counterfactual donkeys don t get high
play

Counterfactual Donkeys Dont Get High Mike Deigan Yale University - PowerPoint PPT Presentation

Aug 04, 2023 •158 likes •1.95k views

Counterfactual Donkeys Dont Get High Mike Deigan Yale University SuB22, Potsdam New Data 1 / 40 New Data Suppose Allie and Bert think Mary the potter probably didnt make anything yesterday. 1 / 40 New Data Suppose Allie and Bert

  1. Ordering Semantics + Dynamic Binding j is an A -possibility for i (or j ∈ / A / i ) i ff ∃ k ( g k = g i ∧ j ∈ { k } [ A ]). Selection function: (8) f ( A , i ) = { j : j ∈ / A / i ∧ ¬∃ k ( k ∈ / A / i ∧ w k < w i w j ) } . Finds the nearest A -possibility, where possibilities are ordered by their worlds. 11 / 40

  2. Ordering Semantics + Dynamic Binding j is an A -possibility for i (or j ∈ / A / i ) i ff ∃ k ( g k = g i ∧ j ∈ { k } [ A ]). Selection function: (8) f ( A , i ) = { j : j ∈ / A / i ∧ ¬∃ k ( k ∈ / A / i ∧ w k < w i w j ) } . Finds the nearest A -possibility, where possibilities are ordered by their worlds. (9) s [ A � C ] = { i : i ∈ s ∧ ∀ j ( j ∈ f ( A , i ) ⊃ { j } [ C ] � ∅ ) } C is verified by all selected possibilities 11 / 40

  3. Ordering Semantics + Dynamic Binding (3) If Balaam owned a donkey, he would beat it. 12 / 40

  4. Ordering Semantics + Dynamic Binding (3) If Balaam owned a donkey, he would beat it. (10) ∃ xDBO ( x ) � BB ( x ) 12 / 40

  5. Dynamic Binding + Ordering Semantics w 0

  6. Dynamic Binding + Ordering Semantics w 0 ¬ DBO DBO DBO = donkey that Balaam owns

  7. Dynamic Binding + Ordering Semantics w 0 ¬ BB BB ¬ DBO DBO DBO = donkey that Balaam owns BB = thing that Balaam beats

  8. Dynamic Binding + Ordering Semantics w 0 • e p • ¬ BB • h BB ¬ DBO DBO DBO = donkey that Balaam owns BB = thing that Balaam beats e = Eeyore h = Herbert p = Platero 13 / 40

  9. w 0 • e • p ¬ BB • h BB ¬ DBO DBO

  10. w 1 ¬ BB BB ∨ w 0 • e • p ¬ BB • h BB ¬ DBO DBO

  11. w 1 • e • p ¬ BB • h BB ∨ w 0 • e • p ¬ BB • h BB ¬ DBO DBO

  12. w 2 • e • p ¬ BB • h BB ∨ w 1 • e • p ¬ BB • h BB ∨ w 0 • e • p ¬ BB • h BB ¬ DBO DBO

  13. w 3 • p • e ¬ BB • h BB ∨ w 2 • e • p ¬ BB • h BB ∨ w 1 • e • p ¬ BB • h BB ∨ w 0 • e • p ¬ BB • h BB ¬ DBO DBO

  14. w 3 • p • e ¬ BB • h BB ∨ w 2 • e • p ¬ BB • h BB ∨ w 1 • e • p ¬ BB • h BB ∨ w 0 • e • p ¬ BB • h � w 0 , g x → e � � w 0 , g x → p � � w 0 , g x → h � BB ¬ DBO DBO

  15. w 3 • p • e ¬ BB • h � w 3 , g x → e � � w 3 , g x → p � � w 3 , g x → h � BB ∨ w 2 • e • p ¬ BB • h � w 2 , g x → e � � w 2 , g x → p � � w 2 , g x → h � BB ∨ w 1 • e • p ¬ BB � w 1 , g x → e � � w 1 , g x → p � � w 1 , g x → h � • h BB ∨ w 0 • e • p ¬ BB • h � w 0 , g x → e � � w 0 , g x → p � � w 0 , g x → h � BB ¬ DBO DBO

  16. w 3 • p • e ¬ BB • h � w 3 , g x → e � � w 3 , g x → p � � w 3 , g x → h � = = BB ∨ w 2 • e • p ¬ BB • h � w 2 , g x → e � � w 2 , g x → p � � w 2 , g x → h � = = BB ∨ w 1 • e • p ¬ BB � w 1 , g x → e � � w 1 , g x → p � � w 1 , g x → h � = = • h BB ∨ w 0 • e • p ¬ BB • h � w 0 , g x → e � � w 0 , g x → p � � w 0 , g x → h � = = BB ¬ DBO DBO

  17. w 3 • p • e ¬ BB • h � w 3 , g x → e � � w 3 , g x → p � � w 3 , g x → h � = = BB ∨ ∨ w 2 • e • p ¬ BB • h � w 2 , g x → e � � w 2 , g x → p � � w 2 , g x → h � = = BB ∨ ∨ w 1 • e • p ¬ BB � w 1 , g x → e � � w 1 , g x → p � � w 1 , g x → h � = = • h BB ∨ ∨ w 0 • e • p ¬ BB • h � w 0 , g x → e � � w 0 , g x → p � � w 0 , g x → h � = = BB ¬ DBO DBO

  18. w 3 • p • e ¬ BB • h � w 3 , g x → e � � w 3 , g x → p � � w 3 , g x → h � = = BB ∨ ∨ w 2 • e • p ¬ BB • h � w 2 , g x → e � � w 2 , g x → p � � w 2 , g x → h � = = BB ∨ ∨ w 1 • e • p ¬ BB � w 1 , g x → e � � w 1 , g x → p � � w 1 , g x → h � = = • h BB ∨ ∨ w 0 • e • p ¬ BB • h � w 0 , g x → e � � w 0 , g x → p � � w 0 , g x → h � = = BB ¬ DBO DBO

  19. w 3 • p • e ¬ BB • h � w 3 , g x → e � � w 3 , g x → p � � w 3 , g x → h � = = BB ∨ ∨ w 2 • e • p ¬ BB • h � w 2 , g x → e � � w 2 , g x → p � � w 2 , g x → h � = = BB ∨ ∨ w 1 • e • p ¬ BB � w 1 , g x → e � � w 1 , g x → p � � w 1 , g x → h � = = • h BB ∨ ∨ w 0 • e • p ¬ BB • h � w 0 , g x → e � � w 0 , g x → p � � w 0 , g x → h � = = BB ¬ DBO DBO

  20. w 3 • p • e ¬ BB • h � w 3 , g x → e � � w 3 , g x → p � � w 3 , g x → h � = = BB ∨ ∨ w 2 • e • p ¬ BB • h � w 2 , g x → e � � w 2 , g x → p � � w 2 , g x → h � = = BB ∨ ∨ w 1 • e • p ¬ BB � w 1 , g x → e � � w 1 , g x → p � � w 1 , g x → h � = = • h BB ∨ ∨ w 0 • e • p ¬ BB • h � w 0 , g x → e � � w 0 , g x → p � � w 0 , g x → h � = = BB ¬ DBO DBO

  21. w 3 • p • e ¬ BB • h � w 3 , g x → e � � w 3 , g x → p � � w 3 , g x → h � = = BB ∨ ∨ w 2 • e • p ¬ BB • h � w 2 , g x → e � � w 2 , g x → p � � w 2 , g x → h � = = BB ∨ ∨ w 1 • e • p ¬ BB � w 1 , g x → e � � w 1 , g x → p � � w 1 , g x → h � = = • h BB ∨ ∨ w 0 • e • p ¬ BB • h � w 0 , g x → e � � w 0 , g x → p � � w 0 , g x → h � = = BB ¬ DBO DBO 14 / 40

  22. w 3 � w 3 , g x → p � w 1 • e • p ¬ BB � w 1 , g x → h � • h BB ¬ DBO DBO ¬ BB DBO

  23. w 3 � w 3 , g x → p � ∃ xDBO ( x ) � BB ( x ) w 1 • e • p ¬ BB � w 1 , g x → h � • h BB ¬ DBO DBO ¬ BB DBO

  24. w 3 � w 3 , g x → p � ∃ xDBO ( x ) � BB ( x ) w 1 • e • p ¬ BB � w 1 , g x → h � ∀ j ( j ∈ f ( A , i ) { j } [ BB ( x )] � ∅ • h BB ¬ DBO DBO ¬ BB DBO

  25. w 3 � w 3 , g x → p � ∃ xDBO ( x ) � BB ( x ) w 1 • e • p ¬ BB � w 1 , g x → h � ∀ j ( j ∈ f ( A , i ) { j } [ BB ( x )] � ∅ • h BB ¬ DBO DBO {� w 1 , g x → h �} [ BB ( x )] ¬ BB DBO

  26. w 3 � w 3 , g x → p � ∃ xDBO ( x ) � BB ( x ) w 1 • e • p ¬ BB � w 1 , g x → h � ∀ j ( j ∈ f ( A , i ) { j } [ BB ( x )] � ∅ • h BB ¬ DBO DBO {� w 1 , g x → h �} [ BB ( x )] ¬ BB w 1 ∈ � BB ( h ) � ? DBO

  27. w 3 � w 3 , g x → p � ∃ xDBO ( x ) � BB ( x ) w 1 • e • p ¬ BB � w 1 , g x → h � ∀ j ( j ∈ f ( A , i ) { j } [ BB ( x )] � ∅ • h BB ¬ DBO DBO {� w 1 , g x → h �} [ BB ( x )] ¬ BB w 1 ∈ � BB ( h ) � ? ✓ DBO

  28. w 3 � w 3 , g x → p � ∃ xDBO ( x ) � BB ( x ) w 1 • e • p ¬ BB � w 1 , g x → h � ∀ j ( j ∈ f ( A , i ) { j } [ BB ( x )] � ∅ • h BB ¬ DBO DBO {� w 1 , g x → h �} [ BB ( x )] = {� w 1 , g x → h �} � ∅ ¬ BB w 1 ∈ � BB ( h ) � ? ✓ DBO

  29. w 3 � w 3 , g x → p � ∃ xDBO ( x ) � BB ( x ) ✓ w 1 • e • p ¬ BB � w 1 , g x → h � ∀ j ( j ∈ f ( A , i ) { j } [ BB ( x )] � ∅ • h BB ¬ DBO DBO {� w 1 , g x → h �} [ BB ( x )] = {� w 1 , g x → h �} � ∅ ¬ BB w 1 ∈ � BB ( h ) � ? ✓ DBO 15 / 40

  30. Ordering Semantics + Dynamic Binding Problem: no universal entailments 16 / 40

  31. Ordering Semantics + Dynamic Binding Problem: no universal entailments (11) If Balaam owned a donkey, he would beat it. (12) a. If Herbert were a donkey Balaam owned, Balaam would beat Herbert. b. If Eeyore were a donkey Balaam owned, Balaam would beat Eeyore. c. If Platero were a donkey Balaam owned, Balaam would beat Platero. 16 / 40

  32. Ordering Semantics + Dynamic Binding Problem: no universal entailments (11) If Balaam owned a donkey, he would beat it. (12) a. If Herbert were a donkey Balaam owned, Balaam would beat Herbert. b. If Eeyore were a donkey Balaam owned, Balaam would beat Eeyore. c. If Platero were a donkey Balaam owned, Balaam would beat Platero. 16 / 40

  33. Ordering Semantics + Dynamic Binding (12-b) If Eeyore were a donkey Balaam owned, Balaam would beat Eeyore. (13) DBO ( e ) � BB ( e ) 17 / 40

  34. w 3 • p • e ¬ BB • h � w 3 , g x → e � � w 3 , g x → p � � w 3 , g x → h � = = BB ∨ ∨ w 2 • e • p ¬ BB • h � w 2 , g x → e � � w 2 , g x → p � � w 2 , g x → h � = = BB ∨ ∨ w 1 • e • p ¬ BB � w 1 , g x → e � � w 1 , g x → p � � w 1 , g x → h � = = • h BB ∨ ∨ w 0 • e • p ¬ BB • h � w 0 , g x → e � � w 0 , g x → p � � w 0 , g x → h � = = BB ¬ DBO DBO

  35. w 3 • p • e ¬ BB • h � w 3 , g x → e � � w 3 , g x → p � � w 3 , g x → h � = = BB ∨ ∨ w 2 • e • p ¬ BB • h � w 2 , g x → e � � w 2 , g x → p � � w 2 , g x → h � = = BB ∨ ∨ w 1 • e • p ¬ BB � w 1 , g x → e � � w 1 , g x → p � � w 1 , g x → h � = = • h BB ∨ ∨ w 0 • e • p ¬ BB • h � w 0 , g x → e � � w 0 , g x → p � � w 0 , g x → h � = = BB ¬ DBO DBO

  36. w 3 • p • e ¬ BB • h � w 3 , g x → e � � w 3 , g x → p � � w 3 , g x → h � = = BB ∨ ∨ w 2 • e • p ¬ BB • h � w 2 , g x → e � � w 2 , g x → p � � w 2 , g x → h � = = BB ∨ ∨ w 1 • e • p ¬ BB � w 1 , g x → e � � w 1 , g x → p � � w 1 , g x → h � = = • h BB ∨ ∨ w 0 • e • p ¬ BB • h � w 0 , g x → e � � w 0 , g x → p � � w 0 , g x → h � = = BB ¬ DBO DBO 18 / 40

  37. w 3 w 2 • e • p ¬ BB • h � w 2 , g x → e � � w 2 , g x → p � � w 2 , g x → h � BB ¬ DBO DBO � w 1 , g x → p � ¬ BB DBO

  38. w 3 DBO ( e ) � BB ( e ) w 2 • e • p ¬ BB • h � w 2 , g x → e � � w 2 , g x → p � � w 2 , g x → h � BB ¬ DBO DBO � w 1 , g x → p � ¬ BB DBO

  39. w 3 DBO ( e ) � BB ( e ) w 2 • e • p ¬ BB • h � w 2 , g x → e � � w 2 , g x → p � � w 2 , g x → h � BB ¬ DBO DBO ∀ j ( j ∈ f ( A , i ) { j } [ BB ( e )] � ∅ � w 1 , g x → p � ¬ BB DBO

  40. w 3 DBO ( e ) � BB ( e ) w 2 • e • p ¬ BB • h � w 2 , g x → e � � w 2 , g x → p � � w 2 , g x → h � BB ¬ DBO DBO ∀ j ( j ∈ f ( A , i ) { j } [ BB ( e )] � ∅ � w 1 , g x → p � w 2 ∈ � BB ( e ) � ? ¬ BB DBO

  41. w 3 DBO ( e ) � BB ( e ) w 2 • e • p ¬ BB • h � w 2 , g x → e � � w 2 , g x → p � � w 2 , g x → h � BB ¬ DBO DBO ∀ j ( j ∈ f ( A , i ) { j } [ BB ( e )] � ∅ � w 1 , g x → p � w 2 ∈ � BB ( e ) � ? ✗ ¬ BB DBO

  42. w 3 DBO ( e ) � BB ( e ) ✗ w 2 • e • p ¬ BB • h � w 2 , g x → e � � w 2 , g x → p � � w 2 , g x → h � BB ¬ DBO DBO ∀ j ( j ∈ f ( A , i ) { j } [ BB ( e )] � ∅ � w 1 , g x → p � w 2 ∈ � BB ( e ) � ? ✗ ¬ BB DBO 19 / 40

  43. Ordering Semantics + Dynamic Binding Problem: no universal entailments (14) If Balaam owned a donkey, he would beat it. (15) a. If Herbert were a donkey Balaam owned, Balaam would beat Herbert. b. If Eeyore were a donkey Balaam owned, Balaam would beat Eeyore. c. If Platero were a donkey Balaam owned, Balaam would beat Platero. 20 / 40

  44. Ordering Semantics + Dynamic Binding Problem: no universal entailments (14) If Balaam owned a donkey, he would beat it. (15) a. If Herbert were a donkey Balaam owned, Balaam would beat Herbert. b. If Eeyore were a donkey Balaam owned, Balaam would beat Eeyore. c. If Platero were a donkey Balaam owned, Balaam would beat Platero. How to fix this? 20 / 40

  45. Ordering Semantics + Dynamic Binding Problem: no universal entailments (14) If Balaam owned a donkey, he would beat it. (15) a. If Herbert were a donkey Balaam owned, Balaam would beat Herbert. b. If Eeyore were a donkey Balaam owned, Balaam would beat Eeyore. c. If Platero were a donkey Balaam owned, Balaam would beat Platero. How to fix this? Route 1: special orderings Route 2: high readings 20 / 40

  46. Route 1: Special Orderings Walker and Romero (2015): universal entailments would follow from A � C i ff the closeness ordering were such that 21 / 40

  47. Route 1: Special Orderings Walker and Romero (2015): universal entailments would follow from A � C i ff the closeness ordering were such that for any a , b ∈ D , the closest world which combines with g x → a to form an A -possibility is as close as the closest world which combines with g x → b to form an A -possibility. 21 / 40

  48. Route 1: Special Orderings Walker and Romero (2015): universal entailments would follow from A � C i ff the closeness ordering were such that for any a , b ∈ D , the closest world which combines with g x → a to form an A -possibility is as close as the closest world which combines with g x → b to form an A -possibility. An ordering set S is special relative to a state s and sentence A i ff (16) ∀ i ( i ∈ s ⊃ ∀ j ( j ∈ / A / i ⊃ ∃ k ( k ∈ f ( A , i ) ∧ g j = g k ))) For all possibilities i in s , if j is an A -possibility for i , then among the nearest (relative to i ) A -possibilities is a possibility which shares an assigment with j . 21 / 40

  49. w 3 • p • e ¬ BB • h � w 3 , g x → p � BB ∨ w 2 • e • p ¬ BB • h BB ∨ w 1 • e • p ¬ BB • h BB ∨ w 0 • e • p ¬ BB • h BB ¬ DBO DBO

  50. w 3 • p • e ¬ BB • h � w 3 , g x → p � BB ∨ w 2 • e • p ¬ BB • h BB ∨ w 1 • e • p ¬ BB • h BB ∨ w 0 • e • p ¬ BB • h BB ¬ DBO DBO

  51. w 3 • p • e ¬ BB • h � w 3 , g x → p � BB ∨ w 2 • e • p ¬ BB • h BB ∨ w 1 • e • p ¬ BB • h BB ∨ w 0 • e • p ¬ BB • h BB ¬ DBO DBO

  52. w 3 • p • e ¬ BB • h � w 3 , g x → p � BB ∨ w 2 • e • p ¬ BB • h BB ∨ w 1 • e • p ¬ BB • h BB ∨ w 0 • e • p ¬ BB • h BB ¬ DBO DBO 22 / 40

  53. w 3 • p • e ¬ BB • h � w 3 , g x → e � � w 3 , g x → p � � w 3 , g x → h � = = BB = = w 2 • e • p ¬ BB • h � w 2 , g x → e � � w 2 , g x → p � � w 2 , g x → h � = = BB = = w 1 • e • p ¬ BB � w 1 , g x → e � � w 1 , g x → p � � w 1 , g x → h � = = • h BB ∨ ∨ w 0 • e • p ¬ BB • h � w 0 , g x → e � � w 0 , g x → p � � w 0 , g x → h � = = BB ¬ DBO DBO

  54. w 3 • p • e ¬ BB • h � w 3 , g x → e � � w 3 , g x → p � � w 3 , g x → h � = = BB = = w 2 • e • p ¬ BB • h � w 2 , g x → e � � w 2 , g x → p � � w 2 , g x → h � = = BB = = w 1 • e • p ¬ BB � w 1 , g x → e � � w 1 , g x → p � � w 1 , g x → h � = = • h BB ∨ ∨ w 0 • e • p ¬ BB • h � w 0 , g x → e � � w 0 , g x → p � � w 0 , g x → h � = = BB ¬ DBO DBO

  55. w 3 • p • e ¬ BB • h � w 3 , g x → e � � w 3 , g x → p � � w 3 , g x → h � = = BB = = w 2 • e • p ¬ BB • h � w 2 , g x → e � � w 2 , g x → p � � w 2 , g x → h � = = BB = = w 1 • e • p ¬ BB � w 1 , g x → e � � w 1 , g x → p � � w 1 , g x → h � = = • h BB ∨ ∨ w 0 • e • p ¬ BB • h � w 0 , g x → e � � w 0 , g x → p � � w 0 , g x → h � = = BB ¬ DBO DBO 23 / 40

Recommend

Counterfactual Donkeys and the Modal Horizon Andreas Walker and Maribel Romero Counterfactual

Counterfactual Donkeys and the Modal Horizon Andreas Walker and Maribel Romero Counterfactual

Counterfactual Donkeys and the Modal Horizon Andreas Walker and Maribel Romero Counterfactual Donkeys and the Modal Horizon Andreas Walker and Maribel Romero 1 Introduction Counterfactual Donkey Sentences 2 Readings High and low readings 3

593 views • 30 slides
GUARD DONKEYS BY BRUCE AND ANGELA MCLEISH Guard Donkeys by Bruce &amp; Angela McLeish The

GUARD DONKEYS BY BRUCE AND ANGELA MCLEISH Guard Donkeys by Bruce &amp; Angela McLeish The

GUARD DONKEYS BY BRUCE AND ANGELA MCLEISH Guard Donkeys by Bruce &amp; Angela McLeish The following notes are from our experience over the last six years. They are indicative only of our own experience and opinions, and we have had no

414 views • 13 slides
Counterfactual Policy Evaluation in Reproducing Kernel Hilbert Spaces Krikamol Muandet Max

Counterfactual Policy Evaluation in Reproducing Kernel Hilbert Spaces Krikamol Muandet Max

Counterfactual Policy Evaluation in Reproducing Kernel Hilbert Spaces Krikamol Muandet Max Planck Institute for Intelligent Systems Tbingen, Germany Jeju, Korea February 22, 2019 Krikamol Muandet Counterfactual Learning in RKHS Jeju,

1.14k views • 61 slides
Counterfactual Regret Minimization and Domination in Extensive-Form Games Richard Gibson

Counterfactual Regret Minimization and Domination in Extensive-Form Games Richard Gibson

Counterfactual Regret Minimization and Domination in Extensive-Form Games Richard Gibson University of Alberta Edmonton, Alberta, Canada Overview Counterfactual Regret Minimization (CFR) Overview Counterfactual Regret Minimization (CFR)

479 views • 36 slides
Counterfactual-based mediation analysis Workshop 2 Rhian Daniel London School of Hygiene and

Counterfactual-based mediation analysis Workshop 2 Rhian Daniel London School of Hygiene and

Counterfactual-based mediation analysis Workshop 2 Rhian Daniel London School of Hygiene and Tropical Medicine CIMPOD 28th February, 2017 Rhian Daniel/Counterfactual-based mediation analysisWorkshop 2 1/55 Setting the scene Case study

1.85k views • 171 slides
Counterfactual-based mediation analysis Workshop 1 Rhian Daniel London School of Hygiene and

Counterfactual-based mediation analysis Workshop 1 Rhian Daniel London School of Hygiene and

Counterfactual-based mediation analysis Workshop 1 Rhian Daniel London School of Hygiene and Tropical Medicine CIMPOD 27th February, 2017 Rhian Daniel/Counterfactual-based mediation analysisWorkshop 1 1/51 Setting the scene Case study

1.78k views • 131 slides
The Actual, the Counterfactual and the Possible An Oceanic-centric approach to tense and modality

The Actual, the Counterfactual and the Possible An Oceanic-centric approach to tense and modality

The Actual, the Counterfactual and the Possible An Oceanic-centric approach to tense and modality Kilu von Prince AFLA, August 20 2020 Background Three modal domains handle/10900/91242 . https://publikationen.uni-tuebingen.de/xmlui/

983 views • 71 slides
A Review of Counterfactual thinking and the first instinct fallacy by Kruger, Wirtz, and

A Review of Counterfactual thinking and the first instinct fallacy by Kruger, Wirtz, and

A Review of Counterfactual thinking and the first instinct fallacy by Kruger, Wirtz, and Miller (2005) BY RICHARD THRIPP EXP 6506 UNIVERSITY OF CENTRAL FLORIDA NOVEMBER 5, 2015 What is counterfac actual t thinking? A

388 views • 23 slides
Dame Vivien Rose DBE Justice of the High Court, Chancery Division 1. There have been many

Dame Vivien Rose DBE Justice of the High Court, Chancery Division 1. There have been many

SWEDISH KONKURRENSVERKET CONFERENCE ON THE PROS AND CONS OF COUNTERFACTUALS STOCKHOLM 6 DECEMBER 2013 PREDICTING THE PAST CONSTRUCTING THE COUNTERFACTUAL IN ANTITRUST DAMAGES CLAIMS Dame Vivien Rose DBE Justice of the High Court, Chancery

321 views • 11 slides
Independent and conditionally independent counterfactual distributions Marcin Wolski European

Independent and conditionally independent counterfactual distributions Marcin Wolski European

Independent and conditionally independent counterfactual distributions Marcin Wolski European Investment Bank M.Wolski@eib.org Society for Nonlinear Dynamics and Econometrics Tokyo March 19, 2018 Views expressed in this study are those of

591 views • 30 slides
Fair Classification with Counterfactual Learning Dr. Maryam Tavakol 1/15 What is Fairness 2/15

Fair Classification with Counterfactual Learning Dr. Maryam Tavakol 1/15 What is Fairness 2/15

July 2020 Fair Classification with Counterfactual Learning Dr. Maryam Tavakol 1/15 What is Fairness 2/15 ML/DM Basics Collecting the data (pre-processing, cleaning, etc.) Learning a model that fits the data (optimizing an objective) 3/15

447 views • 20 slides
Reliable Decision Support using Counterfactual Models Suchi Saria Assistant Professor

Reliable Decision Support using Counterfactual Models Suchi Saria Assistant Professor

Reliable Decision Support using Counterfactual Models Suchi Saria Assistant Professor Computer Science, Applied Math &amp; Stats and Health Policy Institute for Computational Medicine w/ Peter Schulam, PhD candidate Example: Customer Churn !

853 views • 74 slides
Single World Intervention Graphs (SWIGs): Unifying the Counterfactual and Graphical Approaches to

Single World Intervention Graphs (SWIGs): Unifying the Counterfactual and Graphical Approaches to

Single World Intervention Graphs (SWIGs): Unifying the Counterfactual and Graphical Approaches to Causality Thomas Richardson Department of Statistics University of Washington Joint work with James Robins (Harvard School of Public Health)

930 views • 82 slides
The Choice of Effect Measure for Binary Outcomes: Introducing Counterfactual Outcome State

The Choice of Effect Measure for Binary Outcomes: Introducing Counterfactual Outcome State

The Choice of Effect Measure for Binary Outcomes: Introducing Counterfactual Outcome State Transition parameters Anders Huitfeldt The Meta-Research Innovation Center at Stanford (Based on working papers written in collaboration with Andrew

772 views • 41 slides
Trade in Jobs: a counterfactual exercise Robert Stehrer &amp; Roman Stllinger The Vienna

Trade in Jobs: a counterfactual exercise Robert Stehrer &amp; Roman Stllinger The Vienna

1 Trade in Jobs: a counterfactual exercise Robert Stehrer &amp; Roman Stllinger The Vienna Institute for International Economic Studies (wiiw), Austria WIOD Conference: Causes and Consequences of Globalization April 24 th -26th, 2012

499 views • 17 slides
Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich

Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich

Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology ACL 2019 Ran Zmigrod, Sebastian J. Mielke , Hanna Wallach, Ryan Cotterell University of Cambridge // Johns Hopkins University // Microsoft

778 views • 58 slides
Measuring social biases in human annotators using counterfactual queries in Crowdsourcing BHAVYA

Measuring social biases in human annotators using counterfactual queries in Crowdsourcing BHAVYA

Measuring social biases in human annotators using counterfactual queries in Crowdsourcing BHAVYA GHAI PhD Candidate, Computer Science Department Stony Brook University Adviser: Prof. Klaus Mueller Algorithmic Bias When Algorithms exhibit

291 views • 16 slides
Causation as Production and Dependence or, A Model-Invariant Tieory of Causation Counterfactual

Causation as Production and Dependence or, A Model-Invariant Tieory of Causation Counterfactual

Causation as Production and Dependence or, A Model-Invariant Tieory of Causation Counterfactual Causal Models 2. diagram is correct. are causally determined by each other. Ill assume throughout that the canonical model of a neuron default,

257 views • 9 slides
Counterfactual evaluation of machine learning models Michael Manapat @mlmanapat O N L I N E F

Counterfactual evaluation of machine learning models Michael Manapat @mlmanapat O N L I N E F

Counterfactual evaluation of machine learning models Michael Manapat @mlmanapat O N L I N E F R A U D O N L I N E F R A U D O N L I N E F R A U D R A D A R Rules engine (block if amount &gt; $100 and more than 3 charges from IP

581 views • 30 slides
Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback Carolin

Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback Carolin

Introduction Task Objectives Experiments Conclusion Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback Carolin Lawrence , Stefan Riezler Heidelberg University Institute for Computational Linguistics

430 views • 18 slides
Deep Counterfactual Regret Min inimization Noam Brown* 12 , Adam Lerer* 1 , Sam Gross 1 , Tuomas

Deep Counterfactual Regret Min inimization Noam Brown* 12 , Adam Lerer* 1 , Sam Gross 1 , Tuomas

Deep Counterfactual Regret Min inimization Noam Brown* 12 , Adam Lerer* 1 , Sam Gross 1 , Tuomas Sandholm 23 *Equal Contribution 1 Facebook AI Research 2 Carnegie Mellon University 3 Strategic Machine Inc., Strategy Robot Inc., and Optimized

487 views • 11 slides
Measuring the Impact of Microcredit with Counterfactual Impact Evaluations Beatrice dHombres,

Measuring the Impact of Microcredit with Counterfactual Impact Evaluations Beatrice dHombres,

The European Commissions science and knowledge service Joint Research Centre Measuring the Impact of Microcredit with Counterfactual Impact Evaluations Beatrice dHombres, Timothee Demont Leandro Elia, Corinna Ghirelli Joint Research

737 views • 51 slides
Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributions Hao

Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributions Hao

Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributions Hao Wang, Berk Ustun, Flavio P. Calmon hao_wang@g.harvard.edu, {berk,Flavio}@seas.harvard.edu 0 Outline Use cases A bank enters a new market and

297 views • 9 slides
Counterfactual Visual Explanations Yash Goyal Ziyan Wu Jan Ernst Dhruv Batra Devi Parikh

Counterfactual Visual Explanations Yash Goyal Ziyan Wu Jan Ernst Dhruv Batra Devi Parikh

Counterfactual Visual Explanations Yash Goyal Ziyan Wu Jan Ernst Dhruv Batra Devi Parikh Stefan Lee (Georgia Tech) (Siemens) (Siemens) (Georgia Tech) (Georgia Tech) (Georgia Tech) Counterfactual Visual Explanations A Eared Grebe

871 views • 31 slides

More recommend