{"total":98,"rows":[{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471,"area":null},{"id":"2511.08544","title":"LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics","created":"2025-11-11","cited_by_count":254,"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":"2206.11168","title":"Ordered Subgraph Aggregation Networks","created":"2022-06-22","cited_by_count":57,"area":null},{"id":"2202.07559","title":"Unsupervised Learning of Group Invariant and Equivariant Representations","created":"2022-02-15","cited_by_count":39,"area":null},{"id":"2104.06456","title":"Single Image Depth Estimation: An Overview","created":"2021-04-13","cited_by_count":35,"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":"2105.04019","title":"Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision","created":"2021-05-09","cited_by_count":31,"area":null},{"id":"2106.03593","title":"Neural Auction: End-to-End Learning of Auction Mechanisms for E-Commerce Advertising","created":"2021-06-07","cited_by_count":31,"area":null},{"id":"2212.13185","title":"Generalized Differentiable RANSAC","created":"2022-12-26","cited_by_count":30,"area":null},{"id":"2306.02738","title":"A Large-Scale Study of Probabilistic Calibration in Neural Network Regression","created":"2023-06-05","cited_by_count":27,"area":null},{"id":"2308.15651","title":"Ensuring User-side Fairness in Dynamic Recommender Systems","created":"2023-08-29","cited_by_count":27,"area":null},{"id":"2302.01425","title":"Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective","created":"2023-02-02","cited_by_count":26,"area":null},{"id":"2306.02866","title":"Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance","created":"2023-06-05","cited_by_count":26,"area":null},{"id":"2203.09630","title":"Monotonic Differentiable Sorting Networks","created":"2022-03-17","cited_by_count":25,"area":null},{"id":"2104.09856","title":"Permutation-Invariant Variational Autoencoder for Graph-Level Representation Learning","created":"2021-04-20","cited_by_count":23,"area":null},{"id":"2202.12183","title":"Large-scale Stochastic Optimization of NDCG Surrogates for Deep Learning with Provable Convergence","created":"2022-02-24","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":"2206.07290","title":"Differentiable Top-k Classification Learning","created":"2022-06-15","cited_by_count":21,"area":null},{"id":"2306.12330","title":"ProtoGate: Prototype-based Neural Networks with Global-to-local Feature Selection for Tabular Biomedical Data","created":"2023-06-21","cited_by_count":18,"area":null},{"id":"2106.03257","title":"Structured Reordering for Modeling Latent Alignments in Sequence Transduction","created":"2021-06-06","cited_by_count":17,"area":null},{"id":"2403.00323","title":"Softened Symbol Grounding for Neuro-symbolic Systems","created":"2024-03-01","cited_by_count":16,"area":null},{"id":"2110.15797","title":"Discovering Non-monotonic Autoregressive Orderings with Variational Inference","created":"2021-10-27","cited_by_count":15,"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":"2106.07877","title":"Learning Revenue-Maximizing Auctions With Differentiable Matching","created":"2021-06-15","cited_by_count":14,"area":null},{"id":"2204.06521","title":"Optimizing generalized Gini indices for fairness in rankings","created":"2022-04-02","cited_by_count":13,"area":null},{"id":"2301.02009","title":"Learning by Sorting: Self-supervised Learning with Group Ordering Constraints","created":"2023-01-05","cited_by_count":13,"area":null},{"id":"2503.06242","title":"LapSum -- One Method to Differentiate Them All: Ranking, Sorting and Top-k Selection","created":"2025-03-08","cited_by_count":13,"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":"2302.04336","title":"Performative Recommendation: Diversifying Content via Strategic Incentives","created":"2023-02-08","cited_by_count":12,"area":null},{"id":"2502.07962","title":"ESPFormer: Doubly-Stochastic Attention with Expected Sliced Transport Plans","created":"2025-02-11","cited_by_count":10,"area":null},{"id":"2508.05673","title":"Breaking the Top-$K$ Barrier: Advancing Top-$K$ Ranking Metrics Optimization in Recommender Systems","created":"2025-08-04","cited_by_count":9,"area":null},{"id":"2103.12476","title":"Differentiable Agent-Based Simulation for Gradient-Guided Simulation-Based Optimization","created":"2021-03-23","cited_by_count":8,"area":null},{"id":"2103.09656","title":"Set-to-Sequence Methods in Machine Learning: a Review","created":"2021-03-17","cited_by_count":6,"area":null},{"id":"2204.13001","title":"Relevance-based Margin for Contrastively-trained Video Retrieval Models","created":"2022-04-27","cited_by_count":6,"area":null},{"id":"2210.02159","title":"Differentiable Mathematical Programming for Object-Centric Representation Learning","created":"2022-10-05","cited_by_count":6,"area":null},{"id":"2305.19999","title":"Beam Tree Recursive Cells","created":"2023-05-31","cited_by_count":6,"area":null},{"id":"2307.04001","title":"Polynomial Width is Sufficient for Set Representation with High-dimensional Features","created":"2023-07-08","cited_by_count":6,"area":null},{"id":"2310.10462","title":"Adaptive Neural Ranking Framework: Toward Maximized Business Goal for Cascade Ranking Systems","created":"2023-10-16","cited_by_count":6,"area":null},{"id":"2312.04658","title":"PAC-Bayes Generalization Certificates for Learned Inductive Conformal Prediction","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2403.11964","title":"Probabilistic Calibration by Design for Neural Network Regression","created":"2024-03-18","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":"2308.13252","title":"Kissing to Find a Match: Efficient Low-Rank Permutation Representation","created":"2023-08-25","cited_by_count":5,"area":null},{"id":"2404.16828","title":"Made to Order: Discovering monotonic temporal changes via self-supervised video ordering","created":"2024-04-25","cited_by_count":5,"area":null},{"id":"2110.14002","title":"CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator","created":"2021-10-26","cited_by_count":4,"area":null},{"id":"2201.11103","title":"Auto-Compressing Subset Pruning for Semantic Image Segmentation","created":"2022-01-26","cited_by_count":4,"area":null},{"id":"2205.10018","title":"NMA: Neural Multi-slot Auctions with Externalities for Online Advertising","created":"2022-05-20","cited_by_count":4,"area":null},{"id":"2310.07174","title":"Generalized Neural Sorting Networks with Error-Free Differentiable Swap Functions","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2402.02644","title":"Permutation-based Inference for Variational Learning of Directed Acyclic Graphs","created":"2024-02-04","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":"2509.03733","title":"Differentiable Entropy Regularization: A Complexity-Aware Approach for Neural Optimization","created":"2025-09-03","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":"2305.16841","title":"Differentiable Random Partition Models","created":"2023-05-26","cited_by_count":3,"area":null},{"id":"2308.01566","title":"Fast Slate Policy Optimization: Going Beyond Plackett-Luce","created":"2023-08-03","cited_by_count":3,"area":null},{"id":"2404.08860","title":"Enhancing Mobile \"How-to\" Queries with Automated Search Results Verification and Reranking","created":"2024-04-13","cited_by_count":3,"area":null},{"id":"2406.17475","title":"Performative Debias with Fair-exposure Optimization Driven by Strategic Agents in Recommender Systems","created":"2024-06-25","cited_by_count":3,"area":null},{"id":"2411.13322","title":"Scaling Laws for Online Advertisement Retrieval","created":"2024-11-20","cited_by_count":3,"area":null},{"id":"2510.11472","title":"Differentiable Fast Top-K Selection for Large-Scale Recommendation","created":"2025-10-13","cited_by_count":3,"area":null},{"id":"2202.13197","title":"Relational Surrogate Loss Learning","created":"2022-02-26","cited_by_count":2,"area":null},{"id":"2409.04495","title":"Learning to Solve Combinatorial Optimization under Positive Linear Constraints via Non-Autoregressive Neural Networks","created":"2024-09-06","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":"2503.09492","title":"Learning Cascade Ranking as One Network","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2505.15661","title":"Deep greedy unfolding: Sorting out argsorting in greedy sparse recovery algorithms","created":"2025-05-21","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":"2110.04971","title":"A Deep Generative Model for Reordering Adjacency Matrices","created":"2021-10-11","cited_by_count":1,"area":null},{"id":"2110.06880","title":"A Survey of Online Auction Mechanism Design Using Deep Learning Approaches","created":"2021-10-11","cited_by_count":1,"area":null},{"id":"2201.00695","title":"An Efficient Combinatorial Optimization Model Using Learning-to-Rank Distillation","created":"2021-12-24","cited_by_count":1,"area":null},{"id":"2205.00694","title":"A Multi-stage deep architecture for summary generation of soccer videos","created":"2022-05-02","cited_by_count":1,"area":null},{"id":"2206.01370","title":"Towards Improving the Generation Quality of Autoregressive Slot VAEs","created":"2022-06-03","cited_by_count":1,"area":null},{"id":"2212.05124","title":"Multi-view Graph Convolutional Networks with Differentiable Node Selection","created":"2022-12-09","cited_by_count":1,"area":null},{"id":"2407.16058","title":"Revisiting Score Function Estimators for $k$-Subset Sampling","created":"2024-07-22","cited_by_count":1,"area":null},{"id":"2502.05416","title":"Deep Generative Models with Hard Linear Equality Constraints","created":"2025-02-08","cited_by_count":1,"area":null},{"id":"2511.11427","title":"Comprehension of Multilingual Expressions Referring to Target Objects in Visual Inputs","created":"2025-11-14","cited_by_count":1,"area":null},{"id":"2304.13033","title":"SmartChoices: Augmenting Software with Learned Implementations","created":"2023-04-12","cited_by_count":0,"area":null},{"id":"2304.13594","title":"Diffsurv: Differentiable sorting for censored time-to-event data","created":"2023-04-26","cited_by_count":0,"area":null},{"id":"2306.15445","title":"UniUD Submission to the EPIC-Kitchens-100 Multi-Instance Retrieval Challenge 2023","created":"2023-06-27","cited_by_count":0,"area":null},{"id":"2411.01956","title":"EXAGREE: Mitigating Explanation Disagreement with Stakeholder-Aligned Models","created":"2024-11-04","cited_by_count":0,"area":null},{"id":"2411.03253","title":"Discovering Data Structures: Nearest Neighbor Search and Beyond","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2505.24664","title":"Learning Distributions over Permutations and Rankings with Factorized Representations","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2506.02694","title":"XicorAttention: Time Series Transformer Using Attention with Nonlinear Correlation","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2508.14180","title":"RewardRank: Optimizing True Learning-to-Rank Utility","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2511.09093","title":"Factorization-in-Loop: Proximal Fill-in Minimization for Sparse Matrix Reordering","created":"2025-11-12","cited_by_count":0,"area":null},{"id":"2511.14482","title":"Gradient-Based Join Ordering","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2512.17678","title":"You Only Train Once: Differentiable Subset Selection for Omics Data","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2512.22587","title":"Structural Incompatibility of Differentiable Sorting and Within-Vector Rank Normalization","created":"2025-12-27","cited_by_count":0,"area":null},{"id":"2601.09522","title":"Class Adaptive Conformal Training","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2603.17353","title":"Learning Permutation Distributions via Reflected Diffusion on Ranks","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2604.04087","title":"ArrowFlow: Hierarchical Machine Learning in the Space of Permutations","created":"2026-04-05","cited_by_count":0,"area":null},{"id":"2604.13796","title":"Driving Engagement in Daily Fantasy Sports with a Scalable and Urgency-Aware Ranking Engine","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2604.26181","title":"SWAN: World-Aware Adaptive Multimodal Networks for Runtime Variations","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.00915","title":"Learning Dynamic Evidence Routes for Vision Transformer Probing","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":"2605.09112","title":"Contextual Plackett-Luce: An Efficient Neural Model for Probabilistic Sequence Selection under Ambiguity","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.25551","title":"Learning Permutation from Structure Without Supervision","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.08565","title":"EinSort: Sorting is All We Need for Tensorizing LLM","created":"2026-06-07","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}],"next_cursor":null}