Study counterfactuals in combinatorial choice using a representative agent model.
problem Analyzing decision-making from aggregated binary polytope data.
method Nonparametric approach based on a representative agent model, solving polynomial and mixed-integer convex programs.
result Developed a method for counterfactual prediction that works even under model misspecification.
We determine the topology of the moduli space of periodic tilings of the plane by parallelograms. To each such tiling, we associate combinatorial data via the zone curves of the tiling. We show that all tilings with the same combinatorial data form an open subset in a suitable Euclidean space that is homotopy equivalen…
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…
Develops deep learning models for choice modeling.
problem Computational intractability and sample inefficiency in existing choice model learning methods.
method Deep learning-based choice models in two settings: feature-free and feature-based.
result Demonstrates improved recovery of existing choice models and reduced sample complexity.
Automates supervised learning pipeline design with matrix and tensor factorization.
problem Designing effective supervised learning pipelines with many choices.
method Uses matrix and tensor factorization to model pipeline search space and develops greedy experiment design protocols.
result Demonstrates the effectiveness of the approach on real-world classification problems.
New research shows testing IIA in discrete choice is nearly impossible with current sample sizes.
problem Testing the Independence of Irrelevant Alternatives (IIA) in discrete choice models is challenging.
method Combinatorial analysis of Eulerian orientations of cycle decompositions of a bipartite graph.
result Any general test for IIA with low worst-case error requires an exponential number of samples in the number of alternatives.
We consider combinatorial online learning with subset choices when only relative feedback information from subsets is available, instead of bandit or semi-bandit feedback which is absolute. Specifically, we study two regret minimisation problems over subsets of a finite ground set [n], with subset-wise relative prefe…
Math verifies Aganagic's proposal for Khovanov homology.
problem Recovering Khovanov homology from braid group action on Fukaya-Seidel categories.
method Direct calculation of containment between combinatorially defined braid group actions.
result Mathematical verification of Aganagic's proposal for Khovanov homology.
BPNNs learn to solve combinatorial problems faster and more accurately.
problem Generalizing belief propagation for efficient problem solving.
method BPNNs are parameterized operators that operate on factor graphs, generalizing BP. BPNN-D is a learned iterative operator that provably maintains BP's properties.
result BPNN-D converges 1.7x faster on Ising models and provides tighter bounds.
The problem of retrosynthetic planning can be framed as one player game, in which the chemist (or a computer program) works backwards from a molecular target to simpler starting materials though a series of choices regarding which reactions to perform. This game is challenging as the combinatorial space of possible cho…
DMNL bandits optimize assortment choices balancing relevance and diversity.
problem Balancing relevance-driven choice with within-assortment diversity.
method Augments MNL choice probabilities with a submodular diversity function, proposing a white-box UCB-based algorithm.
result Achieves at least a (1−e+11)-approximate regret bound of $ ilde{O}\left(d \sqrt{T/K}
ight)$. Advances combinatorial complexes for better modeling of hierarchical and set-type relations.
problem Lack of effective modeling for complex hierarchical and set-type relations in high-dimensional data.
method Introduces combinatorial complexes as a bridge between cell complexes and hypergraphs, emphasizing their different types of relations.
result Combining set-type and hierarchical relations in a single model can be advantageous in learning tasks.
New combinatorial framework for geometric realizations of subword complexes.
problem Proving or disproving geometric realizations of subword complexes of Coxeter groups.
method Algebraic combinatorics and discrete geometry framework, parameter matrices.
result Existence of parameter matrices equivalent to realizability of subword complexes as chirotopes.
Subjective expected utility theory assumes that decision-makers possess unlimited computational resources to reason about their choices; however, virtually all decisions in everyday life are made under resource constraints - i.e. decision-makers are bounded in their rationality. Here we experimentally tested the predic…
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.
We learn sensor trees from training data to minimize sensor acquisition costs during test time. Our system adaptively selects sensors at each stage if necessary to make a confident classification. We pose the problem as empirical risk minimization over the choice of trees and node decision rules. We decompose the probl…
SBBO optimizes complex spaces using sampling-based models.
problem Optimizing complex spaces with discrete variables.
method Simulation Based Bayesian Optimization (SBBO) using sampling-based surrogate models.
result Empirical effectiveness of SBBO in combinatorial optimization.
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.
Motivated by the observation that overexposure to unwanted marketing activities leads to customer dissatisfaction, we consider a setting where a platform offers a sequence of messages to its users and is penalized when users abandon the platform due to marketing fatigue. We propose a novel sequential choice model to ca…
A taut ideal triangulation of a 3-manifold is a topological ideal triangulation with extra combinatorial structure: a choice of transverse orientation on each ideal 2-simplex, satisfying two simple conditions. The aim of this paper is to demonstrate that taut ideal triangulations are very common, and that their behavio…
Paper proposes new gradient codes for robust distributed machine learning.
problem Robustness against slow machines (stragglers) in distributed machine learning.
method Constructs gradient codes based on probabilistic and Kronecker product methods.
result Gradient codes exist for a wide range of system parameters with comparable error performance.
New algorithms reduce matching regret by limiting frequent updates.
problem Minimizing regret in stochastic matching with rare optimization updates.
method Batched algorithms that limit matching updates to Θ(log log T) rounds.
result Achieve a regret bound of \(\widetilde{\mathcal{O}}(\sqrt{T})\) with reduced computational cost.
For any cluster algebra whose underlying combinatorial data can be encoded by a bordered surface with marked points, we construct a geometric realization in terms of suitable decorated Teichmueller space of the surface. On the geometric side, this requires opening the surface at each interior marked point into an addit…
There have been increasing challenges to solve combinatorial optimization problems by machine learning. Khalil et al. proposed an end-to-end reinforcement learning framework, S2V-DQN, which automatically learns graph embeddings to construct solutions to a wide range of problems. To improve the generalization ability of…
Defines a new symplectic Khovanov homology for links in fibered 3-manifolds.
problem No specific problem stated, but deals with Khovanov homology for links in fibered 3-manifolds.
method Defines a symplectic Khovanov type homology for a transverse link in a fibered closed 3-manifold with an auxiliary loop.
result Conjectural combinatorial dgas for surface categories, higher-dimensional analogs of strands algebras.
PhyloGFN uses GFlowNets to infer phylogenetic trees from sequence data.
problem Challenging phylogenetic tree inference from sequence data due to high complexity.
method Adopting GFlowNets for parsimony-based and Bayesian phylogenetic inference.
result PhyloGFN produces diverse and high-quality evolutionary hypotheses.
Multi-task learning (MTL) has achieved success over a wide range of problems, where the goal is to improve the performance of a primary task using a set of relevant auxiliary tasks. However, when the usefulness of the auxiliary tasks w.r.t. the primary task is not known a priori, the success of MTL models depends on th…
This paper optimizes ad bids and daily budgets for multiple campaigns in pay-per-click advertising.
problem Optimizing ad bids and daily budgets for multiple campaigns in pay-per-click advertising.
method Formulated as a combinatorial semi-bandit problem, solved using Gaussian Processes and four algorithms.
result Regret upper bounded as O(sqrt{T}), where T is the time horizon.
Novel theory combines combinatorial and topological elements.
problem Understanding combinatorial phenomena at the intersection of topology.
method Synthesizes combinatorial and topological approaches with a new framing concept.
result Framed combinatorial spaces exhibit better behavior than classical spaces.
This paper addresses the general problem of modelling and learning rank data with ties. We propose a probabilistic generative model, that models the process as permutations over partitions. This results in super-exponential combinatorial state space with unknown numbers of partitions and unknown ordering among them. We…
Neural model with parameterized algorithms improves graph CO problem solving.
problem Solving NP-hard graph combinatorial optimization problems efficiently and accurately.
method Combining neural models and parameterized algorithms to identify and handle hard and easy parts of CO instances.
result Framework produces superior solution quality and out-of-distribution generalization.
The paper introduces combinatorial Calabi flows to find hyperbolic metrics on surfaces with boundary.
problem Finding hyperbolic metrics on surfaces with totally geodesic boundaries of given lengths.
method Introducing combinatorial Calabi flows and proving their long time existence and global convergence.
result Proves the long time existence and global convergence of combinatorial Calabi flow on surfaces with boundary.
PASTA optimizes assortment selection using pessimism principle.
problem Optimizing assortment selection with limited data coverage.
method Pessimistic Assortment Optimization (PASTA) based on the principle of pessimism.
result PASTA correctly identifies optimal assortment with minimal data coverage.
The paper develops algorithms for finding metrics with prescribed combinatorial curvature on polyhedral surfaces.
problem Finding metrics with prescribed combinatorial curvature on polyhedral surfaces.
method Discrete uniformization theorem, combinatorial α-Yamabe flow, combinatorial α-Calabi flow, edge flipping surgery.
result Longtime existence and convergence of combinatorial α-Yamabe flow and combinatorial α-Calabi flow with surgery.
The paper introduces combinatorial curvature and flow for polyhedral surfaces, proving rigidity and solving the Yamabe problem.
problem Discrete conformal structures on polyhedral surfaces and their rigidity.
method Parameterized combinatorial curvature, combinatorial α-Ricci flow, and flow extension through singularities.
result Existence and convergence of combinatorial α-Ricci flow for solving the Yamabe problem.
Unified framework for CO problems using RL, providing optimal solutions and convergence guarantees.
problem Combinatorial optimization problems
method Unified framework of Markov decision processes (MDPs) and value-based reinforcement learning (RL) techniques
result RL techniques converge to approximate solutions with a guarantee on optimality gap
For triangulated surfaces, we introduce the combinatorial Calabi flow which is an analogue of smooth Calabi flow. We prove that the solution of combinatorial Calabi flow exists for all time. Moreover, the solution converges if and only if Thurston's circle packing exists. As a consequence, combinatorial Calabi flow pro…
Multinomial logit bandit is a sequential subset selection problem which arises in many applications. In each round, the player selects a K-cardinality subset from N candidate items, and receives a reward which is governed by a {\it multinomial logit} (MNL) choice model considering both item utility and substitution…
Fractional combinatorial flow improves surface conformal structures.
problem Improving discrete conformal structures on surfaces.
method Introducing a fractional combinatorial Calabi flow for discrete conformal structures on surfaces.
result Longtime existence and global convergence of the fractional combinatorial Calabi flow for various surface types.
Data science relies on pipelines that are organized in the form of interdependent computational steps. Each step consists of various candidate algorithms that maybe used for performing a particular function. Each algorithm consists of several hyperparameters. Algorithms and hyperparameters must be optimized as a whole …
Combinatorial method computes Legendrian knot invariant.
problem Computing the Heegaard Floer contact invariant for Legendrian knots.
method Combining Plamenevskaya's combinatorial description with Heegaard Floer theory.
result Hat version of LOSS invariant can be computed combinatorially.
Polynomial-time method solves complex combinatorial semi-bandits.
problem Optimal strategies for combinatorial semi-bandits with uncorrelated Gaussian rewards.
method Proposes a polynomial-time method to solve the Graves-Lai optimization problem for various combinatorial structures.
result First known approach to implement asymptotically optimal algorithms in polynomial time for combinatorial semi-bandits.
New combinatorial structure for hierarchically hyperbolic spaces.
problem Constructing new hierarchically hyperbolic spaces.
method Combinatorial hierarchical hyperbolicity criterion to construct and clarify HHS structures.
result HHSs admit a combinatorial structure, clarifying the application of the combinatorial HHS criterion.
New method finds metrics on surfaces with prescribed curvatures using circle packings and surgery.
problem Finding piecewise Euclidean metrics on surfaces with prescribed combinatorial curvatures.
method Combinatorial curvature flows with surgery for inversive distance circle packings.
result Longtime existence and global convergence of combinatorial curvature flows with surgery.
Combinatorial Ricci flow finds hyperbolic metrics on 3-manifolds.
problem Finding complete hyperbolic metrics on cusped 3-manifolds.
method Analogue of surface and compact 3-manifold flows, minimizing co-volume, extending through singularities.
result Existence of complete hyperbolic metric is equivalent to flow convergence.
In this article we give combinatorial criteria to decide whether a transitive cyclic combinatorial d-manifold can be generalized to an infinite family of such complexes, together with an explicit construction in the case that such a family exists. In addition, we substantially extend the classification of combinatorial…
Pure combinatorial models for BPL_n and Gauss map of a combinatorial manifold are described.
The elastic net was introduced as a heuristic algorithm for combinatorial optimisation and has been applied, among other problems, to biological modelling. It has an energy function which trades off a fitness term against a tension term. In the original formulation of the algorithm the tension term was implicitly based…