Paper uses RL to solve constrained combinatorial optimization problems.
problem Constrained combinatorial optimization problems.
method Extending NCO theory to CMDPs, using RL with penalty signals.
result Proposes a superior method for solving constrained problems.
Algorithm improves movie recommendation efficiency with fairness constraints.
problem Improving movie recommendation efficiency with fairness constraints in combinatorial semi-bandits.
method Adopted Thompson Sampling with beta priors and Bernoulli likelihoods to handle fairness constraints.
result Time-averaged regret upper bounded by $\frac{N}{2η} + O\left(\frac{\sqrt{mNT\ln T}}{T}
ight)$, with fairness constraints satisfied.
Master-slave architecture tackles combinatorial multi-armed bandits with diversity constraints.
problem Solving top-K combinatorial multi-armed bandits with non-linear feedback and diversity constraints. method Master-slave architecture with six slave models, teacher learning, and policy co-training.
result Significantly outperforms existing algorithms in synthetic and real datasets.
Unified framework for combinatorial and rounding algorithms in experimental design.
problem Designing and analyzing combinatorial and rounding algorithms for experimental design problems.
method Local search framework for combinatorial algorithms and regret minimization framework for rounding algorithms.
result Unified approach to match and improve all known results in D/A/E-design and obtain new results in unknown settings.
Extends graph factor system to quasi-median graphs.
problem Constraint relaxation for combinatorial HHS machinery.
method Relaxing domain constraints on combinatorial HHS machinery and extending factor system to quasi-median graphs.
result Factor system applied to quasi-median graphs.
A new algorithm balances global reward and group constraints in federated multi-armed bandits.
problem Maximizing global reward while protecting client privacy in federated learning.
method Combinatorial contextual bandit with group constraints, using a two-output Gaussian process.
result TCGP-UCB incurs low regret, balancing super arm reward and group reward constraints.
Improved regret bounds for contextual combinatorial semi-bandits with linear payoffs.
problem Maximizing rewards in decision-making problems with feature vectors and constraints.
method Proposed C^2UCB algorithm and modified reward estimates for general constraints.
result Optimal regret bounds of C^2UCB algorithm and modified algorithm for various constraints.
This work improves privacy in federated combinatorial bandits by balancing regret and privacy.
problem Privacy-preserving learning in competitive online learning settings with quality constraints.
method Proposes P-FCB algorithm for federated combinatorial bandits, balancing regret and privacy.
result Improves regret while maintaining quality constraints and privacy guarantees.
New DAG constraints improve differentiable DAG learning.
problem Recovering DAG structures from observational data is hard due to combinatorial optimization.
method Developed analytic functions to formulate DAG constraints, closed under differentiation, summation, and multiplication.
result Analytic DAG constraints outperform previous methods in various settings.
The paper tackles fair correlation clustering with new algorithms and analysis.
problem Fair variants of correlation clustering under various constraints.
method Introducing a novel combinatorial optimization problem for fairlet decomposition.
result Approximation algorithms for fair correlation clustering under multiple fairness constraints.
We study online prediction where regret of the algorithm is measured against a benchmark defined via evolving constraints. This framework captures online prediction on graphs, as well as other prediction problems with combinatorial structure. A key aspect here is that finding the optimal benchmark predictor (even in hi…
Identifying important components or factors in large amounts of noisy data is a key problem in machine learning and data mining. Motivated by a pattern decomposition problem in materials discovery, aimed at discovering new materials for renewable energy, e.g. for fuel and solar cells, we introduce CombiFD, a framework …
New framework for resilient bi-criteria optimization under noisy feedback.
problem Bi-criteria combinatorial optimization with noisy function evaluations.
method Introducing (α,β,δ,extttN)-resilience and developing a black-box framework. result Achieves sublinear regret and constraint violation for bi-criteria bandit problems.
Unified framework for robust submodular optimization with various constraints.
problem Robust optimization in machine learning applications.
method Unified framework for minimization and maximization under combinatorial constraints.
result Scalable approximation algorithms for various submodular optimization problems.
A stochastic combinatorial semi-bandit is an online learning problem where at each step a learning agent chooses a subset of ground items subject to combinatorial constraints, and then observes stochastic weights of these items and receives their sum as a payoff. In this paper, we consider efficient learning in large-s…
Paper tackles safe combinatorial semi-bandits with risk constraints.
problem Safe combinatorial semi-bandits with risk constraints.
method Formulated probably anytime-safe constraint, designed PASCombUCB algorithm.
result PASCombUCB is almost asymptotically optimal in minimizing regret.
Branched covers between Riemann surfaces are associated with certain combinatorial data, and Hurwitz existence problem asks whether given data satisfying those combinatorial constraints can be realized by some branched cover. We connect recent development in spherical conic metrics to this old problem, and give a new m…
This paper tackles combinatorial optimization under uncertainty with limited feedback.
problem Tackling combinatorial optimization problems with uncertain or unknown parameters.
method Review of techniques for combinatorial pure exploration with limited bandit feedback.
result Introduction of methods for combinatorial optimization under uncertainty with limited observation.
New guarantees for adaptive combinatorial maximization with various objectives.
problem Maximizing under cardinality constraints and minimum cost coverage in adaptive settings.
method Bayesian approach with comprehensive approximation guarantees for various utility functions.
result Maximal gain ratio is a new parameter that provides stronger approximation guarantees than greedy policies.
Develops a new method for learning non-parametric DAGs using RKHS.
problem Challenges of learning non-parametric causal models with large combinatorial search space.
method Uses reproducing kernel Hilbert spaces (RKHS) and sparsity-inducing regularization terms based on partial derivatives to enforce acyclicity.
result Shows improved performance through simulations and data analyses.
This paper tackles robust submodular minimization for image segmentation and correspondence.
problem Robust submodular minimization for image segmentation and correspondence.
method Constrained submodular minimization with scalable approximation algorithms for various combinatorial constraints.
result First work on robust submodular minimization under broad combinatorial constraints.
A framework for generating 3D shapes by sequentially assembling primitives.
problem Combinatorial complexity in generating 3D shapes.
method Bayesian optimization for efficient exploration and exploitation of feasible combinations.
result Successfully generates realistic combinatorial 3D shapes.
This work proposes an unsupervised neural network framework for solving combinatorial optimization problems on graphs.
problem Challenges in neural networks solving combinatorial optimization problems without labeled instances.
method Inspired by Erdos' probabilistic method, a neural network parametrizes a probability distribution over sets, optimizing it to find low-cost integral solutions.
result The method provides valid solutions to the maximum clique problem and local graph clustering, achieving competitive results.
New algorithms ensure fair selection in combinatorial semi-bandit with unrestricted delays.
problem Fair selection in stochastic combinatorial semi-bandit with delayed feedback.
method Introduced merit-based fairness constraints and new bandit algorithms for reward and fairness.
result Achieved sublinear expected reward and fairness regrets with dependence on delay distribution quantiles.
Adaptive allocation with constraints using Thompson sampling.
problem Choosing allocations repeatedly with unknown returns and constraints.
method Thompson sampling approach with finite-sample regret bound.
result Prior-independent bound on expected regret for exponential allocations.
In many practical problems, a learning agent may want to learn the best action in hindsight without ever taking a bad action, which is significantly worse than the default production action. In general, this is impossible because the agent has to explore unknown actions, some of which can be bad, to learn better action…
The paper tackles prescribing discrete Gaussian curvature on polyhedral surfaces.
problem Prescribing discrete Gaussian curvature on polyhedral surfaces.
method Discrete conformal theory and variational principles with constraints.
result Proves Kazdan-Warner type theorems for polyhedral surfaces.
Estimating the structure of directed acyclic graphs (DAGs, also known as Bayesian networks) is a challenging problem since the search space of DAGs is combinatorial and scales superexponentially with the number of nodes. Existing approaches rely on various local heuristics for enforcing the acyclicity constraint. In th…
CPRA efficiently finds diverse solutions in CO problems using UL and parallelization.
problem Finding optimal solutions often requires diverse outcomes in real-world applications.
method CPRA, an UL-based framework, discovers shared representations to generate diverse solutions.
result CPRA outperforms existing UL-based solvers in generating diverse solutions.
GFlowNets improve combinatorial optimization by efficiently sampling from solution spaces.
problem NP-hard combinatorial optimization problems with structured constraints.
method Design Markov decision processes and train conditional GFlowNets to sample solutions.
result GFlowNet policies find high-quality solutions efficiently on various CO tasks.
New method learns DAGs from data without acyclicity constraint.
problem Learning DAGs from data without imposing acyclicity.
method Sparse matrix factorization and ℓ1-penalized optimization. result Empirical success in recovering true graphs and almost-DAG graphs.
Two new methods solve large-scale stochastic convex problems with linear constraints.
problem Solving large-scale stochastic convex optimization problems with many linear constraints.
method Conditional gradient-based methods that process only a subset of constraints at each iteration.
result Rigorous convergence guarantees for the proposed methods.
We describe two nonconventional algorithms for linear regression, called GAME and CLASH. The salient characteristics of these approaches is that they exploit the convex ℓ1-ball and non-convex ℓ0-sparsity constraints jointly in sparse recovery. To establish the theoretical approximation guarantees of GAME an…
In this paper, we review the problem of matrix completion and expose its intimate relations with algebraic geometry, combinatorics and graph theory. We present the first necessary and sufficient combinatorial conditions for matrices of arbitrary rank to be identifiable from a set of matrix entries, yielding theoretical…
NeuroMatch efficiently matches subgraphs in large graphs using neural networks.
problem Determining the presence and location of a query graph in a large target graph.
method NeuroMatch decomposes graphs into subgraphs, embeds them using graph neural networks, and matches them directly in the embedding space.
result NeuroMatch is 100x faster and 18% more accurate than existing methods.
Study optimal policies under budget and coverage constraints.
problem Optimal policy learning with budget and coverage constraints.
method Combination of knapsack structure, affine threshold rule, linear programming relaxation, Greedy-Lagrangian (GLC), and rank-and-cut (RC) algorithms.
result GLC closely approximates the optimal solution and achieves near-optimal performance in finite samples; RC is approximately optimal under certain conditions.
A new deep learning framework for topological data.
problem Developing models for data on complex topological domains.
method Introducing combinatorial complexes and developing attention-based CCNNs.
result CCNNs outperform existing models in tasks involving mesh shape analysis and graph learning.
Paper tackles stochastic k-submodular bandits with full feedback, achieving sublinear regret.
problem Online optimization of k-submodular functions with full-bandit feedback. method Proposes online algorithms for various k-submodular stochastic combinatorial multi-armed bandit problems. result Achieves sublinear α-regret bounds for multiple k-submodular stochastic combinatorial multi-armed bandit problems. Graph learning from data represents a canonical problem that has received substantial attention in the literature. However, insufficient work has been done in incorporating prior structural knowledge onto the learning of underlying graphical models from data. Learning a graph with a specific structure is essential for …
There has been an increased interest in discovering heuristics for combinatorial problems on graphs through machine learning. While existing techniques have primarily focused on obtaining high-quality solutions, scalability to billion-sized graphs has not been adequately addressed. In addition, the impact of budget-con…
New framework tackles submodular welfare with multi-agent combinatorial bandits.
problem Maximizing total welfare among agents with shared constraints and submodular utilities under bandit feedback.
method Proposes an explore-then-commit strategy with randomized assignments for multi-agent combinatorial bandits.
result Achieves ildeO(T2/3) regret, first for partition-based submodular welfare problem under bandit feedback. New algorithm reduces combinatorial semi-bandit regret efficiently.
problem Optimizing rewards from uncorrelated items in combinatorial semi-bandits.
method Developed an approximate version of ESCB with polynomial complexity.
result Achieved statistically efficient and polynomial time algorithm for combinatorial semi-bandits.
Graph Pointer Networks and hierarchical reinforcement learning solve combinatorial optimization problems like TSP.
problem Traveling Salesman Problem (TSP) with constraints.
method Graph Pointer Networks (GPNs) and hierarchical reinforcement learning.
result GPNs and hierarchical RL find optimal solutions for TSP and TSP with time windows.
A stochastic combinatorial semi-bandit is an online learning problem where at each step a learning agent chooses a subset of ground items subject to constraints, and then observes stochastic weights of these items and receives their sum as a payoff. In this paper, we close the problem of computationally and sample effi…
Neural framework learns one solution from multiple for combinatorial problems.
problem Finding any one of many possible solutions for combinatorial problems.
method Adapts existing prediction networks to handle solution multiplicity using a selection module trained via RL.
result Framework significantly improves accuracy in solving combinatorial problems.
In urban environments, supply resources have to be constantly matched to the "right" locations (where customer demand is present) so as to improve quality of life. For instance, ambulances have to be matched to base stations regularly so as to reduce response time for emergency incidents in EMS (Emergency Management Sy…
Differentially private algorithms for submodular maximization under various constraints.
problem Maximizing decomposable submodular functions under constraints while preserving privacy.
method Designing differentially private algorithms for both monotone and non-monotone decomposable submodular maximization under general matroid constraints.
result Improved utility guarantees and competitive performance compared to non-private algorithms.
New algorithm reduces super-arm selection complexity exponentially.
problem Combinatorial multi-armed bandits with cardinality constraint.
method Combination of group-testing and quantized Thompson sampling.
result Achieves same regret order as state-of-the-art algorithms with perfect oracle, but with reduced complexity.