--- title: DR-Submodular Maximization url: https://www.emergentmind.com/topics/dr-submodular-maximization type: topic --- # DR-Submodular Maximization A diminishing-returns (DR) submodular function generalizes classical submodularity from set functions to continuous, integer-lattice, and even lattice-theoretic domains. DR-submodular maximization is the task of optimizing such functions—often non-monotone—subject to combinatorial, convex, lattice, or algebraic constraints. This problem arises in a wide range of applications in machine learning, stochastic inference, resource allocation, and combinatorial optimization, due to the diminishing-returns structure of influence models, entropy relaxations, and probabilistic graphical models. ## 1. Foundations: Definitions and Mathematical Structure A function $F:[0,1]^n \rightarrow \mathbb{R}_+$ (or more generally, defined on a product of intervals or integers) is **DR-submodular** if it exhibits a form of diminishing returns on each coordinate. Formally, for any $x\leq y$ (coordinatewise) and any $i\in[n]$, $\delta\ge 0$, \[ F(x+\delta e_i) - F(x) \ge F(y+\delta e_i) - F(y), \] provided the increments remain in the domain [2203.14740][1805.09480]. If $F$ is differentiable, this is equivalent to the partial derivatives being coordinatewise non-increasing: \[ x \ge y \implies \nabla F(x) \le \nabla F(y), \] and, if $F$ is twice differentiable, to all mixed second partials being nonpositive: \[ \frac{\partial^2 F(x)}{\partial x_i \partial x_j} \le 0 ~~~ \forall i, j. \] This generalizes the diminishing-returns property from set functions to continuous domains [2006.13474]. DR-submodular functions are necessarily (weakly) submodular in the lattice sense, but the converse does not hold unless an additional coordinatewise concavity condition holds [1805.09480]. The notion applies to integer lattices as well, with the submodularity and DR properties defined analogously; this is crucial for problems where variables count repetitions or allocations [2212.06646][1612.00960]. ## 2. Algorithms and Complexity for DR-Submodular Maximization ### 2.1. Monotone DR-Submodular Maximization For the monotone maximization over a convex or down-closed set, several algorithmic paradigms are provably optimal. - **Frank-Wolfe type algorithms** give a $(1 - 1/e)$-approximation in polynomial time under down-closed convex constraints [1606.05615][2006.13474][2305.16671]. At each iteration, one solves a linear maximization over the constraint set, making them projection-free. - **Projected Gradient Ascent** and **derivative-free greedy methods** also achieve $(1-1/e) - \varepsilon$ approximations with $O(1/\varepsilon)$ or $O(1/\varepsilon^3)$ complexity, depending on access to gradients or value oracles [1810.06833][2305.16671]. - For *strongly* DR-submodular functions (i.e., functions concave along nonnegative directions with a quadratic modulus), accelerated convergence and improved ratios $(1-c_f/e)$—where $c_f$ is the curvature—can be achieved [2111.07990]. When the convex set is not down-closed or when constraints are more general, the best achievable polynomial-time ratio drops to $1/2$ for monotone objectives [2305.16671]. ### 2.2. Non-Monotone DR-Submodular Maximization Non-monotone DR-submodular maximization is fundamentally harder; approximation ratios are strictly lower and depend sharply on the feasible set. - For general *convex* (not necessarily down-closed) constraints, a $0.25$-approximation in sub-exponential time is achievable using a Frank–Wolfe style method with a non-constant step size and careful sequence analysis [2203.14740]. Prior sub-exponential time results achieved $1/(3\sqrt3) \approx 0.192$ [2203.14740][1905.09595]. - For **down-closed convex sets**, polynomial-time algorithms achieve $1/e$ approximation [1711.02515][2006.13474][1905.09595], paralleling the multilinear extension paradigm in set-submodular optimization. - If maximizing over the unit box $[0,1]^n$, optimal polynomial-time procedures achieve $1/2$ [1805.09480], with bi-greedy, binary search, or double greedy schemes exploiting coordinatewise concavity. - On the integer lattice (box constraints), double-greedy and accelerated double-greedy (e.g., binary-search) algorithms give $1/2$-approximation in $O(n\log B)$ time [1612.00960][2212.06646]. The inapproximability threshold is $1/2$ for box constraints and $0.478$ for general down-closed polytopes under standard complexity assumptions [2311.01129][2006.13474]. ## 3. Extensions: Lattices, Subspace Selection, and Beyond DR-submodularity admits generalizations to algebraic lattices, enabling unified analysis for subspace selection, PCA, and dictionary learning. In this framework: - **Directional DR-submodularity** on lattices captures diminishing returns with respect to lattice “atoms” and enables tight greedy and double-greedy approximations for subspace constraints [1805.07455]. - PCA and generalized PCA objectives are monotone bidirectional DR-submodular, explaining the optimality of greedy eigenvector selection. - Sparse dictionary selection is downward DR-submodular with an additive coherence gap. Greedy, density-based, and double-greedy algorithms retain provable approximation guarantees under lattice versions of height or knapsack constraints. ## 4. Applications in Machine Learning and Optimization DR-submodular maximization models core mechanisms in several domains: - **Influence maximization**: Assigning continuous resource levels to nodes in a social or communication network often produces DR-submodular objectives via multilinear or more complex extensions [2006.13474]. - **MAP inference in determinantal point processes**: The softmax log-determinant extension is DR-submodular [1805.09480][2006.13474]. - **Mean-field variational inference** for probabilistic log-submodular models: The evidence lower bound (ELBO) is DR-submodular in the mean parameters; DR-DoubleGreedy achieves a $1/2$ approximation to mean-field inference [1805.07482]. - **Submodular quadratic programming**: Quadratic forms $f(x) = x^T H x + h^T x$ with off-diagonal $H_{ij}\le 0$ are DR-submodular; maximization over convex polytopes falls into the framework [1805.09480][2006.13474]. - **Budget allocation, resource scheduling, energy management** and other applications where marginal utility decreases with increased allocation across multiple units. ## 5. Hardness, Lower Bounds, and the State of the Art The landscape of achievable approximation ratios is sharply determined by the convexity and monotonicity structure: | Setting | Approx. Ratio (Poly Time) | Lower Bound / Inapproximability | |-----------------------------------|---------------------------|-----------------------------------| | Monotone, down-closed convex | $1-1/e$ | NP-hard for $>1-1/e$ | | Monotone, general convex | $1/2$ | NP-hard for $>1/2$ | | Non-monotone, down-closed convex | $1/e$ | NP-hard for $>1/e$ | | Non-monotone, box ([0,1]^n) | $1/2$ | NP-hard for $>1/2$ | | General convex (non-mono) | 0.25 (sub-exp), $0.192$ (poly) | Hard for $>0.478$ | Recent breakthroughs have leveraged improved damage bounds on multilinear extensions, yielding a $0.401$-approximation for general down-closed polytopes, which closes part of the gap to the $0.478$ inapproximability barrier [2311.01129]. ## 6. Online, Decentralized, and Oracle-Efficient Extensions - **Online non-monotone DR-submodular maximization** admits regret-minimizing algorithms with the same constants as offline settings but with sublinear regret, e.g., $1/e$ over down-closed domains, $1/2$ over $[0,1]^n$, and $(1-1/\sqrt{3})/(3)$ for general convex sets [1909.11426][1905.09595]. - **Bandit and stochastic value-oracle settings**: Recent unified Frank–Wolfe frameworks provide first regret guarantees under stochastic and bandit-feedback scenarios [2305.16671]. - **Derivative-free and robust optimization**: For monotone continuous DR-submodular objectives, derivative-free greedy methods are robust to noise, retaining $(1-e^{-\beta})$-approximation [1810.06833]. - **Decentralized optimization**: Communication-efficient decentralized online DR-submodular maximization achieves $(1-1/e)$-regret $O(\sqrt{T})$ with only one gradient query and message per round, scaling to large networks [2208.08681]. ## 7. Open Problems and Research Directions - Tightening the gap between inapproximability and algorithmic lower bounds, especially for the general non-monotone case. - Extending lattice submodularity to encompass constraints beyond cardinality/height, e.g., general matroid-like structures [1805.07455][1907.04279]. - Further reducing oracle complexity or per-iteration cost, particularly in high-dimensional, stochastic, or adversarial environments [2305.16671][2203.14740]. - Developing more refined structural bounds (e.g., history-dependent damage bounds) to push constants for constrained maximization [2311.01129]. - Characterizing the relations and transformations between continuous DR-submodular maximization and set-function or integer-lattice optimization, particularly for relaxations, rounding, and sampling [2006.13474][2212.06646]. --- **References** - [2203.14740] An improved approximation algorithm for maximizing a DR-submodular function over a convex set - [1805.09480] Optimal Algorithms for Continuous Non-monotone Submodular and DR-Submodular Maximization - [2311.01129] Constrained Submodular Maximization via New Bounds for DR-Submodular Functions - [2212.06646] Profit Maximization in Social Networks and Non-monotone DR-submodular Maximization - [1805.07482] Optimal DR-Submodular Maximization and Applications to Provable Mean Field Inference - [2006.13474] Continuous Submodular Function Maximization - [1711.02515] Continuous DR-submodular Maximization: Structure and Algorithms - [2111.07990] Fast First-Order Methods for Monotone Strongly DR-Submodular Maximization - [1606.05615] Guaranteed Non-convex Optimization: Submodular Maximization over Continuous Domains - [1805.07455] Subspace Selection via DR-Submodular Maximization on Lattices - [1905.09595] Non-monotone DR-submodular Maximization: Approximation and Regret Guarantees - [2305.16671] A Unified Approach for Maximizing Continuous DR-submodular Functions - [1810.06833] Maximizing Monotone DR-submodular Continuous Functions by Derivative-free Optimization - [2208.08681] Communication-Efficient Decentralized Online Continuous DR-Submodular Maximization - [1909.11426] Online Non-Monotone DR-submodular Maximization - [1612.00960] Non-monotone DR-Submodular Function Maximization - [2111.10175] Randomized Algorithms for Monotone Submodular Function Maximization on the Integer Lattice - [1907.04279] Multiple Knapsack-Constrained Monotone DR-Submodular Maximization on Distributive Lattice --- Continuous Greedy Algorithm on Median Complex --- Source: https://www.emergentmind.com/topics/dr-submodular-maximization