{"total":81,"rows":[{"id":"2103.16378","title":"End-to-End Constrained Optimization Learning: A Survey","created":"2021-03-30","cited_by_count":157,"area":null},{"id":"2307.13565","title":"Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunities","created":"2023-07-25","cited_by_count":130,"area":null},{"id":"2110.01515","title":"A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning","created":"2021-10-04","cited_by_count":82,"area":null},{"id":"2306.10374","title":"A Survey of Contextual Optimization Methods for Decision Making under Uncertainty","created":"2023-06-17","cited_by_count":82,"area":null},{"id":"2104.03059","title":"Differentiable Patch Selection for Image Recognition","created":"2021-04-07","cited_by_count":68,"area":null},{"id":"2210.08277","title":"Deep Differentiable Logic Gate Networks","created":"2022-10-15","cited_by_count":67,"area":null},{"id":"2103.17202","title":"GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection","created":"2021-03-31","cited_by_count":66,"area":null},{"id":"2103.01826","title":"Strategic Classification Made Practical","created":"2021-03-02","cited_by_count":59,"area":null},{"id":"2111.11591","title":"Efficient Video Transformers with Spatial-Temporal Token Selection","created":"2021-11-23","cited_by_count":59,"area":null},{"id":"2105.02343","title":"CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints","created":"2021-05-05","cited_by_count":49,"area":null},{"id":"2206.14234","title":"PyEPO: A PyTorch-based End-to-End Predict-then-Optimize Library for Linear and Integer Programming","created":"2022-06-28","cited_by_count":32,"area":null},{"id":"2205.15213","title":"Backpropagation through Combinatorial Algorithms: Identity with Projection Works","created":"2022-05-30","cited_by_count":29,"area":"lr"},{"id":"2207.13513","title":"Learning with Combinatorial Optimization Layers: a Probabilistic Approach","created":"2022-07-27","cited_by_count":29,"area":null},{"id":"2110.12351","title":"Integrated Conditional Estimation-Optimization","created":"2021-10-24","cited_by_count":25,"area":null},{"id":"2110.05651","title":"Learning with Algorithmic Supervision via Continuous Relaxations","created":"2021-10-11","cited_by_count":21,"area":null},{"id":"2202.07570","title":"ScoreNet: Learning Non-Uniform Attention and Augmentation for Transformer-Based Histopathological Image Classification","created":"2022-02-15","cited_by_count":21,"area":null},{"id":"2206.07290","title":"Differentiable Top-k Classification Learning","created":"2022-06-15","cited_by_count":21,"area":null},{"id":"2110.03360","title":"Sparse MoEs meet Efficient Ensembles","created":"2021-10-07","cited_by_count":19,"area":null},{"id":"2103.09879","title":"Self-Supervised Learning of Audio Representations from Permutations with Differentiable Ranking","created":"2021-03-17","cited_by_count":14,"area":null},{"id":"2204.13845","title":"GenDR: A Generalized Differentiable Renderer","created":"2022-04-29","cited_by_count":12,"area":null},{"id":"2102.07456","title":"Neuro-algorithmic Policies enable Fast Combinatorial Generalization","created":"2021-02-15","cited_by_count":11,"area":null},{"id":"2301.13395","title":"Differentiating Through Integer Linear Programs with Quadratic Regularization and Davis-Yin Splitting","created":"2023-01-31","cited_by_count":11,"area":null},{"id":"2106.03188","title":"Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach","created":"2021-06-06","cited_by_count":10,"area":null},{"id":"2202.02193","title":"Stochastic smoothing of the top-K calibrated hinge loss for deep imbalanced classification","created":"2022-02-04","cited_by_count":10,"area":null},{"id":"2411.12355","title":"DynFocus: Dynamic Cooperative Network Empowers LLMs with Video Understanding","created":"2024-11-19","cited_by_count":10,"area":null},{"id":"2311.07633","title":"Benchmarking PtO and PnO Methods in the Predictive Combinatorial Optimization Regime","created":"2023-11-13","cited_by_count":8,"area":null},{"id":"2312.07718","title":"CaVE: A Cone-Aligned Approach for Fast Predict-then-optimize with Binary Linear Programs","created":"2023-12-12","cited_by_count":8,"area":null},{"id":"2106.09761","title":"Unsupervised Resource Allocation with Graph Neural Networks","created":"2021-06-17","cited_by_count":7,"area":null},{"id":"2110.09107","title":"Differentiable Rendering with Perturbed Optimizers","created":"2021-10-18","cited_by_count":7,"area":null},{"id":"2505.19053","title":"Structured Reinforcement Learning for Combinatorial Decision-Making","created":"2025-05-25","cited_by_count":7,"area":"deeprl"},{"id":"2302.10128","title":"Sketch In, Sketch Out: Accelerating both Learning and Inference for Structured Prediction with Kernels","created":"2023-02-20","cited_by_count":5,"area":null},{"id":"2310.04328","title":"Robust Losses for Decision-Focused Learning","created":"2023-10-06","cited_by_count":5,"area":null},{"id":"2510.04318","title":"Adaptive Coverage Policies in Conformal Prediction","created":"2025-10-05","cited_by_count":5,"area":null},{"id":"2101.01082","title":"Learning to solve the single machine scheduling problem with release times and sum of completion times","created":"2021-01-04","cited_by_count":4,"area":null},{"id":"2110.01532","title":"Differentiable Spline Approximations","created":"2021-10-04","cited_by_count":4,"area":null},{"id":"2405.14273","title":"Exact Solution to Data-Driven Inverse Optimization of MILPs in Finite Time via Gradient-Based Methods","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2410.08125","title":"Generalizing Stochastic Smoothing for Differentiation and Gradient Estimation","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2605.14019","title":"Regret Equals Covariance: A Closed-Form Characterization for Stochastic Optimization","created":"2026-05-13","cited_by_count":4,"area":null},{"id":"2105.01480","title":"Neural Weighted A*: Learning Graph Costs and Heuristics with Differentiable Anytime A*","created":"2021-05-04","cited_by_count":3,"area":null},{"id":"2307.16304","title":"You Shall Pass: Dealing with the Zero-Gradient Problem in Predict and Optimize for Convex Optimization","created":"2023-07-30","cited_by_count":3,"area":null},{"id":"2407.17200","title":"Generalization Bounds of Surrogate Policies for Combinatorial Optimization Problems","created":"2024-07-24","cited_by_count":3,"area":null},{"id":"2505.11360","title":"Efficient End-to-End Learning for Decision-Making: A Meta-Optimization Approach","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2601.10583","title":"Combinatorial Optimization Augmented Machine Learning","created":"2026-01-15","cited_by_count":3,"area":"deeprl"},{"id":"2605.00649","title":"Model Compression with Exact Budget Constraints via Riemannian Manifolds","created":"2026-05-01","cited_by_count":3,"area":null},{"id":"2605.12754","title":"Constraint-Aware Flow Matching: Decision Aligned End-to-End Training for Constrained Sampling","created":"2026-05-12","cited_by_count":3,"area":"diffusion"},{"id":"2108.02658","title":"Sparse Communication via Mixed Distributions","created":"2021-08-05","cited_by_count":2,"area":null},{"id":"2110.01773","title":"Differentiable Equilibrium Computation with Decision Diagrams for Stackelberg Models of Combinatorial Congestion Games","created":"2021-10-05","cited_by_count":2,"area":null},{"id":"2111.11358","title":"A Surrogate Objective Framework for Prediction+Optimization with Soft Constraints","created":"2021-11-22","cited_by_count":2,"area":null},{"id":"2302.14473","title":"Implicit Bilevel Optimization: Differentiating through Bilevel Optimization Programming","created":"2023-02-28","cited_by_count":2,"area":null},{"id":"2311.15112","title":"Everybody Needs a Little HELP: Explaining Graphs via Hierarchical Concepts","created":"2023-11-25","cited_by_count":2,"area":null},{"id":"2410.19055","title":"Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms","created":"2024-10-24","cited_by_count":2,"area":null},{"id":"2505.03953","title":"Sufficient Decision Proxies for Decision-Focused Learning","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2505.14240","title":"Learning with Local Search MCMC Layers","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2603.08824","title":"SoftJAX & SoftTorch: Empowering Automatic Differentiation Libraries with Informative Gradients","created":"2026-03-09","cited_by_count":2,"area":null},{"id":"2607.22263","title":"Explicit Iteration Complexity of Exact Data-Driven Inverse Optimization for Integer Linear Programs","created":"2026-07-24","cited_by_count":2,"area":null},{"id":"2104.00755","title":"Reconciling the Discrete-Continuous Divide: Towards a Mathematical Theory of Sparse Communication","created":"2021-04-01","cited_by_count":1,"area":null},{"id":"2412.08287","title":"DistrictNet: Decision-aware learning for geographical districting","created":"2024-12-11","cited_by_count":1,"area":null},{"id":"2503.05622","title":"Decision-aware training of spatiotemporal forecasting models to select a top K subset of sites for intervention","created":"2025-03-07","cited_by_count":1,"area":null},{"id":"2601.21775","title":"Differentiable Knapsack and Top-k Operators via Dynamic Programming","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2606.01081","title":"Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2105.12697","title":"Structural Causal Models Reveal Confounder Bias in Linear Program Modelling","created":"2021-05-26","cited_by_count":0,"area":null},{"id":"2203.15274","title":"Finding Structure and Causality in Linear Programs","created":"2022-03-29","cited_by_count":0,"area":null},{"id":"2405.18293","title":"CF-OPT: Counterfactual Explanations for Structured Prediction","created":"2024-05-28","cited_by_count":0,"area":null},{"id":"2406.02180","title":"On The Statistical Representation Properties Of The Perturb-Softmax And The Perturb-Argmax Probability Distributions","created":"2024-06-04","cited_by_count":0,"area":null},{"id":"2508.20978","title":"Scaling Neuro-symbolic Problem Solving: Solver-Free Learning of Constraints and Objectives","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2510.16015","title":"Decision-focused Sensing and Forecasting for Adaptive and Rapid Flood Response: An Implicit Learning Approach","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2603.07606","title":"TT-Sparse: Learning Sparse Rule Models with Differentiable Truth Tables","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2603.17139","title":"Contextual Preference Distribution Learning","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.04328","title":"Soft Tournament Equilibrium: Differentiable Set-Valued Inference for Non-Transitive Pairwise Comparisons","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2604.26297","title":"NeuroPlastic: A Plasticity-Modulated Optimizer for Biologically Inspired Learning Dynamics","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.06210","title":"Super-Level-Set Regression: Conditional Quantiles via Volume Minimization","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.10979","title":"Bellman-Taylor Score Decoding for Markov Decision Processes with State-Dependent Feasible Action Sets","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2607.24007","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.04057","title":"LaPrune: Controllable Differentiable Sparsity at Million Scale","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.06912","title":"Fast LapSum: Exact Differentiable Top-$k$ at Million Scale","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.10650","title":"Decision-Aware Approximation of Belief Functions for Evidential Combinatorial Optimization","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.01807","title":"SPD: Single Pass Decoding for Generative Reranking","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.23242","title":"Proximal Residual Value Functions for Consistent Planning and Real-Time Execution","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.37065","title":"RL-PaO: Prediction as Action in Decision Making under Uncertainty","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38363","title":"Simulator-Refined Diffusion for Radio-Frequency Inverse Design","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.01823","title":"Generalized Engression Models","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}