMMENTS ON By Judea Pearl (UCLA) notation 1990’s Artificial Intelligence Hoover From Hoover (2004) “Lost Causes” Hoover slide notation 1990’s Artificial Intelligence Already unified more? ^ additional? ^ (Statistical) Commendable! Already permitted additional? ^ additional? ^ P. 215 (Statistical) Commendable! Already permitted additional? ^ additional? ^ WHITE & CHALAK PICTURE OF UNIFICATION 1950 - 2005 SEM Neyman-Rubin DAGs 2006 Settable System MY PICTURE OF UNIFICATION 1920 - 1990 Informal SEM Neyman-Rubin Informal Diagrams 1990 - 2000 Formal SEM Graphs Complete Neyman-Rubin DAGs 2006 (W&C) Multi-agent extension CAUSAL ANALYSIS WITHOUT TEARS TRADITIONAL STATISTICAL INFERENCE PARADIGM Data P Joint Distribution Q(P) (Aspects of P) Inference e.g., Infer whether customers who bought product A would also buy product B. Q = P(B|A) THE CAUSAL INFERENCE PARADIGM Data Joint Distribution Data Generating Model Q(M) (Aspects of M) Inference Some Q(M) cannot be inferred from P. e.g., Infer whether customers who bought product A would still buy A if we were to double the price. FROM STATISTICAL TO CAUSAL ANALYSIS: 1. THE DIFFERENCES Probability and statistics deal with static relations Statistics Probability inferences Data from passive observations Causal analysis deals with changes (dynamics) 1. Effects of Data interventions Causal 2. Causes of Model Causal effects assumptions 3. Explanations Experiments joint distribution FAMILIAR CAUSAL MODEL ORACLE FOR MANIPILATION X Y Z INPUT OUTPUT WHY CAUSALITY NEEDS SPECIAL MATHEMATICS SEM Equations are Non-algebraic: Y = 2X X=1 X=1 Y=2 Process information Static information Had X been 3, Y would be 6. If we raise X to 3, Y would be 6. Must “wipe out” X = 1. CAUSAL MODELS AND CAUSAL DIAGRAMS Definition: A causal model is a 3-tuple M = V,U,F with a mutilation operator do(x): M Mx where: (i) V = {V1…,Vn} endogenous variables, (ii) U = {U1,…,Um} background variables (iii) F = set of n functions, fi : V \ Vi U Vi vi = fi(pai,ui) PAi V \ Vi Ui U • CAUSAL MODELS AND CAUSAL DIAGRAMS Definition: A causal model is a 3-tuple M = V,U,F with a mutilation operator do(x): M Mx where: (i) V = {V1…,Vn} endogenous variables, (ii) U = {U1,…,Um} background variables (iii) F = set of n functions, fi : V \ Vi U Vi vi = fi(pai,ui) PAi V \ Vi Ui U q b1 p d1i u1 p b2q d 2 w u2 U1 I W Q P U2 PAQ CAUSAL MODELS AND MUTILATION Definition: A causal model is a 3-tuple M = V,U,F with a mutilation operator do(x): M Mx where: (i) V = {V1…,Vn} endogenous variables, (ii) U = {U1,…,Um} background variables (iii) F = set of n functions, fi : V \ Vi U Vi vi = fi(pai,ui) PAi V \ Vi Ui U (iv) Mx= U,V,Fx, X V, x X where Fx = {fi: Vi X } {X = x} (Replace all functions fi corresponding to X with the constant functions X=x) • CAUSAL MODELS AND MUTILATION Definition: A causal model is a 3-tuple M = V,U,F with a mutilation operator do(x): M Mx where: (i) V = {V1…,Vn} endogenous variables, (attributes) (ii) U = {U1,…,Um} background variables (iii) F = set of n functions, fi : V \ Vi U Vi vi = fi(pai,ui) PAi V \ Vi Ui U (iv) q b1 p d1i u1 p b2q d 2 w u2 U1 I W Q P U2 CAUSAL MODELS AND MUTILATION Definition: A causal model is a 3-tuple M = V,U,F with a mutilation operator do(x): M Mx where: (i) V = {V1…,Vn} endogenous variables, (attributes) (ii) U = {U1,…,Um} background variables (iii) F = set of n functions, fi : V \ Vi U Vi vi = fi(pai,ui) PAi V \ Vi Ui U (iv) M p q b1 p d1i u1 U1 p b2q d 2 w u2 p p0 I W U2 Q P P = p0 PROBABILISTIC CAUSAL MODELS Definition: A causal model is a 3-tuple M = V,U,F with a mutilation operator do(x): M Mx where: (i) V = {V1…,Vn} endogenous variables, (ii) U = {U1,…,Um} background variables (iii) F = set of n functions, fi : V \ Vi U Vi vi = fi(pai,ui) PAi V \ Vi Ui U (iv) Mx= U,V,Fx, X V, x X where Fx = {fi: Vi X } {X = x} (Replace all functions fi corresponding to X with the constant functions X=x) Definition (Probabilistic Causal Model): M, P(u) P(u) is a probability assignment to the variables in U. CAUSAL MODELS AND COUNTERFACTUALS Definition: The sentence: “Y would be y (in situation u), had X been x,” denoted Yx(u) = y, means: The solution for Y in a mutilated model Mx, (i.e., the equations for X replaced by X = x) and U=u, is equal to y. •Joint probabilities of counterfactuals: P(Yx y, Z w z ) u:Yx (u ) y,Z w (u ) z P(u ) GRAPHICAL – COUNTERFACTUALS SYMBIOSIS Every causal model implies constraints on counterfactuals e.g., Yx, z (u ) Yx (u ) Yx Z y | X consistent, and readable from the graph. Every theorem in SEM is a theorem in N-R, and conversely. GRAPHICAL TEST OF IDENTIFICATION The causal effect of X on Y, P( y | do( x)) P(Yx (u ) y ) is identifiable in G if there is a set Z of variables such that Z d-separates X from Y in Gx. G Z1 Gx Z1 Z2 Z3 Z2 Z3 Z4 X Z Z6 Z5 Y Z4 X Z6 Moreover, P(y | do(x)) = P(y | x,z) P(z) z (“adjusting” for Z) Z5 Y RULES OF CAUSAL CALCULUS Rule 1: Ignoring observations P(y | do{x}, z, w) = P(y | do{x}, w) if (Y Z|X,W )G Rule 2: Action/observation exchange X P(y | do{x}, do{z}, w) = P(y | do{x},z,w) if (Y Z|X,W )G Rule 3: Ignoring actions XZ P(y | do{x}, do{z}, w) = P(y | do{x}, w) if (Y Z|X,W )G X Z(W) RECENT RESULTS ON IDENTIFICATION Theorem (Tian 2002): We can identify P(v | do{x}) (x a singleton) if and only if there is no child Z of X connected to X by a bi-directed path. X Z1 Z Zk RECENT RESULTS ON IDENTIFICATION (Cont.) • do-calculus is complete • A complete graphical criterion available • for identifying causal effects of any set on any set References: Shpitser and Pearl 2006 (AAAI, UAI) CONCLUSIONS Structural-model semantics enriched with logic + graphs leads to formal interpretation and practical assessments of wide variety of (if not all) causal and counterfactual relationships. e.g., causal effects, responsibility, direct and indirect effects Multi-agent systems? MULTI-AGENT GRAPHS Agent 1 Agent 2 ux1 ux2 X1 X2 uy1 u z1 Y1 Z1 uy2 u z2 Y2 Z2 WHITE & CHALAK PICTURE OF UNIFICATION 1950 - 2005 SEM Neyman-Rubin DAGs 2006 Settable System MY PICTURE OF UNIFICATION 1920 - 1990 Informal SEM Neyman-Rubin Informal Diagrams 1990 - 2000 Formal SEM Graphs Complete Neyman-Rubin DAGs 2006 (W&C) Multi-agent extension