Preference Elicitation in Single and Multiple User Settings Darius Braziunas, Craig Boutilier, 2005 (Boutilier, Patrascu, Poupart, Shuurmans, 2003, 2005) Nathanael Hyafil, Craig Boutilier, 2006a, 2006b Department of Computer Science University of Toronto

Overview Preference Elicitation in A.I. Single User Elicitation Foundations of Local queries [BB-05] Bayesian Elicitation [BB-05] Regret-based Elicitation [BPPS-03,05] Multi-agent Elicitation (Mechanism Design) One-Shot Elicitation [HB-06b] Sequential Mechanisms [HB-06a]

Preference Elicitation in AI Shopping for a Car: Luggage Capacity? Two Door? Cost? Engine Size? Color? Options?

The Preference Bottleneck Preference elicitation: the process of determining a user’s preferences/utilities to the extent necessary to make a decision on her behalf Why a bottleneck? preferences vary widely large (multiattribute) outcome spaces quantitative utilities (the “numbers”) difficult to assess

Automated Preference Elicitation The interesting questions: decomposition of preferences what preference info is relevant to the task at hand? when is the elicitation effort worth the improvement it offers in terms of decision quality? what decision criterion to use given partial utility info?

Overview Preference Elicitation in A.I. Single User Elicitation Constraint-based Optimization Factored Utility Models Types of Uncertainty Types of Queries Single User Elicitation Multi-agent Elicitation (Mechanism Design)

Constraint-based Decision Problems Constraint-based optimization (CBO): outcomes over variables X = {X1 … Xn} constraints C over X spell out feasible decisions generally compact structure, e.g., X1 & X2  ¬ X3 add a utility function u: Dom(X) → R preferences over configurations

Constraint-based Decision Problems Must express u compactly like C generalized additive independence (GAI) model proposed by Fishburn (1967) [and BG95] nice generalization of additive linear models given by graphical model capturing independence

Factored Utilities: GAI Models Set of K factors fk over subset of vars X[k] “local” utility for each local configuration [Fishburn67] u in this form exists iff lotteries p and q are equally preferred whenever p and q have the same marginals over each X[k] A B f1(A) a: 3 a: 1 f2(B) b: 3 b: 1 C f3(BC) bc: 12 bc: 2 … u(abc) = f1(a)+ f2(b)+ f3(bc)

Optimization with GAI Models f1(A) a: 3 a: 1 f2(B) b: 3 b: 1 A B C f3(BC) bc: 12 bc: 2 … Optimize using simple IP (or Var Elim, or…) number of vars linear in size of GAI model

Difficulties in CBO Constraint elicitation generally stable across different users Utility (objective) representation GAI solidifies many of intuitions in soft constraints Utility elicitation: how do we assess individual user preferences? need to elicit GAI model structure (independence) need to elicit (constraints on) GAI parameters need to make decisions with imprecise parameters

Strict Utility Function Uncertainty User’s actual utility u unknown Assume feasible set F U = [0,1]n allows for unquantified or “strict” uncertainty e.g., F a set of linear constraints on GAI terms How should one make a decision? elicit info? u(red,2door,280hp) > 0.4 u(red,2door,280hp) > u(blue,2door,280hp)

Strict Uncertainty Representation f1(L) l: [7,11] l: [2,5] L P N f2(L,N) l,n: [2,4] l,n: [1,2] Utility Function

Bayesian Utility Function Uncertainty User’s actual utility u unknown Assume density P over U = [0,1]n Given belief state P, EU of decision x is: EU(x , P) = U (px . u) P( u ) du Decision making is easy, but elicitation harder? must assess expected value of information in query

Bayesian Representation f1(L) l: L P N f2(L,N) l,n: … Utility Function

Query Types Comparison queries (is x preferred to x’ ?) impose linear constraints on parameters Sk fk(x[k]) > Sk fk(x’[k]) Interpretation is straightforward U

Query Types Bound queries (is fk(x[k]) > v ?) U response tightens bound on specific utility parameter can be phrased as a local standard gamble query U

Overview Preference Elicitation in A.I. Single User Elicitation Foundations of Local queries Bayesian Elicitation Regret-based Elicitation Multi-agent Elicitation (Mechanism Design) One-Shot Elicitation Sequential Mechanisms

Difficulties with Bound Queries Bound queries focus on local factors but values cannot be fixed without reference to others! seemingly “different” local prefs correspond to same u u(Color,Doors,Power) = u1(Color,Doors) + u2(Doors,Power) u(red,2door,280hp) = u1(red,2door) + u2(2door,280hp) u(red,4door,280hp) = u1(red,4door) + u2(4door,280hp) 10 6 1 4 9 6 3 3

Local Queries [BB05] We wish to avoid queries on whole outcomes can’t ask purely local outcomes but can condition on a subset of default values Conditioning set C(f) for factor fi(Xi) : variables that share factors with Xi setting default outcomes on C(f) renders Xi independent of remaining variables enables local calibration of factor values

Local Standard Gamble Queries Local std. gamble queries use “best” and “worst” (anchor) local outcomes -- conditioned on default values of conditioning set bound queries on other parameters relative to these gives local value function v(x[i]) (e.g., v(ABC) ) Hence we can legitimately ask local queries: But local Value Functions not enough: must calibrate: requires global scaling

Global Scaling Elicit utilities of anchor outcomes wrt global best and worst outcomes the 2*m “best” and “worst” outcomes for each factor these require global std gamble queries (note: same is true for pure additive models)

Bound Query Strategies Identify conditioning sets Ci for each factor fi Decide on “default” outcome For each fi identify top and bottom anchors e.g., the most and least preferred values of factor i given default values of Ci Queries available: local std gambles: use anchors for each factor, C-sets global std gambles: gives bounds on anchor utilities

Overview Preference Elicitation in A.I. Single User Elicitation Foundations of Local queries Bayesian Elicitation Regret-based Elicitation Multi-agent Elicitation (Mechanism Design) One-Shot Elicitation Sequential Mechanisms

Partial preference information Bayesian uncertainty Probability distribution p over utility functions Maximize expected (expected) utility MEU decision x* = arg maxx Ep [u(x)] Consider: elicitation costs values of possible decisions optimal tradeoffs between elicitation effort and improvement in decision quality Priors, updating distributions mixtures of (truncated) Gaussians, uniforms, Beta distributions

Query selection At each step of elicitation process, we can obtain more preference information make or recommend a terminal decision

Bayesian approach Myopic EVOI MEU(p) ... q1 q2 r1,1 r1,2 r2,1 r2,2 ... MEU(p1,1) MEU(p1,2) MEU(p2,1) MEU(p2,2)

Expected value of information MEU(p) q1 ... q2 r1,1 r1,2 r2,1 r2,2 ... MEU(p1,1) MEU(p1,2) MEU(p2,1) MEU(p2,2) MEU(p) = Ep [u(x*)] Expected posterior utility: EPU(q,p) = Er|q,p [MEU(pr)] Expected value of information of query q: EVOI(q) = EPU(q,p) – MEU(p)

Bayesian approach Myopic EVOI Ask query with highest EVOI - cost [Chajewska et al ’00] Global standard gamble queries (SGQ) “Is u(oi) > l?” Multivariate Gaussian distributions over utilities [Braziunas and Boutilier ’05] Local SGQ over utility factors Mixture of uniforms distributions over utilities

Local elicitation in GAI models [Braziunas and Boutilier ’05] Local elicitation procedure Bayesian uncertainty over local factors Myopic EVOI query selection Local comparison query “Is local value of factor setting xi greater than l”? Binary comparison query Requires yes/no response query point l can be optimized analytically This is the intro slide to how we fill in subutility values (local elicitation) Stress these things (need to express our motivation!): GAI elicitation with full outcome direct queries was already addressed by Gonzales & Perny. In this part, we are still talking about complete elicitation. The particular queries do not matter Here, we will be talking about local elicitation. Later, we will address the issue of incomplete (partial) elicitation with specific local comparison queries

Experiments Car rental domain: 378 parameters [Boutilier et al. ’03] 26 variables, 2-9 values each, 13 factors 2 strategies Semi-random query Query factor and local configuration chosen at random Query point set to the mean of local value function EVOI query Search through factors and local configurations Query point optimized analytically Explain that random query isn’t random!

Experiments Percentage utility error (w.r.t. true max utility) First thing to say: flat lines (marked with x ) are random strategy Downward curved lines are EVOI strategy 3 types of priors random mixture of 5 uniforms uniform mixture of 10 uniforms approximating Gaussian Shows how quickly decision quality improves (utility error decreases) with the number of queries No. of queries

Bayesian Elicitation: Future Work GAI structure elicitation and verification Sequential EVOI Noisy responses

Overview Single User Elicitation Foundations of Local queries Bayesian Elicitation Regret-based Elicitation why MiniMax Regret (MMR) ? Decision making with MMR Elicitation with MMR Multi-agent Elicitation (Mechanism Design)

Minimax Regret: Utility Uncertainty Regret of x w.r.t. u: Max regret of x w.r.t. F: Decision with minimax regret w.r.t. F:

Why Minimax Regret?* Appealing decision criterion for strict uncertainty contrast maximin, etc. not often used for utility uncertainty [BBB01,HS010] x x’ x’ x’ x’ Better x x’ x x x x x’ u1 u2 u3 u4 u5 u6

Why Minimax Regret? Minimizes regret in presence of adversary provides bound worst-case loss robustness in the face of utility function uncertainty In contrast to Bayesian methods: useful when priors not readily available can be more tractable; see [CKP00/02, Bou02] effective elicitation even if priors available [WB03]

Overview Single User Elicitation Foundations of Local queries Bayesian Elicitation Regret-based Elicitation why MiniMax Regret (MMR) ? Decision making with MMR Elicitation with MMR Multi-agent Elicitation (Mechanism Design

Computing Max Regret Max regret MR(x,F) computed as an IP number of vars linear in GAI model size number of (precomputed) constants (i.e., local regret terms) quadratic in GAI model size r( x[k] , x’[k] ) = u(x’[k] ) – u(x[k] )

Minimax Regret in Graphical Models We convert minimax to min (standard trick) obtain a MIP with one constraint per feasible config linearly many vars (in utility model size) Key question: can we avoid enumerating all x’ ?

Constraint Generation Very few constraints will be active in solution Iterative approach: solve relaxed IP (using a subset of constraints) Solve for maximally violated constraint if any add it and repeat; else terminate

Constraint Generation Performance Key properties: aim: graphical structure permits practical solution convergence (usually very fast, few constraints) very nice anytime properties considerable scope for approximation produces solution x* as well as witness xw

Overview Single User Elicitation Foundations of Local queries Bayesian Elicitation Regret-based Elicitation why MiniMax Regret (MMR) ? Decision making with MMR Elicitation with MMR Multi-agent Elicitation (Mechanism Design)

Regret-based Elicitation [Boutilier, Patrascu, Poupart, Schuurmans IJCAI05; AIJ 06] Minimax optimal solution may not be satisfactory Improve quality by asking queries new bounds on utility model parameters Which queries to ask? what will reduce regret most quickly? myopically? sequentially? Closed form solution seems infeasible to date we’ve looked only at heuristic elicitation

Elicitation Strategies I Halve Largest Gap (HLG) ask if parameter with largest gap > midpoint MMR(U) ≤ maxgap(U), hence nlog(maxgap(U)/e) queries needed to reduce regret to e bound is tight like polyhedral-based conjoint analysis [THS03] f1(a,b) f1(a,b) f1(a,b) f1(a,b) f2(b,c) f2(b,c) f2(b,c) f2(b,c)

Elicitation Strategies II Current Solution (CS) only ask about parameters of optimal solution x* or regret-maximizing witness xw intuition: focus on parameters that contribute to regret reducing u.b. on xw or increasing l.b. on x* helps use early stopping to get regret bounds (CS-5sec) f1(a,b) f1(a,b) f1(a,b) f1(a,b) f2(b,c) f2(b,c) f2(b,c) f2(b,c)

Elicitation Strategies III Optimistic-pessimistic (OP) query largest-gap parameter in one of: optimistic solution xo pessimistic solution xp Computation: CS needs minimax optimization OP needs standard optimization HLG needs no optimization Termination: CS easy Others ?

Results (Small Random) 10vars; < 5 vals 10 factors, at most 3 vars Avg 45 trials

Results (Car Rental, Unif) 26 vars; 61 billion configs 36 factors, at most 5 vars; 150 parameters Avg 45 trials

Results (Real Estate, Unif) 20 vars; 47 million configs 29 factors, at most 5 vars; 100 parameters Avg 45 trials

Results (Large Rand, Unif) 25 vars; < 5 vals 20 factors, at most 3 vars A 45 trials

Summary of Results CS works best on test problems time bounds (CS-5): little impact on query quality always know max regret (or bound) on solution time bound adjustable (use bounds, not time) OP competitive on most problems computationally faster (e.g., 0.1s vs 14s on RealEst) no regret computed so termination decisions harder HLG much less promising

Interpretation HLG: But: provable regret reduced very quickly true regret faster (often to optimality) OP and CS restricted to feasible decisions CS focuses on relevant parameters

Conclusion – Single User Local parameter elicitation Theoretically sound Computationally practical Easier to answer Bayesian EVOI / Regret-based elicitation Good guides for elicitation Integrated in computationally tractable algorithms Future Work: Sequential reasoning

Questions? References: D. Braziunas and C. Boutilier: “Local Utility Elicitation in GAI Models”, UAI 2005 C. Boutilier, R. Patrascu, P. Poupart, D. Shuurmans: “Constraint-based Optimization and Utility Elicitation using the Minimax Decision Criterion”, Artificial Intelligence, 2006 (CP-2003 + IJCAI 2005)

Preference Elicitation in Single and Multiple User Settings Part 2 Darius Braziunas, Craig Boutilier, 2005 (Boutilier, Patrascu, Poupart, Shuurmans, 2003, 2005) Nathanael Hyafil, Craig Boutilier, 2006a, 2006b Department of Computer Science University of Toronto

Overview Single User Elicitation Multi-agent Elicitation Foundations of Local queries Bayesian Elicitation Regret-based Elicitation Multi-agent Elicitation Background: Mechanism Design Partial Revelation Mechanisms One-Shot Elicitation Sequential Mechanisms

Bargaining for a Car Luggage Capacity? Two Door? Cost? Engine Size? Color? Options? $$ $$ $$

Multiagent PE: Mechanism Design Incentive to misrepresent preferences Mechanism design tackles this: Design rules of game to induce behavior that leads to maximization of some objective (e.g., Social Welfare, Revenue, ...) Objective value depends on private information held by self-interested agents  Elicitation + Incentives Applications: Auctions, multi-attribute Negotiation, Procurement problems, Network protocols, Autonomic computing, ...

Basic Social Choice Setup Choice of x from outcomes X Agents 1..n: type ti Ti and valuation vi(x, ti) Type vectors: tT and t-i T-i Goal: optimize social choice function f: T  X e.g., social welfare SW(x,t) =  vi(x, ti) Assume payments and quasi-linear utility: ui(x, i ,ti ) = vi(x, ti ) - i Our focus: SW maximization, quasi-linear utility

Basic Mechanism Design A mechanism m consists of three components: actions Ai allocation function O: A X payment functions pi : A R m induces a Bayesian game m implements social choice function f if in equilibrium  : O((t)) = f(t) for all tT

Incentive Compatibility (Truth-telling) Dominant Strategy IC No matter what: agent i should tell the truth Bayes-Nash IC Assume others tell the truth Assume agent i has Bayesian prior over others’ types Then, in expectation, agent i should tell the truth Ex-Post IC Assume agent i knows the others’ types Then agent i should tell the truth

Properties Mechanism is Efficient: Ex Post Individually Rational: maximizes SW given reported types:  -efficient: within  of optimal SW Ex Post Individually Rational: No agent can lose by participating -IR: can lose at most 

Direct Mechanisms Revelation principle: focus on direct mechanisms where agents directly and (in eq.) truthfully reveal their full types For example, Groves scheme (e.g., VCG): choose efficient allocation and use payment function: implements SWM in dominant strategies incentive compatible, efficient, individually rational

Groves Schemes Strong results: Groves is basically the “only choice” for dominant strategy implementation Roberts (1979): only social choice functions implementable in dominant strategies are affine welfare maximizers (if all valuations possible) Green and Laffont (1977): must use Groves payments to implement affine maximizers Implications for partial revelation

Issues with Classical Mechanism Design Computation Costs e.g., Winner Determination Revelation Costs Communication Computation Cognitive Privacy

Issues with Classical Mechanism Design Full Revelation and “Quality” trade-off revelation costs with Social Welfare Full Revelation and Incentives very dependent need “new” concepts

Overview Single User Elicitation Multi-agent Elicitation Foundations of Local queries Bayesian Elicitation Regret-based Elicitation Multi-agent Elicitation Background: Mechanism Design Partial Revelation Mechanisms One-Shot Elicitation Sequential Mechanisms

Partial Revelation Mechanisms Full revelation unappealing A partial type is any subset i  Ti A one-shot (direct) partial revelation mechanism each agent reports a partial type i  i typically i partitions type space, but not required A truthful strategy: report i s.t. ti  i Goal: minimize revelation, computation, communication by suitable choice of partial types

Implications of Roberts Partial revelation means we can’t generally maximize social welfare must allocate under type uncertainty But if SCF is not an affine maximizer, we can’t expect dominant strategy implementation What are some solutions? relax solution concept to BNE / Ex-Post relax solution concept to approx incentives incremental and “hope for” less than full elicitation relax conditions on Roberts results

Existing Work on PRMs [Conen,Hudson,Sandholm, Parkes, Nisan&Segal, Blumrosen&Nisan] Most Approaches: require enough revelation to determine optimal allocation and VCG payments hence can’t offer savings in general [Nisan&Segal05] Sequential, not one-shot specific settings (1-item, combinatorial auctions) Priority games [Blumrosen&Nisan 02] genuinely partial and approximate efficiency but very restricted valuation space (1-item)

Preference Elicitation in MechDes We move beyond this by allowing approximately optimal allocation specifically, regret-based allocation models Avoid Roberts by relaxing solution concept: Bayes-Nash equilibrium? NO! [HB-06b] Ex-Post IC? NO ! [HB-06b] approximate, ex-post implementation

Partial Revelation MD: Impossibility Results Bayes-Nash Equilibrium Theorem: [HB-06b] Deterministic PRMs are Trivial Randomized PRMs are Pseudo-Trivial Consequences: max expected SW = same as best trivial max expected revenue = same as best trivial  “Useless” Ex-Post Equilibrium Same

Overview Single User Elicitation Multi-agent Elicitation Foundations of Local queries Bayesian Elicitation Regret-based Elicitation Multi-agent Elicitation Background: Mechanism Design Partial Revelation Mechanisms One-Shot Elicitation Sequential Mechanisms

Regret-based PRMs In any PRM, how is allocation to be chosen? x*() is minimax optimal decision for A regret-based PRM: O()=x*() for all   

Regret-based PRMs: Efficiency Efficiency not possible with PRMs (unless MR=0) but bounds are quite obvious Prop: If MR(x*(),)   for all  , then regret-based PRM m is -efficient for truthtelling agents. thus we can tradeoff efficiency for elicitation effort

Regret-based PRMs: Incentives Can generalize Groves payments let fi (i) be an arbitrary type in i Thm: Let m be a regret-based PRM with partial types  and a partial Groves payment scheme. If MR(x*(),)   for all  , then m is -ex post incentive compatible

Regret-based PRMs: Rationality Can generalize Clark payments as well Thm: Let m be a regret-based PRM with partial types  and a partial Clark payment scheme. If MR(x*(),)   for all  , then m is -ex post individually rational. A Clark-style regret-based PRM gives approximate efficiency, approximate IC (ex post) and approximate IR (ex post)

Approximate Incentives and IR Natural to trade off efficiency for elicitation effort Is approximate IC acceptable? computing a good “lie”? Good? Huge computation costs if incentive to deviate from truth is small enough, then formal, approximate IC ensures practical, exact IC Is approximate IR acceptable? Similar argument Thus regret-based PRMs offer scope to tradeoff as long as we can find a good set of partial types

Computation and Design/Elicitation Minimax optimization given partial type vector  same techniques as for single agent varies with setting (experiments: CBO with GAI) Designing the mechanism one-shot PRM: must choose partial types for each i sequential PRM: need elicitation strategy we apply generalization of CS to each task

(One-shot) Partial Type Optimization Designing PRM: must pick partial types we focus on bounds on utility parameters A simple greedy approach Let  be current partial type vectors (initially {T} ) Let  =(1,… i,…n )   be partial type vector with greatest MMR Choose agent i and suitable split of partial type i into ’i and ’’i Replace all  [i ] by pair of vectors: i  ’i ;’’i Repeat until bound  is acceptable

The Mechanism Tree (1,… i,…n ) (’1,… i,…n ) (’’1,… i,…n )

A More Refined Approach Simple model has drawbacks exponential blowup (“naïve” partitioning) split of i useful in reducing regret in one partial type vector , but is applied at all partial type vectors Refinement apply split only at leaves where it is “useful” keeps tree from blowing up, saves computation new splits traded off against “cached” splits once done, use either naïve/variable resolution types for each agent

Naïve vs. Variable Resolution p2 p2 p1 p1 i i

Heuristic for Choosing Splits Adopt variant of current solution strategy Let  be partial type vector with max MMR optimal solution x* regret-maximizing witness xw only split on parameters of utility functions of optimal solution x* or regret-maximizing witness xw intuition: focus on parameters that contribute to regret reducing u.b. on xw or increasing l.b. on x* helps pick agent-parameter pair with largest gap

Preliminary Empirical Results Very preliminary results use only very naïve algorithm single buyer, single seller 16 goods specified by 4 boolean variables valuation/cost given by GAI model two factors, two vars each (buyer/seller factors are different) thus 16 values/costs specified by 8 parameters no constraints on feasible allocations

Preliminary Empirical Results

Overview Single User Elicitation Multi-agent Elicitation Foundations of Local queries Bayesian Elicitation Regret-based Elicitation Multi-agent Elicitation Background: Mechanism Design Partial Revelation Mechanisms One-Shot Elicitation Sequential Mechanisms

Sequential PRMs Optimization of one-shot PRMs unable to exploit conditional “queries” e.g., if seller cost of x greater than your upper bound, needn’t ask you for your valuation of x Sequential PRMs incrementally elicit partial type information apply similar heuristics for designing query policy incentive properties somewhat weaker: opportunity to manipulate payments by altering the query path thus additional criteria can be used to optimize

Sequential PRMs: Definition Set of queries Qi response rRi(qi) interpreted as partial type i (r)  Ti history h: sequence of query-response pairs possibly followed by allocation (terminal) Sequential mechanism m maps: nonterminal histories to queries/allocations terminal histories to set of payment functions pi Revealed partial type i(h): intersect. i (r), r in h m is partial revelation if exists realizable terminal h s.t. i(h) admits more than one type ti

Sequential PRMs: Properties Strategies i(hi ,qi ,ti) selects responses i is truthful if ti  i (i(hi ,qi ,ti)) truthful strategies must be history independent (Determ.) strategy profile  induces history h if h is terminal, then quasi-linear utility realized if history is unbounded, then assume utility = 0 Regret-based PRM allocation defined as in one-shot

Max VCG Payment Scheme Assume terminal history h let  be revealed PTV at h, x*() be allocation Max VCG payment scheme: where VCG payment is:

Incentive Properties Suppose we elicit type info until MMR allocation has max regret   and we use “max VCG” Define: Thm: m is -efficient, -ex post IR and (+(x*()))-ex post IC. weaker results due to possible payment manipulation

Elicitation Approaches Two Phases: Standard max regret based approaches give us bounds on efficiency , no a priori  bounds Regret-based followed by payment elicitation once  small enough, elicit additional payment information until max  is small enough

Elicitation Approaches Direct optimization: global manipulability: u(best lie) - u(truth) ask queries that directly reduce global manipulability can be formulated as regret-style optimization analogous query strategies possible

Test Domains Car Rental Problem: Small Random Problems: 1 client , 2 dealers GAI valuation/costs: 13 factors, size 1-4 Car: 8 attributes, 2-9 values Total 825 parameters Small Random Problems: supplier-selection, 1 buyer, 2 sellers 81 parameters

Results: Car Rental Initial regret: 99% of opt SW Zero-regret: 71/77 queries Avg remaining uncertainty: 92% vs 64% at zero-manipulability Avg nb params queried: 8% relevant parameters reduces revelation improves decision quality

Results: Random Problems

Contributions Theoretical framework for Partial Revelation Mech Design One-shot mechanisms generalize VCG to PRMs (allocation + payments) v. general payments: secondary objectives algorithm to design partial types Sequential mechanisms slightly different model, but similar results algorithm to design query strategy Viewpoint: why approximate incentives are useful Approximate decision  trade off cost vs. quality Formal, approximate IC ensures practical, exact IC Applicable to general Mechanism Design problems Empirically very effective

PRMs: Future Work Further investigate splitting / elicitation heuristics More experimentation Larger problems Combinatorial Auctions Formal model manipulability cost  formal, exact IC Formal model revelation costs  explicit revelation vs efficiency trade-off Sequentially optimal elicitation

Questions ? References: Nathanael Hyafil and Craig Boutilier “Regret-based Incremental Partial Revelation Mechanisms”, AAAI 2006 “One-shot Partial Revelation Mechanisms”, Working Paper, 2006

Extra Slides - Part 1

Fishburn [1967]: Default Outcomes Define default outcome: For any x, let x[I] be restriction of x to vars I, with remaining replaced by default values: Utility of x can be written [F67]: sum of utilities of certain related “key” outcomes

Key Outcome Decomposition Example: GAI over I={ABC}, J={BCD}, K={DE} u(x) = u(x[I]) + u(x[J]) + u(x[K]) - u(x[IJ]) - u(x[IK]) - u(x[JK]) + u(x[IJK]) u(abcde) = u(x[abc]) + u(x[bcd]) + u(x[de]) - u(x[bc]) - u(x[]) - u(x[d]) + u(x[]) u(abcde) = u(abcd0e0) + u(a0bcde0) + u(a0b0c0de) - u(a0bcd0e0) - u(a0b0c0de0)

Canonical Decompostion [F67] This leads to canonical decompostion of u: u1(x1, x2) u2(x2, x3) e.g., I={ABC}, J={BCD}, K={DE} u(abcde) = u(abcd0e0) + u(a0bcde0) - u(a0bcd0e0) + u(a0b0c0de) - u(a0b0c0de0)

Local Queries Thus, if for some y (where Y =X \ Xi \ C(Xi) ) then for all y’ hence we can legitimately ask local queries:

Implications for Minimax Regret Complicates MMR utility of outcome depends linearly on GAI parameters but GAI parameters depend on bounds induced by two types of queries: quadratic constraints Local pairwise regret notion can be modified To compute rx[k]x’[k] set values: vx’[k] to u.b. and vx[k] to l.b. If vx’[k]↑ > vx[k]↓: max u(xT[k]) and min u(x[k]) otherwise do the opposite

Bayesian Utility Function Uncertainty User’s actual utility u unknown Assume density P over U = [0,1]n Given belief state P, EU of decision x is: Decision making is easy, but elicitation harder? must assess expected value of information in query

Extra Slides - Part 2