{"total":60,"rows":[{"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":"2106.01798","title":"Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions","created":"2021-06-03","cited_by_count":98,"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":"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":"2206.11168","title":"Ordered Subgraph Aggregation Networks","created":"2022-06-22","cited_by_count":57,"area":null},{"id":"2203.08509","title":"Differentiable DAG Sampling","created":"2022-03-16","cited_by_count":47,"area":null},{"id":"2210.01941","title":"SIMPLE: A Gradient Estimator for $k$-Subset Sampling","created":"2022-10-04","cited_by_count":34,"area":null},{"id":"2207.05984","title":"Unsupervised Learning for Combinatorial Optimization with Principled Objective Relaxation","created":"2022-07-13","cited_by_count":32,"area":null},{"id":"2310.15978","title":"Graph Deep Learning for Time Series Forecasting","created":"2023-10-24","cited_by_count":26,"area":null},{"id":"2205.13492","title":"Sparse Graph Learning from Spatiotemporal Time Series","created":"2022-05-26","cited_by_count":22,"area":null},{"id":"2110.05651","title":"Learning with Algorithmic Supervision via Continuous Relaxations","created":"2021-10-11","cited_by_count":21,"area":null},{"id":"2312.17241","title":"Compact Neural Graphics Primitives with Learned Hash Probing","created":"2023-12-28","cited_by_count":19,"area":null},{"id":"2208.04055","title":"Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions","created":"2022-08-08","cited_by_count":14,"area":null},{"id":"2305.16358","title":"Differentiable Clustering with Perturbed Spanning Forests","created":"2023-05-25","cited_by_count":14,"area":null},{"id":"2301.12047","title":"Backpropagation of Unrolled Solvers with Folded Optimization","created":"2023-01-28","cited_by_count":13,"area":null},{"id":"2102.09050","title":"End-to-end learnable EEG channel selection for deep neural networks with Gumbel-softmax","created":"2021-02-11","cited_by_count":12,"area":null},{"id":"2209.04862","title":"Adaptive Perturbation-Based Gradient Estimation for Discrete Latent Variable Models","created":"2022-09-11","cited_by_count":12,"area":null},{"id":"2106.02206","title":"Stochastic Iterative Graph Matching","created":"2021-06-04","cited_by_count":10,"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":"2301.11898","title":"DAG Learning on the Permutahedron","created":"2023-01-27","cited_by_count":9,"area":null},{"id":"2206.07235","title":"Training Discrete Deep Generative Models via Gapped Straight-Through Estimator","created":"2022-06-15","cited_by_count":8,"area":null},{"id":"2110.15072","title":"Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces","created":"2021-10-28","cited_by_count":7,"area":null},{"id":"2208.06124","title":"Gradient Estimation for Binary Latent Variables via Gradient Variance Clipping","created":"2022-08-12","cited_by_count":7,"area":null},{"id":"2211.10420","title":"Mirror Sinkhorn: Fast Online Optimization on Transport Polytopes","created":"2022-11-18","cited_by_count":6,"area":null},{"id":"2407.05920","title":"LPGD: A General Framework for Backpropagation through Embedded Optimization Layers","created":"2024-07-08","cited_by_count":6,"area":null},{"id":"2203.01629","title":"Learning Group Importance using the Differentiable Hypergeometric Distribution","created":"2022-03-03","cited_by_count":5,"area":null},{"id":"2303.15311","title":"Improving Dual-Encoder Training through Dynamic Indexes for Negative Mining","created":"2023-03-27","cited_by_count":5,"area":null},{"id":"2306.15103","title":"Structured Dialogue Discourse Parsing","created":"2023-06-26","cited_by_count":4,"area":null},{"id":"2510.24039","title":"Geometric Algorithms for Neural Combinatorial Optimization with Constraints","created":"2025-10-28","cited_by_count":4,"area":null},{"id":"2105.14038","title":"Learning to Extend Program Graphs to Work-in-Progress Code","created":"2021-05-28","cited_by_count":3,"area":null},{"id":"2209.12590","title":"Learning to Drop Out: An Adversarial Approach to Training Sequence VAEs","created":"2022-09-26","cited_by_count":3,"area":null},{"id":"2308.10077","title":"Contrastive Learning for Non-Local Graphs with Multi-Resolution Structural Views","created":"2023-08-19","cited_by_count":3,"area":null},{"id":"2411.00119","title":"Soft Condorcet Optimization for Ranking of General Agents","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2108.02658","title":"Sparse Communication via Mixed Distributions","created":"2021-08-05","cited_by_count":2,"area":null},{"id":"2112.03638","title":"Scaling Structured Inference with Randomization","created":"2021-12-07","cited_by_count":2,"area":null},{"id":"2205.01324","title":"Learning Discrete Structured Variational Auto-Encoder using Natural Evolution Strategies","created":"2022-05-03","cited_by_count":2,"area":null},{"id":"2206.02761","title":"Dual Decomposition of Convex Optimization Layers for Consistent Attention in Medical Images","created":"2022-06-06","cited_by_count":2,"area":null},{"id":"2307.14193","title":"Efficient Learning of Discrete-Continuous Computation Graphs","created":"2023-07-26","cited_by_count":2,"area":null},{"id":"2308.03291","title":"SynJax: Structured Probability Distributions for JAX","created":"2023-08-07","cited_by_count":2,"area":null},{"id":"2402.07772","title":"End-to-End Learning for Fair Multiobjective Optimization Under Uncertainty","created":"2024-02-12","cited_by_count":2,"area":null},{"id":"2509.15641","title":"Information Geometry of Variational Bayes","created":"2025-09-19","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":"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":"2209.05212","title":"Structured Recognition for Generative Models with Explaining Away","created":"2022-09-12","cited_by_count":1,"area":null},{"id":"2309.13459","title":"A Model-Agnostic Graph Neural Network for Integrating Local and Global Information","created":"2023-09-23","cited_by_count":1,"area":null},{"id":"2312.17394","title":"Analyzing and Enhancing the Backward-Pass Convergence of Unrolled Optimization","created":"2023-12-28","cited_by_count":1,"area":null},{"id":"2406.01162","title":"Conditional Gumbel-Softmax for constrained feature selection with application to node selection in wireless sensor networks","created":"2024-06-03","cited_by_count":1,"area":null},{"id":"2606.14283","title":"DIFF-ERO: A Conformance-Aware Loss for Deep Learning in Process Mining","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2210.09428","title":"Improving Low-Resource Cross-lingual Parsing with Expected Statistic Regularization","created":"2022-10-17","cited_by_count":0,"area":null},{"id":"2301.06122","title":"CORE: Learning Consistent Ordinal REpresentations for Image Ordinal Estimation","created":"2023-01-15","cited_by_count":0,"area":null},{"id":"2311.12917","title":"Orchard: building large cancer phylogenies using stochastic combinatorial search","created":"2023-11-21","cited_by_count":0,"area":null},{"id":"2402.10339","title":"What to Do When Your Discrete Optimization Is the Size of a Neural Network?","created":"2024-02-15","cited_by_count":0,"area":null},{"id":"2410.12492","title":"End-to-end Planner Training for Language Modeling","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2410.17415","title":"End-to-End Optimization and Learning of Fair Court Schedules","created":"2024-10-22","cited_by_count":0,"area":null},{"id":"2505.23546","title":"Going from a Representative Agent to Counterfactuals in Combinatorial Choice","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2509.24728","title":"Beyond Softmax: A Natural Parameterization for Categorical Random Variables","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2606.08497","title":"Explaining Black-Box Language Models: Learning to Optimize Linguistically-Structured Word Subsets","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2607.11146","title":"Rank-Conditioned Sample Reuse for the Plackett--Luce Best-of-$K$ Objective","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.12127","title":"Connected by Construction: Learning Tractable Near-Tour Marginals for Traveling Salesman Problems","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.20636","title":"MIL-BERT: Classification of Arbitrarily Large Text with Performance and Explanatory Guarantees","created":"2026-08-21","cited_by_count":0,"area":null}],"next_cursor":null}