Optimization with Demand Oracles

TL;DR

This paper develops demand oracle-based algorithms for combinatorial procurement auctions, achieving improved approximation ratios over classical greedy methods, including near-optimal bounds for subadditive valuations.

Contribution

It introduces demand oracle algorithms that surpass the classic e/(e-1) approximation barrier for procurement problems, including non-monotone and subadditive valuations.

Findings

Achieves approximation ratio of 9/8+ε for general problems

Attains ratio of 9/8 for cardinality constraints

Proves near-optimality requiring exponential demand queries for ratios below 2

Abstract

We study \emph{combinatorial procurement auctions}, where a buyer with a valuation function $v$ and budget $B$ wishes to buy a set of items. Each item $i$ has a cost $c_i$ and the buyer is interested in a set $S$ that maximizes $v(S)$ subject to $\Sigma_{i\in S}c_i\leq B$. Special cases of combinatorial procurement auctions are classical problems from submodular optimization. In particular, when the costs are all equal (\emph{cardinality constraint}), a classic result by Nemhauser et al shows that the greedy algorithm provides an $\frac e {e-1}$ approximation. Motivated by many papers that utilize demand queries to elicit the preferences of agents in economic settings, we develop algorithms that guarantee improved approximation ratios in the presence of demand oracles. We are able to break the $\frac e {e-1}$ barrier: we present algorithms that use only polynomially many demand queries and have approximation ratios of $\frac 9 8+\epsilon$ for the general problem and $\frac 9 8$ for maximization subject to a cardinality constraint. We also consider the more general class of subadditive valuations. We present algorithms that obtain an approximation ratio of $2+\epsilon$ for the general problem and 2 for maximization subject to a cardinality constraint. We guarantee these approximation ratios even when the valuations are non-monotone. We show that these ratios are essentially optimal, in the sense that for any constant $\epsilon>0$, obtaining an approximation ratio of $2-\epsilon$ requires exponentially many demand queries.